Current IssueSpecial IssueEditorial BoardOnline First ArticlesArchive
Current IssueSpecial IssueEditorial BoardOnline First ArticlesArchive

Review Article

Artificial Intelligence in Crop Management: A Review

N
Neroju Manasa1,*
G
Guda Bhargavi1
K
Kasula Vamshi Krishna2
J
J. Vamshi3
B
B. Bhavana4
1Department of Agronomy, SR University, Warangal-506 371, Telangana, India.
2Department of Agronomy, SoAS, Malla Reddy University, Hyderabad-500 043, Telangana, India.
3Department of Plant Pathology, UIAH, Agriculture, Guru Nanak University, Ibrahimpatnam-501 506, Telangana, India.
4Department of Agronomy, SoAS, Malla Reddy University, Hyderabad-500 043, Telangana, India.

ABSTRACT

Artificial Intelligence (AI) is gradually becoming more prevalent in agriculture by providing technology for crop cultivation, pests control, soil monitoring and data processing. This kind of technology also enables farmers to make decisions of planting seeds as the technology reveals whether seeds suitable for a given area and even climate information. AI can help farmers get more profit from their produce when applied, improve on quality and make marketing more efficient. To improve the status of the soil it also avails the right nutrients and gives information on the quality of the soil. Precision can be improved by adjusting the spacing and planting width and depth functions with technology. In addition, the use of AI incorporated in health monitoring systems ensures that data regarding the state of the crops and their nutritional requirements are well obtained reducing the time it takes to get high yields of good stocks and an enhanced quantity is produced. AI integrated with Machine learning (ML) technology has revolutionized farming by agile farming, precision farming thereby reducing wastage and promoting sustainable farming. Measures of plant and soil health are Hyper-Spectral photography and three-dimensional laser scanning those records large amount of data for analysis. This chapter explores several uses of AI are realized in agriculture including in crop management, pest control and disease control. It also outlines the opportunities as well as the challenges of AI for agriculture for optimization of the yield in agriculture.

INTRODUCTION

Agriculture remains the oldest and essential sector of our global economy where farmers produce what the world needs to live such as food, fibres and energy sources. Industrial agriculture remains the prime employer through worldwide while simultaneously generating substantial economic development through agriculture. According to (Oyakhilomen and Zibah, 2014) current agricultural practices form the basic way people survive, increase national income, expand trade activities, reduce unemployment numbers and give other industries their raw materials while pushing forward the economy. The farming industry makes a large economic impact on India. Agricultural activities use the workforce of more than 60% of the nation’s population which produce about 17% of total economic output. Rural communities rely on agriculture for survival since 70% of their households make their living from the land. During the last several decades Indian agriculture achieved remarkable growth (Arjun, 2013). Despite these challenges, the agricultural industry has continually experienced setbacks associated with factors such as climate change, scarcity of water, soil degradation and the occurrence of pests and diseases within most farms. These obstacles have led to low production and a simultaneous increase in the level of food shortage. The implementation of technology demonstrates a powerful solution to transform agricultural practises while dealing with current agricultural challenges. Modern science considers Artificial Intelligence (AI) as one of its greatest transformative technologies. The integration of artificial intelligence into everyday life keeps expanding our ability to transform our environment (Kundalia et al., 2020). With advancements in both computational power and cloud connectivity AI continues to transform rapidly as various economic sectors gain access to AI benefits. These benefits include weed control and crop harvest timing determination and soil evaluation as well as yield prediction capabilities. AI has undergone testing to serve as development tools across numerous industries since the last ten years. Agricultural decision-making has become a field where AI demonstrates its potential for improvement (Vyas et al., 2022) and (Sharma et al., 2021).
       
Precision farming is one of the broad areas which have already been achieved by increasing the application of artificial intelligence in crop management to the extent that the farmer is in a position to manage field scenarios and input quantities like the quantity of water, fertilisers and pesticides to be used. Automated drones and sensors capture better images and data on nutrient deficiency and disease epidemics for improvement. Monitoring of crop health that may be made through reliable AI models and the farmer is then in a position to make adjustments to reduce the effects of the disease before they are worst experienced. Moreover, through irrigation systems, AI controls the water input because it utilizes the applicable data to know the amount of water in the soil and therefore prevent the wastage of water and maximize the efficiency of water use. Weeds pose a serious hazard to many agricultural activities; presence of weeds reduces agricultural production while destroying crops and killing pastures along with occasional threats to farm cattle. AI sensors perform weed detection by analysing specific areas to select appropriate herbicide treatments. Besides, incidence of pests and diseases which adversely affects production of crops and increases cost of production. The incidences of pests and diseases are alarming since they lead to low yields and high cost of production. Since farmers are not able to employ such techniques, pests and diseases pose a threat to agricultural produce which in turn leads to loss of money and harvest. It is important for these problems to be solved as a way of ensuring the advances in agriculture and the availability of food as well as welfare of the farming people. Therefore, there is increased importance in addressing such challenges, since AI is progressive in identifying solutions towards increased farming practice resilience (Ahmed et al., 2024). It is possible for farmers to keep track of their crops using AI technologies on drones. Experts monitor the pictures taken by the drone and write a report on the farm condition. It makes it easier for farmers to manage pests. In today’s farming, certain farmers have robots that complete time-consuming chores on the farm. They assist farmers by taking over parts of the jobs that are expensive to do by hand. In addition, AI is not only applicable to farm systems but also in supply chain and intelligence of the markets. Using technologies such as AI, farmers and agribusinesses can make informed decisions on things or on aspects like demand, pricing and distribution within the market. However, AI adoption in agriculture has its limitations such as high implementation cost, illiteracy of farmers in the use of digital platforms and final consumer privacy. However, the technology has advanced so much in recent years that government and industry support has made these solutions increasingly easier and cheaper to maintain. One of the powerful approaches that can help overcome such limitations is with specific farmer training programmes and digital literacy campaigns. Trainings on the use of AI tools like drones, sensors and decision support system targeting farmer in hands on trainings, field demonstration and mobile advisory in local languages are facilitated through these initiatives.
 
Need for AI in agriculture
 
Agriculture is a labour and time-consuming, hence with growing population and demand for agricultural produce the efficiency of automation is progressively gaining importance. Specifically, AI benefits farmers in elements as well as componentry’s and paradigms of application and technology. Technology-driven predictive analytics and improved farm and crop management systems to ensure quality crop supply. Satellite images, weather records for identifying the area of the cultivated land and monitoring the condition of crops in real-time (Subeesh and Mehta, 2021). AI, big data and ML are useful in determining the price, projecting production and yield and detecting pest and disease incidence respectively for use in businesses. They can tell farmers the production requirements, which crops to grow for maximum profits, use of chemicals like pesticides and forecast market prices in future. AI technologies are proving great assistance in eliminating traditional barriers in every field of life. Business, transport, medicine and farming are the fields in which AI is used. The global population is growing, but at the same time urbanisation is progressing very rapidly. This is due to the fact that farmers are now under pressure to produce more production to feed the people hence they need a way to do so (Menshchikov et al., 2021). The use of AI on the global scale is perhaps one of the most promising in the agriculture industry. Many of the produce companies are experiencing challenges in managing pests and various illness or diseases that are notorious to the plants (Sharma, 2021). They are compounded by climate change, monoculture practices and the use of pesticides. These aspects come together to give the farmers a new challenge. This is however compounded by aspects such as irregularity of rains, scarce labour force and the annual challenge of output raising. This means that the agricultural industry will require expanding in the forthcoming years incredibly and farm productivity will require doubling if we have to achieve our targets almost. Taking all these challenges into consideration, it is pertinent to understand that AI offers agriculture automation (Blessy, 2021).
 
Role of AI in crop management
 
In today’s global market, various technologies in AI-based are being developed to optimize the market and supply chain, weather forecasting, agricultural analytics and efficiency of crop and soil (Fig 1). Digital agricultural innovation involves the application of cloud computing systems, data structures, IoT and AI. This makes it possible for farmers to employ technical methods of irrigation, fertilisation, disease and pest identification and control, spraying and harvesting. Computer Vision: Applied Artificial Intelligence - Using image and video data - drone cameras, satellite imagery - monitor disease or pests, weather conditions, timing and quantity of chemical sprays, time to harvest, produce shelf life.

Fig 1: Role of AI in crop management (Source: Author).


 
Soil health monitoring
 
Soil can be termed as bedrock of agriculture and therefore ensuring crucial when organising Agri spherical production. Modern methods of determination of soil using the help of various techniques and sensors based on artificial intelligence allow to determine its moisture, nutrient and acidity levels. This information is further fed to the machine learning algorithms to get recommendations on conditions suitable for growth of crops in the soil.
 
Weather forecasting
 
Mobile apps that provide information on weather related issues go a long way in the management of daily agricultural activities. These contribute to the assistance they provide to farmers using weather-based agro alerts besides weather information. Popular mobile applications for weather forecast include Meghdoot, Mausam and Damini endeavours to provide specific crop related weather information for the farming community in India in order to get better access to Climate Information Service. Mobile application known as Meghdoot or Cloud Messenger which was launched in August 2019. Established by ICRISAT’s Digital Agriculture research domain in Hyderabad, IITM, Pune and IMD, New Delhi in collaboration (Lahiri et al., 2024). Meghdoot is a simple and easily accessible mobile application which provides farmers at different places with the advice on cropping in their respective local languages based on the weather information. It is jointly organised by the Indian Council of Agricultural Research (ICAR), Indian Institute of Tropical Meteorology and Indian Meteorological Department (IMD).
 
Water management
 
Irrigation or water management is a labour consuming process necessary for the management of the water availability, the rainfall and the water needs for production in agricultural system. Automated irrigation systems have advantages of more crop yield, less human interferences, less water consumption as compared to the conventional method, more frequency and low volume of water application. A smart irrigation system is an approach of managing and controlling the irrigation in agricultural land through using IoT devices, automation and control technology. According to Kumar et al. (2017), the use of this system indicated that any conventional agricultural practice, which was previously carried out by manpower, can be transformed into an automated process with minimal supervision.
 
Weed management
 
The farmers expected production and profit are always affected by weeds. The survey showed that, failure to control the weeds would lead to scaling down of the dried beans and maize harvest by at least fifty per cent. This could be attributed to the time the crops were exposed to the weeds (Rao et al., 2014). According to the WSSA (Weed Science Society of America), some weeds are capable of opening the path during the wildfire by flooding during hurricanes are toxic and cause fatal liver failure if eaten, some outcompete plants or crops for water, nutrients and soil. There are a few weeds that are toxic, cause allergies or that are otherwise dangerous to the human beings (Swanton and Blackshaw, 2015). Recently, (Pantazi et al., 2016) developed a new algorithm based on machine learning algorithm using hyperspectral imaging for the purposes of crop versus weed classification.
 
Pest and disease detection
 
The role of pests and diseases are that they can considerably reduce crop yields. The online detection of pest and diseases requires the use of image recognition based on the artificial intelligence business that with an application of deep learning, is capable of detecting symptoms at early stages (Mehta et al., 2025). The farmers will be informed of the alerts and recommendations concerning the appropriate treatment, reducing the harm and the use of chemical pesticides.
 
Applications of AI in agriculture
 
By 2050 the global food production must increase by 50%, So the world requires our farmers to grow 50% more food before 2050. According to Bagchi et al., (2021) almost all demand growth will be met by other farming areas rather than opening new farmlands. The current need for higher food production with reduced resources drives the agricultural revolution through AI technology. Technology built with artificial intelligence can support different advancements in agricultural work. The system includes both business recommendations plus analytics platforms that connect to IoT devices and camera equipment (Fig 2).

Fig 2: Applications of AI (Source: Author).


 
Crop and soil analysis monitoring
 
Traditional approaches are usually slow and always tend to be categorically different from what can be observed using the automated digital detection and analysis techniques. Hyper spectral imaging and 3D Laser Scanning are the two methods that can enable improvements in information and plant metrics over thousands of acres at the same spatial resolution. The sensors, cameras and infrared rays help diagnose the health of the soil and measure the nutritional content of the soil. This is also useful to determine the effect of some seeds on the type of land, the impact of changing weather on the soil and the likelihood of spreading diseases and pests (Sandric et al., 2022). With this knowledge, improved crop application rates are achieved, both cost and more yield per hectare for the farmer. However, currently, the Haryana state is using a total of 207.56 kg of chemical fertilizers per hectare per year, which is considered to be rather high among all the other Indian states. Fertilizers are also expensive to acquire and use in the farms and the substances in the fertilizers are often toxic.
 
AI- Automated Irrigation systems
 
Since agriculture is the oldest profession of civilized mankind irrigation systems, it is a very challenging task to irrigate large areas of plant. To address this problem several irrigation scheduling approaches have been put forward which depend on the measurement of the available water in the soil, the water status of the crops and the climatic factors. Irrigation scheduling involves when to irrigate as well as the quantity of water to apply. Based on these characteristics, there are four major types of automated irrigation systems including:
•  Closed loop system based on a predefined irrigation schedule and assumes the control system has complete authority on the quantity and duration of the water to be applied.
•  An open loop hydro-prin that depends on the amount of water to be delivered and the time for irrigation to take place.
•  Volume based system wherein a fixed volume of water is applied for agriculture.
•  System related to clocks which is connected to clock controllers.
 
Improve decision making
 
The use of artificial intelligence in decision-making technology in agriculture is slowly increasing. Increasing information is recorded and subsequently used in the agricultural decision-making process. This has been made possible by increased use of sensors, faster availability of imagery from satellites, comparatively low production costs of data loggers, increased use of drones and more readily available data archives for irrigation, among other things (Banthia and Chaudaki, 2022). This is an elaborate process that requires a lot of human involvement and can be mechanized for efficiency. One can program machines to learn temperature patterns in a region and the soil qualities in order to enhance production. Precision farming uses more manageable and incrementally measurable methods in place of the repetitive and labour-intensive technique used in agriculture.
 
Food supply chain
 
Implementation of AI in agriculture will help the agriculture sector to deliver better crops and also help to improve various agriculture-related activities in the food value chain. It led to a clamour for more foods while promoting employment to more than six billion people as part of the whole system. This has been achieved through the incorporation of AI in the agricultural industry which has catalysed what may be best described as an agricultural revolution. It has protected crop production from population pressure, climate change, source of income and food-borne crisis. AI in crop management and yield has a lot of potential, but there are a few disadvantages on the application of these new forms of AI that experts believe have not yet been identified. Building AI models for increasing economic efficiency and sustainability supports the path of development of new models using suitable scale management strategies and technologies for the managers of farm and forest.
 
AI technologies in crop management
 
Remote sensing and drones
 
Satellite and aerial images, in the current world, are widely used in the observation and assessment of crop vigor and the state of soil humidity and other conditions that affect crop productivity. These technologies have changed the ways through which farmers and agribusiness adopt the practice of farming empowering them to monitor and decide on the health of crops (Cucho-Padin et al., 2020). Satellite information provides the possibility of having different spatial resolution from kilometres up to hundreds and tens of meters. Many of these lower resolution products are publicly available, but they are not suitable for the small-scale farming. Even today, the satellite systems that possess some of the highest spatial resolutions that are measured in meters, including just a few meters, are relatively costly and this is a factor that needs to be reduced to enhance the use of the systems in agriculture among other fields. In recent years, there are easily available satellite data like Landsat and Sentinel; the new and advanced Sentinel-2 containing the new ESA’s Sentinel-2 and NASA’s Landsat 9 mainly deals with vegetation data. There are also benefits of high resolution in measurements, short time interval and wide area that makes it very useful for large parcel crop monitoring (Karakus et al., 2023).
       
Another important application of drones also in agriculture is for precision spraying. Drone application of fertilizers, pesticides and herbicides is efficient since it does not cause wastage of chemicals and pollutes the environment. They help in the identification of variability and distribution of soil type, moisture content and small geographical features on the ground. This information helps in designing of irrigation schedules and proper management of the nutrients to be applied hence improving on utilization of the available resources (Eitel et al., 2023). Also, crop scouting and yield estimation are some of the activities that are enhanced through the use of drones.
 
IoT and smart sensors
 
It shows that IoT, smart sensors and AI have immense potential for gathering real time information and analysing them to monitor the soil nutrients, water quantity, crop quality and crop yield in a specific area of land (Ayaz et al., 2019). IoT integrated with smart sensors has replaced the traditional mode of farming; smart farming has a greater yield. IoT-based solutions for smart and sustainable agriculture also aids in measuring soil health, soil erosion, crop fertiliser needs, analysis of soil fertility status, crop production standards etc. Smart solutions like infrared thermography along with smart sensors have been developed to capture the topological information of agricultural land. Internet of Things and smart soil moisture sensors are used to identify whether an agricultural land is in pre-harvest or post-harvest stage. Several challenges in the global population from microbial species as pointed (Rajak and Ganguly, 2023). Microbial contamination in agrifoods can be detected with the help of Microfluids based on-chip artificial pore. The two common methods of detecting pathogens onsite are the lateral flow test and the lateral flow assays. Notably, the deployment of deep learning approaches is focused on interpreting data that is collected by various sensors. IoT and UAV are the two pillars of smart farming that can be monitored at a low manpower-high yield level. Hence, the need for enriching smart farming by utilising machine-deep learning techniques and Arduino controls as suggested (Shafi et al., 2020). IoT could have been introduced much easily for sensing the situation of crop quality, drought management, ground water irrigation status and soil health. Some of the indices identified that could be used for smart farming include: Vegetation health index (VHI), Standardised anomaly index (SAI), Evaporative stress index (ESI).
       
Integration of Agricultural IoTs with expert systems is helping farmers to optimize their crop planting and crop management schedules (Liu et al., 2016). At present there are all the equipment’s available in the market and are in use for the environmental details, agricultural details cum crops details and animal movement details. Electro mechanical sensors, biosensors and physical property sensors are some of the significant inventions in agriculture areas. Physical property sensors utilize devices that detect some physical property of the external environment allowing biological sensors to detect biological sensitive signals such as sweat, saliva, urine and so on. As we know that day by day water is getting scarce in the world, so the management of water is very essential.
 
Big data analytics and machine learning
 
Despite the widespread adoption of data analytics for crop yield management practises, a number of studies have been conducted. For example, Klerkx et al. (2019) performed a systematic review of ML-supported crop yield prediction and reported key ML algorithms, prediction features and performance metrics used for the crop yield predictions. Adjusting the yield estimation using agrarian indicators in the ML methodologies This allowed them to determine the positive correlation between the yields and climatic factors that determine the crops production (Elavarasan et al., 2018). Published the first systematic review on the application of computer vision/ artificial intelligence on grain quality, disease detection and phenotyping on the five cereal crops (maize, rice, wheat, soybean and barley) (Patricio and Rieder, 2018). The use of big data analytics in the agricultural industry is still in its early form and data, plus the tools to analyse the data, are present, but many problems remain.
 
Robotics and automation
 
Robotics and automation have become an integral part of crop management in the modern world, which has brought about a drastic change in the means of agriculture. Machines such as driverless tractors, intelligent farm machinery, automated weeder and harvester has minimized the employment of labour while enhancing efficiency of usage of resources. AI has evolved and acted upon the traditional farming equipment and made the farming equipment self-driven. Self-driving tractors, drones, robotic spraying machines incorporated with artificial intelligence and geographic information system (GIS) can execute several farming activities like ploughing, sowing seeds, watering, spraying insecticides with very little human interferences. These consist of tools for monitoring features or conditions of soil, the crops and the environment for purposes of making accurate input application. It decreases cost of production, minimizes on waste and increases the yield of crops produced. AI also enhances the execution of self-driving farm machinery leading to proper management of farming practice which is known as precision agriculture to enhance yield and sustainability (Mohan et al., 2023).
       
Autonomous robotic weeders along with systems involving machine vision and artificial intelligence to detect the weeds and removes them individually decreasing on the use of chemical herbicides, hence enhancing ecological agriculture. These systems are also useful for solving problems of labour shortage, increasing the speed of harvesting and quality of crops (Chandra, 2023).
 
Case studies
 
Case study 1: Soil analysis and monitoring
 
Applying of artificial intelligence for soil health monitoring in Raleigh, North Carolina, USA, brought extremely positive performance improvements in agro-inputs where use of chemical fertiliser was reduced by almost 40%. Also, the geographic information system (GIS) technologies can analyse space thereby assisting in the management of water during irrigation. For instance, in Alfalfa in Riverdale, California, the use of GIS technologies in irrigation increased per acre crop yield by up to 37.5% and lowered the water consumption by 20% (Akhter et al., 2024). Thus, use of AI in soil analysis and health monitoring enhances the sustainability within a specific area of arable land.
 
Case study 2: Crop sowing
 
In the year 2016, Microsoft and ICRISAT (International Crop Research Institute for the Semi-Arid Tropics) jointly initiated a pilot project in Devanakonda Mandal, Kurnool district andhra Pradesh. Each farmer in the group received notifications on their mobiles regarding the best times to plant, how to prepare their fields and how much fertiliser to apply based on soil tests. This method increased the crop yield by an estimated 30%. In 2017, the project was broadened to cover around 3,000 farmers in Karnataka and Andhra Pradesh during the Kharif season, working with groundnut, ragi, maize, rice and cotton, among other farms. According to the study, AI techniques increased crop yields by 10% to 30% for different crops (Nagpal, 2017). As a result, using AI in crop sowing may increase the amount farmers get from each acre and minimize their costs.
 
Challenges and limitations of AI in crop management
 
Despite the enhanced crop management solutions proposed through AI, there is still much that needs to be achieved for one to attain its benefits. These issues are in terms of technical, economical and social requirements that are important to ensure AI and ML implementation in the agricultural sector. In particular, the data collection process may be difficult, especially in agricultural industry and in the areas where the availability of technologies is low. The quality of data can also be very inconsistent and thus it introduces bias in the models. Also, data fusion of multiple data sources such as weather data, soil sensors, drone imagery may pose challenges due to the different formats and levels of data (Kamilaris and Prenafeta-Boldú, 2018).
       
Moreover, one of the challenges that come along with the use of AI models like deep learning models is the interpretability and more importantly the aspect of trust which is very vital in resolution making in agriculture. Implementation of AI in agriculture requires a huge capital investment on both the physical assets such as the sensors and the drones as well as software. Unfortunately, the expenses are too high to be afforded by most small-scale farmers, which hampers the effectiveness of these technologies. Also, the process of maintenance and upgrade of these tools can also increase the costs and may hinder the farmers in the developing nations from accessing them (Oliveira et al., 2023). Other issues affecting implementation include availability of infrastructure such as internet connection in most rural areas and even electricity and technical support especially in developing countries. As highlighted (Kumari et al., 2018), farmers need certain basic technologies, which they do not possess to be in a position to either adopt or apply artificial intelligence in crop management. The key issues of using Artificial intelligence for smart agriculture include data protection, job losses as well as the digital gap. Also, the replacement of tasks done by labours may bring about unemployment, especially in developing world where agriculture is dominant. It also worsens inequalities because some farmers use better technologies than others due to their financial capabilities (Bronson et al., 2019). Also, the level of modernization in the agricultural sector varies from country to another and what works in one country may not work in other, there is a lot of localization issues that will be required (Wolfert et al., 2017).
 
Future prospects and innovations

AI in crop management future looks very promising as it can bring changes in agricultural productivity and usage. AI has capabilities in aspects such as machine learning, data analytics and sensors and it is predicted to change the future of precision farming in terms of resource management, crop checking and intervention. Automatic systems that involve use of AI can determine appropriate conditions favourable for irrigation, fertilization, pest control and harvesting thus increasing yields and covering a wide range of areas. The prospects of AI in crop management are looking bright with further development in the future that looks set to act as the next big shift in agriculture’s efficiency, sustainability and productivity. In the next years, better models that would help predict yields, pest infestations as well as the weather will be developed. The advancement in AI algorithm will enable farmers attain better information hence giving them a better stand in managing risks produced by inordinate climate change and/ or fluctuating markets (Adli et al., 2023).
               
Instead, as more advanced AI and ML are introduced, farmers should expect to receive farming solutions that are most suited to their particular farm. These solutions will integrate regional specific characteristics including the type of land, climate condition of the area and/or type of crops in order to give venture specific solutions to the farmers. Such a level of differentiation will assist the small and medium-sized farms to manage their activities and be at par with the large-scale farming businesses. Ethical guidelines will be an important feature to interrogate to make sure that the positive impacts of AI on crop management will be shared equitably. Some of the future research areas may include data protection, data origin, algorithm revealing and the issue of availing the opportunities given by these technologies to smallholder farmers and those in the rural areas.

CONCLUSION

The application of AI in agriculture is a viable solution to the emerging problems of food production in the world today. Precision farming also refers to resource using techniques that include watering system, fertilisation, thereby indicating favourable outcome. Other application include; use of artificial intelligence in farming such as in the drones for monitoring crop health and early detection of disease or nutrient deficiencies. Precision irrigation systems improve on water use whereby automatic weed control also minimises on use of herbicides thus making it economical and environmentally efficient. Also, AI continues to impact the supply chain since it has enhanced the flow of market information and reduced waste through proper distribution. There are obstacles like high implementation costs and lack of competencies in the development and application of these technologies but due to continuous improvements in that area and increasing governmental and industrial support, the application of these solutions is becoming cheaper and more approachable. Thus, the rising demand for food due to the expanding population, the effects of climate change and limited resources make the use of artificial intelligence not simply beneficial, but crucial for the agricultural industry.
       
So, by adopting these technologies, there is opportunity to develop sustainable farming system that can feed the world in the future.

CONFLICT OF INTEREST

The authors declare that there are no conflicts of interest regarding the publication of this review article. The authors have no financial, commercial, personal or institutional relationships that could influence the content, interpretation, or conclusions presented in this manuscript.

REFERENCES


  1. Adli, H.K., Remli, M.A., Wan Salihin Wong, K.N.S., Ismail, N.A., González-Briones, A., Corchado, J.M. and Mohamad, M.S. (2023). Recent advancements and challenges of AIoT application in smart agriculture: A review. Sensors. 23(7): 3752.

  2. Ahmed, M.N., Singh, A.P., Hussain, M.R., Rasool, M.A., Khan, I.M. and Dildar, M.S. (2024). Enhancing Crop Production Using Artificial Intelligence in Agricultural Revolution. In: 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP) IEEE. 1: 432-437. 

  3. Akhter, A., Nabi, A., Narayan, S., Akhter, S., Lone, B. A., Yousuf, V. et al. (2024). Digital technology: A game changer in vegetable cultivation. Annual Research and Review in Biology. 39(2): 30-52.

  4. Arjun, K.M. (2013). Indian agriculture-status, importance and role in Indian economy. International Journal of Agriculture and Food Science Technology. 4(4): 343-346.

  5. Ayaz, M., Ammad-Uddin, M., Sharif, Z., Mansour, A. and Aggoune, E.H.M. (2019). Internet-of-Things (IoT)-based smart agriculture: Toward making the fields talk. IEEE Access. 7: 129551-129583.

  6. Bagchi, N.S., Mishra, P. and Behera, B. (2021). Value chain development for linking land-constrained farmers to markets: Experience from two selected villages of West Bengal, India. Land Use Policy. 104: 105363.

  7. Banthia, V. and Chaudaki, G. (2022). The study on use of artificial intelligence in agriculture. Journal of Advanced Research in Applied Artificial Intelligence and Neural Network. 5(2): 18-22.

  8. Blessy, J.A. (2021). Smart Irrigation System Techniques Using Artificial Intelligence and IoT. In: 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) IEEE. pp. 1355-1359. 

  9. Bronson, K. (2019). Looking through a responsible innovation lens at uneven engagements with digital farming. NJAS- Wageningen Journal of Life Sciences. 90: 100294.

  10. Cucho-Padin, G., Loayza, H., Palacios, S., Balcazar, M., Carbajal, M. and Quiroz, R. (2020). Development of low-cost remote sensing tools and methods for supporting smallholder agriculture. Applied Geomatics. 12(3): 247-263.

  11. Chandra, V.S. (2023). Role of artificial intelligence in Indian agriculture: A review. Agricultural Reviews. 44(4): 558- 562. doi: 10.18805/ag.R-2296.

  12. Eitel, J.U., Basler, D., Braun, S., Buchmann, N., D’Odorico, P., Etzold, S. et al.  (2023). Towards monitoring stem growth phenology from space with high resolution satellite data. Agricultural and Forest Meteorology. 339: 109549.

  13. Elavarasan, D., Vincent, D.R., Sharma, V., Zomaya, A.Y. and Srinivasan, K. (2018). Forecasting yield by integrating Agrarian factors and machine learning models: A survey. Computers and Electronics in Agriculture. 155: 257-282.

  14. Kamilaris, A. and Prenafeta-Boldu, F.X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture. 147: 70-90.

  15. Karakus, P. (2023). Investigation of meteorological effects on Çivril Lake, Turkey, with sentinel-2 data on Google Earth engine platform. Sustainability. 15(18): 13398.

  16. Klerkx, L., Jakku, E. and Labarthe, P. (2019). A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda. NJAS-Wageningen Journal of Life Sciences. 90: 100315.

  17. Kumar, A., Surendra, A., Mohan, H., Valliappan, K. M. and Kirthika, N. (2017). Internet of Things based Smart Irrigation using Regression Algorithm. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) IEEE. pp. 1652-1657. 

  18. Kumari, S., Jeble, S. and Patil, Y.B. (2018). Barriers to technology adoption in agriculture-based industry and its integration into technology acceptance model. International Journal of Agricultural Resources, Governance and Ecology. 14(4): 338-351.

  19. Kundalia, K., Patel, Y. and Shah, M. (2020). Multi-label movie genre detection from a movie poster using knowledge transfer learning. Augmented Human Research. 5(1): 11.

  20. Lahiri, B., Anurag, T. S., Borah, S., Marak, N. R., Pavan Kumar, S. T., Sangma, S. M. et al. (2024). Designing a user-centric mobile-based agro advisory system for sustainable development of smallholder farming systems in the eastern Himalayas, India. Information Technology for Development. 30(4): 665-695.

  21. Liu, C., Cutforth, H., Chai, Q. and Gan, Y. (2016). Farming tactics to reduce the carbon footprint of crop cultivation in semiarid areas: A review. Agronomy for Sustainable Development. 36(4): 69.

  22. Menshchikov, A., Shadrin, D., Prutyanov, V., Lopatkin, D., Sosnin, S., Tsykunov, E. et al. (2021). Real-time detection of hogweed: UAV platform empowered by deep learning. IEEE Transactions on Computers. 70(8): 1175-1188.

  23. Mohan, S.S., Venkat, R., Rahaman, S., Vinayak, M. and Babu, B.H. (2023). Role of AI in agriculture: Applications, limitations and challenges: A review. Agricultural Reviews. 44(2): 231-237. doi: 10.18805/ag.R-2215.

  24. Mehta, A.R., Kumar, P., Prem, G., Aggarwal, S. and Kumar, R. (2025). Leveraging artificial intelligence for disease diagnosis in agricultural crops: A review. Indian Journal of Agricultural Research. 59(5): 681-690. doi: 10.18805/IJARe.A-6363.

  25. Nagpal, J. (2017). Digital Agriculture: Farmers in India are using AI to increase crop yields. Microsoft India News Center.

  26. Oliveira, R.C.D. and Silva, R.D.D.S.E. (2023). Artificial intelligence in agriculture: Benefits, challenges and trends. Applied Sciences. 13(13): 7405.

  27. Oyakhilomen, O. and Zibah, R.G. (2014). Agricultural production and economic growth in Nigeria: Implication for rural poverty alleviation. Quarterly Journal of International Agriculture. 53(3): 207-223.

  28. Pantazi, X.E., Moshou, D. and Bravo, C. (2016). Active learning system for weed species recognition based on hyperspectral sensing. Biosystems Engineering. 146: 193-202.

  29. Patricio, D.I. and Rieder, R. (2018). Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Computers and Electronics in Agriculture. 153: 69-81.

  30. Rajak, P. and Ganguly, A. (2023). In silico study unfolds inhibitory potential of epicatechin gallate against SARS-CoV-2 entry and replication within the host cell. Mechanobiology in Medicine. 1(2): 100015.

  31. Rao, A.N., Wani, S.P. and Ladha, J.K. (2014). Weed Management Research in India- An Analysis of Past and Outlook for Future. In: DWR - Souvenir, Celebrating Silver Jubilee (1989-2014). 2014. Directorate of Weed Research, Jabalpur India. p. 1-26.

  32. Sandric, I., Irimia, R., Petropoulos, G.P., Stateras, D., Kalivas, D. and Ple’oianu, A. (2022). Drone Imagery in Support of Orchards Trees Vegetation Assessment based on Spectral Indices and Deep Learning. In Information and Communication Technologies for Agriculture-Theme I: Sensors. Cham: Springer International Publishing. (pp. 233-248).

  33. Shafi, U., Mumtaz, R., Iqbal, N., Zaidi, S.M.H., Zaidi, S.A.R., Hussain, I. and Mahmood, Z. (2020). A multi-modal approach for crop health mapping using low altitude remote sensing, internet of things (IoT) and machine learning. IEEE Access. 8: 112708-112724.

  34. Sharma, R. (2021). Artificial Intelligence in Agriculture: A Review. In: 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE. (pp. 937-942).

  35. Sharma, U., Tomar, P., Bhardwaj, H. and Sakalle, A. (2021). Artificial Intelligence and Its Implications in Education. In: Impact of AI Technologies on Teaching, Learning and Research in Higher Education. IGI Global. (pp. 222-235).

  36. Subeesh, A. and Mehta, C.R. (2021). Automation and digitization of agriculture using artificial intelligence and internet of things. Artificial Intelligence in Agriculture. 5: 278-291.

  37. Swanton, C.J., Nkoa, R. and Blackshaw, R.E. (2015). Experimental methods for crop-weed competition studies. Weed Science. 63(SP1): 2-11.

  38. Vyas, S., Shabaz, M., Pandit, P., Parvathy, L.R. and Ofori, I. (2022). Integration of artificial intelligence and blockchain technology in healthcare and agriculture. Journal of Food Quality. 1: 4228448.

  39. Wolfert, S., Ge, L., Verdouw, C. and Bogaardt, M.J. (2017). Big data in smart farming-A review. Agricultural Systems. 153: 69-80.
Published In
Agricultural Science Digest
Article Metrics
Metrics Icon
54
Views
0
Citations
Reviewed By
Share Article
Download Article
In this Article
    Contact us
    Follow us

    Review Article

    Artificial Intelligence in Crop Management: A Review

    N
    Neroju Manasa1,*
    G
    Guda Bhargavi1
    K
    Kasula Vamshi Krishna2
    J
    J. Vamshi3
    B
    B. Bhavana4
    1Department of Agronomy, SR University, Warangal-506 371, Telangana, India.
    2Department of Agronomy, SoAS, Malla Reddy University, Hyderabad-500 043, Telangana, India.
    3Department of Plant Pathology, UIAH, Agriculture, Guru Nanak University, Ibrahimpatnam-501 506, Telangana, India.
    4Department of Agronomy, SoAS, Malla Reddy University, Hyderabad-500 043, Telangana, India.

    ABSTRACT

    Artificial Intelligence (AI) is gradually becoming more prevalent in agriculture by providing technology for crop cultivation, pests control, soil monitoring and data processing. This kind of technology also enables farmers to make decisions of planting seeds as the technology reveals whether seeds suitable for a given area and even climate information. AI can help farmers get more profit from their produce when applied, improve on quality and make marketing more efficient. To improve the status of the soil it also avails the right nutrients and gives information on the quality of the soil. Precision can be improved by adjusting the spacing and planting width and depth functions with technology. In addition, the use of AI incorporated in health monitoring systems ensures that data regarding the state of the crops and their nutritional requirements are well obtained reducing the time it takes to get high yields of good stocks and an enhanced quantity is produced. AI integrated with Machine learning (ML) technology has revolutionized farming by agile farming, precision farming thereby reducing wastage and promoting sustainable farming. Measures of plant and soil health are Hyper-Spectral photography and three-dimensional laser scanning those records large amount of data for analysis. This chapter explores several uses of AI are realized in agriculture including in crop management, pest control and disease control. It also outlines the opportunities as well as the challenges of AI for agriculture for optimization of the yield in agriculture.

    INTRODUCTION

    Agriculture remains the oldest and essential sector of our global economy where farmers produce what the world needs to live such as food, fibres and energy sources. Industrial agriculture remains the prime employer through worldwide while simultaneously generating substantial economic development through agriculture. According to (Oyakhilomen and Zibah, 2014) current agricultural practices form the basic way people survive, increase national income, expand trade activities, reduce unemployment numbers and give other industries their raw materials while pushing forward the economy. The farming industry makes a large economic impact on India. Agricultural activities use the workforce of more than 60% of the nation’s population which produce about 17% of total economic output. Rural communities rely on agriculture for survival since 70% of their households make their living from the land. During the last several decades Indian agriculture achieved remarkable growth (Arjun, 2013). Despite these challenges, the agricultural industry has continually experienced setbacks associated with factors such as climate change, scarcity of water, soil degradation and the occurrence of pests and diseases within most farms. These obstacles have led to low production and a simultaneous increase in the level of food shortage. The implementation of technology demonstrates a powerful solution to transform agricultural practises while dealing with current agricultural challenges. Modern science considers Artificial Intelligence (AI) as one of its greatest transformative technologies. The integration of artificial intelligence into everyday life keeps expanding our ability to transform our environment (Kundalia et al., 2020). With advancements in both computational power and cloud connectivity AI continues to transform rapidly as various economic sectors gain access to AI benefits. These benefits include weed control and crop harvest timing determination and soil evaluation as well as yield prediction capabilities. AI has undergone testing to serve as development tools across numerous industries since the last ten years. Agricultural decision-making has become a field where AI demonstrates its potential for improvement (Vyas et al., 2022) and (Sharma et al., 2021).
           
    Precision farming is one of the broad areas which have already been achieved by increasing the application of artificial intelligence in crop management to the extent that the farmer is in a position to manage field scenarios and input quantities like the quantity of water, fertilisers and pesticides to be used. Automated drones and sensors capture better images and data on nutrient deficiency and disease epidemics for improvement. Monitoring of crop health that may be made through reliable AI models and the farmer is then in a position to make adjustments to reduce the effects of the disease before they are worst experienced. Moreover, through irrigation systems, AI controls the water input because it utilizes the applicable data to know the amount of water in the soil and therefore prevent the wastage of water and maximize the efficiency of water use. Weeds pose a serious hazard to many agricultural activities; presence of weeds reduces agricultural production while destroying crops and killing pastures along with occasional threats to farm cattle. AI sensors perform weed detection by analysing specific areas to select appropriate herbicide treatments. Besides, incidence of pests and diseases which adversely affects production of crops and increases cost of production. The incidences of pests and diseases are alarming since they lead to low yields and high cost of production. Since farmers are not able to employ such techniques, pests and diseases pose a threat to agricultural produce which in turn leads to loss of money and harvest. It is important for these problems to be solved as a way of ensuring the advances in agriculture and the availability of food as well as welfare of the farming people. Therefore, there is increased importance in addressing such challenges, since AI is progressive in identifying solutions towards increased farming practice resilience (Ahmed et al., 2024). It is possible for farmers to keep track of their crops using AI technologies on drones. Experts monitor the pictures taken by the drone and write a report on the farm condition. It makes it easier for farmers to manage pests. In today’s farming, certain farmers have robots that complete time-consuming chores on the farm. They assist farmers by taking over parts of the jobs that are expensive to do by hand. In addition, AI is not only applicable to farm systems but also in supply chain and intelligence of the markets. Using technologies such as AI, farmers and agribusinesses can make informed decisions on things or on aspects like demand, pricing and distribution within the market. However, AI adoption in agriculture has its limitations such as high implementation cost, illiteracy of farmers in the use of digital platforms and final consumer privacy. However, the technology has advanced so much in recent years that government and industry support has made these solutions increasingly easier and cheaper to maintain. One of the powerful approaches that can help overcome such limitations is with specific farmer training programmes and digital literacy campaigns. Trainings on the use of AI tools like drones, sensors and decision support system targeting farmer in hands on trainings, field demonstration and mobile advisory in local languages are facilitated through these initiatives.
     
    Need for AI in agriculture
     
    Agriculture is a labour and time-consuming, hence with growing population and demand for agricultural produce the efficiency of automation is progressively gaining importance. Specifically, AI benefits farmers in elements as well as componentry’s and paradigms of application and technology. Technology-driven predictive analytics and improved farm and crop management systems to ensure quality crop supply. Satellite images, weather records for identifying the area of the cultivated land and monitoring the condition of crops in real-time (Subeesh and Mehta, 2021). AI, big data and ML are useful in determining the price, projecting production and yield and detecting pest and disease incidence respectively for use in businesses. They can tell farmers the production requirements, which crops to grow for maximum profits, use of chemicals like pesticides and forecast market prices in future. AI technologies are proving great assistance in eliminating traditional barriers in every field of life. Business, transport, medicine and farming are the fields in which AI is used. The global population is growing, but at the same time urbanisation is progressing very rapidly. This is due to the fact that farmers are now under pressure to produce more production to feed the people hence they need a way to do so (Menshchikov et al., 2021). The use of AI on the global scale is perhaps one of the most promising in the agriculture industry. Many of the produce companies are experiencing challenges in managing pests and various illness or diseases that are notorious to the plants (Sharma, 2021). They are compounded by climate change, monoculture practices and the use of pesticides. These aspects come together to give the farmers a new challenge. This is however compounded by aspects such as irregularity of rains, scarce labour force and the annual challenge of output raising. This means that the agricultural industry will require expanding in the forthcoming years incredibly and farm productivity will require doubling if we have to achieve our targets almost. Taking all these challenges into consideration, it is pertinent to understand that AI offers agriculture automation (Blessy, 2021).
     
    Role of AI in crop management
     
    In today’s global market, various technologies in AI-based are being developed to optimize the market and supply chain, weather forecasting, agricultural analytics and efficiency of crop and soil (Fig 1). Digital agricultural innovation involves the application of cloud computing systems, data structures, IoT and AI. This makes it possible for farmers to employ technical methods of irrigation, fertilisation, disease and pest identification and control, spraying and harvesting. Computer Vision: Applied Artificial Intelligence - Using image and video data - drone cameras, satellite imagery - monitor disease or pests, weather conditions, timing and quantity of chemical sprays, time to harvest, produce shelf life.

    Fig 1: Role of AI in crop management (Source: Author).


     
    Soil health monitoring
     
    Soil can be termed as bedrock of agriculture and therefore ensuring crucial when organising Agri spherical production. Modern methods of determination of soil using the help of various techniques and sensors based on artificial intelligence allow to determine its moisture, nutrient and acidity levels. This information is further fed to the machine learning algorithms to get recommendations on conditions suitable for growth of crops in the soil.
     
    Weather forecasting
     
    Mobile apps that provide information on weather related issues go a long way in the management of daily agricultural activities. These contribute to the assistance they provide to farmers using weather-based agro alerts besides weather information. Popular mobile applications for weather forecast include Meghdoot, Mausam and Damini endeavours to provide specific crop related weather information for the farming community in India in order to get better access to Climate Information Service. Mobile application known as Meghdoot or Cloud Messenger which was launched in August 2019. Established by ICRISAT’s Digital Agriculture research domain in Hyderabad, IITM, Pune and IMD, New Delhi in collaboration (Lahiri et al., 2024). Meghdoot is a simple and easily accessible mobile application which provides farmers at different places with the advice on cropping in their respective local languages based on the weather information. It is jointly organised by the Indian Council of Agricultural Research (ICAR), Indian Institute of Tropical Meteorology and Indian Meteorological Department (IMD).
     
    Water management
     
    Irrigation or water management is a labour consuming process necessary for the management of the water availability, the rainfall and the water needs for production in agricultural system. Automated irrigation systems have advantages of more crop yield, less human interferences, less water consumption as compared to the conventional method, more frequency and low volume of water application. A smart irrigation system is an approach of managing and controlling the irrigation in agricultural land through using IoT devices, automation and control technology. According to Kumar et al. (2017), the use of this system indicated that any conventional agricultural practice, which was previously carried out by manpower, can be transformed into an automated process with minimal supervision.
     
    Weed management
     
    The farmers expected production and profit are always affected by weeds. The survey showed that, failure to control the weeds would lead to scaling down of the dried beans and maize harvest by at least fifty per cent. This could be attributed to the time the crops were exposed to the weeds (Rao et al., 2014). According to the WSSA (Weed Science Society of America), some weeds are capable of opening the path during the wildfire by flooding during hurricanes are toxic and cause fatal liver failure if eaten, some outcompete plants or crops for water, nutrients and soil. There are a few weeds that are toxic, cause allergies or that are otherwise dangerous to the human beings (Swanton and Blackshaw, 2015). Recently, (Pantazi et al., 2016) developed a new algorithm based on machine learning algorithm using hyperspectral imaging for the purposes of crop versus weed classification.
     
    Pest and disease detection
     
    The role of pests and diseases are that they can considerably reduce crop yields. The online detection of pest and diseases requires the use of image recognition based on the artificial intelligence business that with an application of deep learning, is capable of detecting symptoms at early stages (Mehta et al., 2025). The farmers will be informed of the alerts and recommendations concerning the appropriate treatment, reducing the harm and the use of chemical pesticides.
     
    Applications of AI in agriculture
     
    By 2050 the global food production must increase by 50%, So the world requires our farmers to grow 50% more food before 2050. According to Bagchi et al., (2021) almost all demand growth will be met by other farming areas rather than opening new farmlands. The current need for higher food production with reduced resources drives the agricultural revolution through AI technology. Technology built with artificial intelligence can support different advancements in agricultural work. The system includes both business recommendations plus analytics platforms that connect to IoT devices and camera equipment (Fig 2).

    Fig 2: Applications of AI (Source: Author).


     
    Crop and soil analysis monitoring
     
    Traditional approaches are usually slow and always tend to be categorically different from what can be observed using the automated digital detection and analysis techniques. Hyper spectral imaging and 3D Laser Scanning are the two methods that can enable improvements in information and plant metrics over thousands of acres at the same spatial resolution. The sensors, cameras and infrared rays help diagnose the health of the soil and measure the nutritional content of the soil. This is also useful to determine the effect of some seeds on the type of land, the impact of changing weather on the soil and the likelihood of spreading diseases and pests (Sandric et al., 2022). With this knowledge, improved crop application rates are achieved, both cost and more yield per hectare for the farmer. However, currently, the Haryana state is using a total of 207.56 kg of chemical fertilizers per hectare per year, which is considered to be rather high among all the other Indian states. Fertilizers are also expensive to acquire and use in the farms and the substances in the fertilizers are often toxic.
     
    AI- Automated Irrigation systems
     
    Since agriculture is the oldest profession of civilized mankind irrigation systems, it is a very challenging task to irrigate large areas of plant. To address this problem several irrigation scheduling approaches have been put forward which depend on the measurement of the available water in the soil, the water status of the crops and the climatic factors. Irrigation scheduling involves when to irrigate as well as the quantity of water to apply. Based on these characteristics, there are four major types of automated irrigation systems including:
    •  Closed loop system based on a predefined irrigation schedule and assumes the control system has complete authority on the quantity and duration of the water to be applied.
    •  An open loop hydro-prin that depends on the amount of water to be delivered and the time for irrigation to take place.
    •  Volume based system wherein a fixed volume of water is applied for agriculture.
    •  System related to clocks which is connected to clock controllers.
     
    Improve decision making
     
    The use of artificial intelligence in decision-making technology in agriculture is slowly increasing. Increasing information is recorded and subsequently used in the agricultural decision-making process. This has been made possible by increased use of sensors, faster availability of imagery from satellites, comparatively low production costs of data loggers, increased use of drones and more readily available data archives for irrigation, among other things (Banthia and Chaudaki, 2022). This is an elaborate process that requires a lot of human involvement and can be mechanized for efficiency. One can program machines to learn temperature patterns in a region and the soil qualities in order to enhance production. Precision farming uses more manageable and incrementally measurable methods in place of the repetitive and labour-intensive technique used in agriculture.
     
    Food supply chain
     
    Implementation of AI in agriculture will help the agriculture sector to deliver better crops and also help to improve various agriculture-related activities in the food value chain. It led to a clamour for more foods while promoting employment to more than six billion people as part of the whole system. This has been achieved through the incorporation of AI in the agricultural industry which has catalysed what may be best described as an agricultural revolution. It has protected crop production from population pressure, climate change, source of income and food-borne crisis. AI in crop management and yield has a lot of potential, but there are a few disadvantages on the application of these new forms of AI that experts believe have not yet been identified. Building AI models for increasing economic efficiency and sustainability supports the path of development of new models using suitable scale management strategies and technologies for the managers of farm and forest.
     
    AI technologies in crop management
     
    Remote sensing and drones
     
    Satellite and aerial images, in the current world, are widely used in the observation and assessment of crop vigor and the state of soil humidity and other conditions that affect crop productivity. These technologies have changed the ways through which farmers and agribusiness adopt the practice of farming empowering them to monitor and decide on the health of crops (Cucho-Padin et al., 2020). Satellite information provides the possibility of having different spatial resolution from kilometres up to hundreds and tens of meters. Many of these lower resolution products are publicly available, but they are not suitable for the small-scale farming. Even today, the satellite systems that possess some of the highest spatial resolutions that are measured in meters, including just a few meters, are relatively costly and this is a factor that needs to be reduced to enhance the use of the systems in agriculture among other fields. In recent years, there are easily available satellite data like Landsat and Sentinel; the new and advanced Sentinel-2 containing the new ESA’s Sentinel-2 and NASA’s Landsat 9 mainly deals with vegetation data. There are also benefits of high resolution in measurements, short time interval and wide area that makes it very useful for large parcel crop monitoring (Karakus et al., 2023).
           
    Another important application of drones also in agriculture is for precision spraying. Drone application of fertilizers, pesticides and herbicides is efficient since it does not cause wastage of chemicals and pollutes the environment. They help in the identification of variability and distribution of soil type, moisture content and small geographical features on the ground. This information helps in designing of irrigation schedules and proper management of the nutrients to be applied hence improving on utilization of the available resources (Eitel et al., 2023). Also, crop scouting and yield estimation are some of the activities that are enhanced through the use of drones.
     
    IoT and smart sensors
     
    It shows that IoT, smart sensors and AI have immense potential for gathering real time information and analysing them to monitor the soil nutrients, water quantity, crop quality and crop yield in a specific area of land (Ayaz et al., 2019). IoT integrated with smart sensors has replaced the traditional mode of farming; smart farming has a greater yield. IoT-based solutions for smart and sustainable agriculture also aids in measuring soil health, soil erosion, crop fertiliser needs, analysis of soil fertility status, crop production standards etc. Smart solutions like infrared thermography along with smart sensors have been developed to capture the topological information of agricultural land. Internet of Things and smart soil moisture sensors are used to identify whether an agricultural land is in pre-harvest or post-harvest stage. Several challenges in the global population from microbial species as pointed (Rajak and Ganguly, 2023). Microbial contamination in agrifoods can be detected with the help of Microfluids based on-chip artificial pore. The two common methods of detecting pathogens onsite are the lateral flow test and the lateral flow assays. Notably, the deployment of deep learning approaches is focused on interpreting data that is collected by various sensors. IoT and UAV are the two pillars of smart farming that can be monitored at a low manpower-high yield level. Hence, the need for enriching smart farming by utilising machine-deep learning techniques and Arduino controls as suggested (Shafi et al., 2020). IoT could have been introduced much easily for sensing the situation of crop quality, drought management, ground water irrigation status and soil health. Some of the indices identified that could be used for smart farming include: Vegetation health index (VHI), Standardised anomaly index (SAI), Evaporative stress index (ESI).
           
    Integration of Agricultural IoTs with expert systems is helping farmers to optimize their crop planting and crop management schedules (Liu et al., 2016). At present there are all the equipment’s available in the market and are in use for the environmental details, agricultural details cum crops details and animal movement details. Electro mechanical sensors, biosensors and physical property sensors are some of the significant inventions in agriculture areas. Physical property sensors utilize devices that detect some physical property of the external environment allowing biological sensors to detect biological sensitive signals such as sweat, saliva, urine and so on. As we know that day by day water is getting scarce in the world, so the management of water is very essential.
     
    Big data analytics and machine learning
     
    Despite the widespread adoption of data analytics for crop yield management practises, a number of studies have been conducted. For example, Klerkx et al. (2019) performed a systematic review of ML-supported crop yield prediction and reported key ML algorithms, prediction features and performance metrics used for the crop yield predictions. Adjusting the yield estimation using agrarian indicators in the ML methodologies This allowed them to determine the positive correlation between the yields and climatic factors that determine the crops production (Elavarasan et al., 2018). Published the first systematic review on the application of computer vision/ artificial intelligence on grain quality, disease detection and phenotyping on the five cereal crops (maize, rice, wheat, soybean and barley) (Patricio and Rieder, 2018). The use of big data analytics in the agricultural industry is still in its early form and data, plus the tools to analyse the data, are present, but many problems remain.
     
    Robotics and automation
     
    Robotics and automation have become an integral part of crop management in the modern world, which has brought about a drastic change in the means of agriculture. Machines such as driverless tractors, intelligent farm machinery, automated weeder and harvester has minimized the employment of labour while enhancing efficiency of usage of resources. AI has evolved and acted upon the traditional farming equipment and made the farming equipment self-driven. Self-driving tractors, drones, robotic spraying machines incorporated with artificial intelligence and geographic information system (GIS) can execute several farming activities like ploughing, sowing seeds, watering, spraying insecticides with very little human interferences. These consist of tools for monitoring features or conditions of soil, the crops and the environment for purposes of making accurate input application. It decreases cost of production, minimizes on waste and increases the yield of crops produced. AI also enhances the execution of self-driving farm machinery leading to proper management of farming practice which is known as precision agriculture to enhance yield and sustainability (Mohan et al., 2023).
           
    Autonomous robotic weeders along with systems involving machine vision and artificial intelligence to detect the weeds and removes them individually decreasing on the use of chemical herbicides, hence enhancing ecological agriculture. These systems are also useful for solving problems of labour shortage, increasing the speed of harvesting and quality of crops (Chandra, 2023).
     
    Case studies
     
    Case study 1: Soil analysis and monitoring
     
    Applying of artificial intelligence for soil health monitoring in Raleigh, North Carolina, USA, brought extremely positive performance improvements in agro-inputs where use of chemical fertiliser was reduced by almost 40%. Also, the geographic information system (GIS) technologies can analyse space thereby assisting in the management of water during irrigation. For instance, in Alfalfa in Riverdale, California, the use of GIS technologies in irrigation increased per acre crop yield by up to 37.5% and lowered the water consumption by 20% (Akhter et al., 2024). Thus, use of AI in soil analysis and health monitoring enhances the sustainability within a specific area of arable land.
     
    Case study 2: Crop sowing
     
    In the year 2016, Microsoft and ICRISAT (International Crop Research Institute for the Semi-Arid Tropics) jointly initiated a pilot project in Devanakonda Mandal, Kurnool district andhra Pradesh. Each farmer in the group received notifications on their mobiles regarding the best times to plant, how to prepare their fields and how much fertiliser to apply based on soil tests. This method increased the crop yield by an estimated 30%. In 2017, the project was broadened to cover around 3,000 farmers in Karnataka and Andhra Pradesh during the Kharif season, working with groundnut, ragi, maize, rice and cotton, among other farms. According to the study, AI techniques increased crop yields by 10% to 30% for different crops (Nagpal, 2017). As a result, using AI in crop sowing may increase the amount farmers get from each acre and minimize their costs.
     
    Challenges and limitations of AI in crop management
     
    Despite the enhanced crop management solutions proposed through AI, there is still much that needs to be achieved for one to attain its benefits. These issues are in terms of technical, economical and social requirements that are important to ensure AI and ML implementation in the agricultural sector. In particular, the data collection process may be difficult, especially in agricultural industry and in the areas where the availability of technologies is low. The quality of data can also be very inconsistent and thus it introduces bias in the models. Also, data fusion of multiple data sources such as weather data, soil sensors, drone imagery may pose challenges due to the different formats and levels of data (Kamilaris and Prenafeta-Boldú, 2018).
           
    Moreover, one of the challenges that come along with the use of AI models like deep learning models is the interpretability and more importantly the aspect of trust which is very vital in resolution making in agriculture. Implementation of AI in agriculture requires a huge capital investment on both the physical assets such as the sensors and the drones as well as software. Unfortunately, the expenses are too high to be afforded by most small-scale farmers, which hampers the effectiveness of these technologies. Also, the process of maintenance and upgrade of these tools can also increase the costs and may hinder the farmers in the developing nations from accessing them (Oliveira et al., 2023). Other issues affecting implementation include availability of infrastructure such as internet connection in most rural areas and even electricity and technical support especially in developing countries. As highlighted (Kumari et al., 2018), farmers need certain basic technologies, which they do not possess to be in a position to either adopt or apply artificial intelligence in crop management. The key issues of using Artificial intelligence for smart agriculture include data protection, job losses as well as the digital gap. Also, the replacement of tasks done by labours may bring about unemployment, especially in developing world where agriculture is dominant. It also worsens inequalities because some farmers use better technologies than others due to their financial capabilities (Bronson et al., 2019). Also, the level of modernization in the agricultural sector varies from country to another and what works in one country may not work in other, there is a lot of localization issues that will be required (Wolfert et al., 2017).
     
    Future prospects and innovations

    AI in crop management future looks very promising as it can bring changes in agricultural productivity and usage. AI has capabilities in aspects such as machine learning, data analytics and sensors and it is predicted to change the future of precision farming in terms of resource management, crop checking and intervention. Automatic systems that involve use of AI can determine appropriate conditions favourable for irrigation, fertilization, pest control and harvesting thus increasing yields and covering a wide range of areas. The prospects of AI in crop management are looking bright with further development in the future that looks set to act as the next big shift in agriculture’s efficiency, sustainability and productivity. In the next years, better models that would help predict yields, pest infestations as well as the weather will be developed. The advancement in AI algorithm will enable farmers attain better information hence giving them a better stand in managing risks produced by inordinate climate change and/ or fluctuating markets (Adli et al., 2023).
                   
    Instead, as more advanced AI and ML are introduced, farmers should expect to receive farming solutions that are most suited to their particular farm. These solutions will integrate regional specific characteristics including the type of land, climate condition of the area and/or type of crops in order to give venture specific solutions to the farmers. Such a level of differentiation will assist the small and medium-sized farms to manage their activities and be at par with the large-scale farming businesses. Ethical guidelines will be an important feature to interrogate to make sure that the positive impacts of AI on crop management will be shared equitably. Some of the future research areas may include data protection, data origin, algorithm revealing and the issue of availing the opportunities given by these technologies to smallholder farmers and those in the rural areas.

    CONCLUSION

    The application of AI in agriculture is a viable solution to the emerging problems of food production in the world today. Precision farming also refers to resource using techniques that include watering system, fertilisation, thereby indicating favourable outcome. Other application include; use of artificial intelligence in farming such as in the drones for monitoring crop health and early detection of disease or nutrient deficiencies. Precision irrigation systems improve on water use whereby automatic weed control also minimises on use of herbicides thus making it economical and environmentally efficient. Also, AI continues to impact the supply chain since it has enhanced the flow of market information and reduced waste through proper distribution. There are obstacles like high implementation costs and lack of competencies in the development and application of these technologies but due to continuous improvements in that area and increasing governmental and industrial support, the application of these solutions is becoming cheaper and more approachable. Thus, the rising demand for food due to the expanding population, the effects of climate change and limited resources make the use of artificial intelligence not simply beneficial, but crucial for the agricultural industry.
           
    So, by adopting these technologies, there is opportunity to develop sustainable farming system that can feed the world in the future.

    CONFLICT OF INTEREST

    The authors declare that there are no conflicts of interest regarding the publication of this review article. The authors have no financial, commercial, personal or institutional relationships that could influence the content, interpretation, or conclusions presented in this manuscript.

    REFERENCES


    1. Adli, H.K., Remli, M.A., Wan Salihin Wong, K.N.S., Ismail, N.A., González-Briones, A., Corchado, J.M. and Mohamad, M.S. (2023). Recent advancements and challenges of AIoT application in smart agriculture: A review. Sensors. 23(7): 3752.

    2. Ahmed, M.N., Singh, A.P., Hussain, M.R., Rasool, M.A., Khan, I.M. and Dildar, M.S. (2024). Enhancing Crop Production Using Artificial Intelligence in Agricultural Revolution. In: 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP) IEEE. 1: 432-437. 

    3. Akhter, A., Nabi, A., Narayan, S., Akhter, S., Lone, B. A., Yousuf, V. et al. (2024). Digital technology: A game changer in vegetable cultivation. Annual Research and Review in Biology. 39(2): 30-52.

    4. Arjun, K.M. (2013). Indian agriculture-status, importance and role in Indian economy. International Journal of Agriculture and Food Science Technology. 4(4): 343-346.

    5. Ayaz, M., Ammad-Uddin, M., Sharif, Z., Mansour, A. and Aggoune, E.H.M. (2019). Internet-of-Things (IoT)-based smart agriculture: Toward making the fields talk. IEEE Access. 7: 129551-129583.

    6. Bagchi, N.S., Mishra, P. and Behera, B. (2021). Value chain development for linking land-constrained farmers to markets: Experience from two selected villages of West Bengal, India. Land Use Policy. 104: 105363.

    7. Banthia, V. and Chaudaki, G. (2022). The study on use of artificial intelligence in agriculture. Journal of Advanced Research in Applied Artificial Intelligence and Neural Network. 5(2): 18-22.

    8. Blessy, J.A. (2021). Smart Irrigation System Techniques Using Artificial Intelligence and IoT. In: 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) IEEE. pp. 1355-1359. 

    9. Bronson, K. (2019). Looking through a responsible innovation lens at uneven engagements with digital farming. NJAS- Wageningen Journal of Life Sciences. 90: 100294.

    10. Cucho-Padin, G., Loayza, H., Palacios, S., Balcazar, M., Carbajal, M. and Quiroz, R. (2020). Development of low-cost remote sensing tools and methods for supporting smallholder agriculture. Applied Geomatics. 12(3): 247-263.

    11. Chandra, V.S. (2023). Role of artificial intelligence in Indian agriculture: A review. Agricultural Reviews. 44(4): 558- 562. doi: 10.18805/ag.R-2296.

    12. Eitel, J.U., Basler, D., Braun, S., Buchmann, N., D’Odorico, P., Etzold, S. et al.  (2023). Towards monitoring stem growth phenology from space with high resolution satellite data. Agricultural and Forest Meteorology. 339: 109549.

    13. Elavarasan, D., Vincent, D.R., Sharma, V., Zomaya, A.Y. and Srinivasan, K. (2018). Forecasting yield by integrating Agrarian factors and machine learning models: A survey. Computers and Electronics in Agriculture. 155: 257-282.

    14. Kamilaris, A. and Prenafeta-Boldu, F.X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture. 147: 70-90.

    15. Karakus, P. (2023). Investigation of meteorological effects on Çivril Lake, Turkey, with sentinel-2 data on Google Earth engine platform. Sustainability. 15(18): 13398.

    16. Klerkx, L., Jakku, E. and Labarthe, P. (2019). A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda. NJAS-Wageningen Journal of Life Sciences. 90: 100315.

    17. Kumar, A., Surendra, A., Mohan, H., Valliappan, K. M. and Kirthika, N. (2017). Internet of Things based Smart Irrigation using Regression Algorithm. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) IEEE. pp. 1652-1657. 

    18. Kumari, S., Jeble, S. and Patil, Y.B. (2018). Barriers to technology adoption in agriculture-based industry and its integration into technology acceptance model. International Journal of Agricultural Resources, Governance and Ecology. 14(4): 338-351.

    19. Kundalia, K., Patel, Y. and Shah, M. (2020). Multi-label movie genre detection from a movie poster using knowledge transfer learning. Augmented Human Research. 5(1): 11.

    20. Lahiri, B., Anurag, T. S., Borah, S., Marak, N. R., Pavan Kumar, S. T., Sangma, S. M. et al. (2024). Designing a user-centric mobile-based agro advisory system for sustainable development of smallholder farming systems in the eastern Himalayas, India. Information Technology for Development. 30(4): 665-695.

    21. Liu, C., Cutforth, H., Chai, Q. and Gan, Y. (2016). Farming tactics to reduce the carbon footprint of crop cultivation in semiarid areas: A review. Agronomy for Sustainable Development. 36(4): 69.

    22. Menshchikov, A., Shadrin, D., Prutyanov, V., Lopatkin, D., Sosnin, S., Tsykunov, E. et al. (2021). Real-time detection of hogweed: UAV platform empowered by deep learning. IEEE Transactions on Computers. 70(8): 1175-1188.

    23. Mohan, S.S., Venkat, R., Rahaman, S., Vinayak, M. and Babu, B.H. (2023). Role of AI in agriculture: Applications, limitations and challenges: A review. Agricultural Reviews. 44(2): 231-237. doi: 10.18805/ag.R-2215.

    24. Mehta, A.R., Kumar, P., Prem, G., Aggarwal, S. and Kumar, R. (2025). Leveraging artificial intelligence for disease diagnosis in agricultural crops: A review. Indian Journal of Agricultural Research. 59(5): 681-690. doi: 10.18805/IJARe.A-6363.

    25. Nagpal, J. (2017). Digital Agriculture: Farmers in India are using AI to increase crop yields. Microsoft India News Center.

    26. Oliveira, R.C.D. and Silva, R.D.D.S.E. (2023). Artificial intelligence in agriculture: Benefits, challenges and trends. Applied Sciences. 13(13): 7405.

    27. Oyakhilomen, O. and Zibah, R.G. (2014). Agricultural production and economic growth in Nigeria: Implication for rural poverty alleviation. Quarterly Journal of International Agriculture. 53(3): 207-223.

    28. Pantazi, X.E., Moshou, D. and Bravo, C. (2016). Active learning system for weed species recognition based on hyperspectral sensing. Biosystems Engineering. 146: 193-202.

    29. Patricio, D.I. and Rieder, R. (2018). Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Computers and Electronics in Agriculture. 153: 69-81.

    30. Rajak, P. and Ganguly, A. (2023). In silico study unfolds inhibitory potential of epicatechin gallate against SARS-CoV-2 entry and replication within the host cell. Mechanobiology in Medicine. 1(2): 100015.

    31. Rao, A.N., Wani, S.P. and Ladha, J.K. (2014). Weed Management Research in India- An Analysis of Past and Outlook for Future. In: DWR - Souvenir, Celebrating Silver Jubilee (1989-2014). 2014. Directorate of Weed Research, Jabalpur India. p. 1-26.

    32. Sandric, I., Irimia, R., Petropoulos, G.P., Stateras, D., Kalivas, D. and Ple’oianu, A. (2022). Drone Imagery in Support of Orchards Trees Vegetation Assessment based on Spectral Indices and Deep Learning. In Information and Communication Technologies for Agriculture-Theme I: Sensors. Cham: Springer International Publishing. (pp. 233-248).

    33. Shafi, U., Mumtaz, R., Iqbal, N., Zaidi, S.M.H., Zaidi, S.A.R., Hussain, I. and Mahmood, Z. (2020). A multi-modal approach for crop health mapping using low altitude remote sensing, internet of things (IoT) and machine learning. IEEE Access. 8: 112708-112724.

    34. Sharma, R. (2021). Artificial Intelligence in Agriculture: A Review. In: 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE. (pp. 937-942).

    35. Sharma, U., Tomar, P., Bhardwaj, H. and Sakalle, A. (2021). Artificial Intelligence and Its Implications in Education. In: Impact of AI Technologies on Teaching, Learning and Research in Higher Education. IGI Global. (pp. 222-235).

    36. Subeesh, A. and Mehta, C.R. (2021). Automation and digitization of agriculture using artificial intelligence and internet of things. Artificial Intelligence in Agriculture. 5: 278-291.

    37. Swanton, C.J., Nkoa, R. and Blackshaw, R.E. (2015). Experimental methods for crop-weed competition studies. Weed Science. 63(SP1): 2-11.

    38. Vyas, S., Shabaz, M., Pandit, P., Parvathy, L.R. and Ofori, I. (2022). Integration of artificial intelligence and blockchain technology in healthcare and agriculture. Journal of Food Quality. 1: 4228448.

    39. Wolfert, S., Ge, L., Verdouw, C. and Bogaardt, M.J. (2017). Big data in smart farming-A review. Agricultural Systems. 153: 69-80.
    In this Article
      Contact us
      Follow us
      Published In
      Agricultural Science Digest

      Editorial Board

      View all (0)