Background: Accurate fish disease identification is important for ecological research, biodiversity monitoring and conservation. Traditional methods are time-consuming and error-prone. Deep learning provides an automated solution for species classification using image data. Fish disease classification using image-based recognition is an emerging research area, critical for the aquaculture industry. Accurate disease detection is essential for preventing outbreaks, minimizing economic losses and ensuring fish health. 
 
Methods: This study employs the VGGNet-19 architecture to detect fish diseases. The dataset, sourced from Kaggle, contains images of fish affected by various diseases. Images are pre-processed with resizing, normalization and data augmentation techniques, including random flipping, rotation and zoom. The model is trained with an 80%-10%-10% split for training, validation and testing. Performance is evaluated using accuracy, a confusion matrix, a classification report and ROC curves. 
 
Result: The custom model achieved an overall accuracy of 90.96%. It performed well across most disease categories, correctly distinguishing between healthy and infected fish. Some misclassifications were observed between similar diseases, indicating areas for improvement. Despite these challenges, the results demonstrate the effectiveness of deep learning for fish disease classification.

A Deep Convolutional Neural Network for Multi-class Fish Disease Classification using VGGNet-19 Architecture

Background: Tomato is one of the most extensively grown and consumed crops in the world. Diseases, such as bacterial spots and bacterial specks, cause significant economic losses by reducing both yield and quality. These diseases damage and destroy the leaves of tomato plants, making it difficult for the plant to produce fruit. 
&nbsp; 
Methods: The purpose of this work is to use Convolutional Neural Network (CNN) models to diagnose diseases in tomato plants more quickly and accurately. This paper compares the ResNet-152 and VGGNet models for the classification of bacterially-induced tomato leaf diseases. 
&nbsp; 
Result: An accuracy of 98% is achieved using the ResNet-152 model for disease classification.

Convolutional Neural Network Architectures for Enhanced Tomato Leaf Disease Classification using ResNet-152 and VGGNet Model

Background: Wheat is an important crop of India That is grown in the winter season (October to April). A field study was conducted for nine plots having a dimension of 3 &times; 2 meter and different nutrient was applied to test the biomass yield. The objectives are to describe (a): To conduct field experiments under controlled conditions and vary the dosage of fertilizers for different treatments. (b): To observe the variation in crop yield of wheat with different dosages of fertilizers. (c): To model the crop yield of different treatments using InfoCrop and DSSAT crop models. 
 
Methods: An experiment was conducted for Wheat crop having a dimension of 3 &times; 2 meter at the Indian Institute of Technology, UK-India. Three plots (C1, C2, C3) was given control fertilizer supply while plot (F1, F2, F3) given -25%, +25%, +50% and plot (N1, N2, N3) given -25%, +25%, +50% w.r.t to control. The simulation model Infocrop and DSSAT were simulated to check test the model. 
 
Result: In this study, two crop simulation models namely Infocrop and DSSAT were used to predict the yield of wheat crops. Field experiments were carried out at a farm site at Roorkee, India and different treatments of fertilizers are applied to the field plots. In total, seven fertilizer treatments are used: C (controlled with a normal dosage of fertilizers), F1, F2, F3 (varying amount of applied farmyard manure), N1, N2 and N3 (varying amount of applied urea). The objective of the study was to evaluate yields of the seven treatments using Infocrop and DSSAT crop models and compare them to the observed values of yields. The grain yield of the controlled treatment (C1, C2, C3) was predicted accurately by both models. There was a significant variation in the grain yields of the F1, F2, F3 treatments with the application of farm yard manure (FYM). DSSAT under-predicted the grain yields for the plot F1, F2, F3 treatments and over-predicted these for N1, N2, N3 treatments. Overall, Infocrop, which was developed and validated for Indian conditions, simulated the grain yield more accurately as compared to the DSSAT model under varying applications of FYM and urea dosages.

Wheat Yield Modelling using Infocrop and DSSAT Crop Simulation Models

<div>Background: A reliable method for controlling the sex of farm animals has the potential to revolutionize dairy farming. This can only be achieved by use of a method capable of separating X and Y chromosome bearing spermatozoa at lower cost and causing no significant damages to sperm viability. Realizing significance of buffaloes in Indian dairy farming, present study was aimed to develop appropriate density gradient model for enrichment of X chromosome bearing spermatozoa population in semen of Murrah buffalo bull.&nbsp; 
 
Methods: Density gradient centrifugation (DGC) technique was employed for enriching X chromosome spermatozoa in buffalo bull semen using four gradient media viz., Percoll, Optiprep, Ficoll and Sucrose. Percentage enrichment of X chromosome bearing spermatozoa in all the DGC models was determined by SYBR green based Real Time PCR. 
 
Result: Our investigations revealed that number of layers and centrifugation speed (g) factors in a density gradient centrifugation model, have significant effect on the percentage enrichment of X chromosome content in semen samples.Three layers, four layers and five layers density gradient centrifugation models showed significant differences (P&lt;0.05) in the sex ratio towards X spermatozoa population in semen (61.72%&plusmn;0.81, 64.55%&plusmn;0.26 and 67.31&plusmn;0.33%) respectively. Density gradient centrifugation models with centrifugation speed (g) 200x g and 300x g also showed significant differences (P&lt;0.05) in the sex ratio towards X spermatozoa population in semen (66.36%&plusmn;0.25 and 62.69&plusmn;0.22%) respectively. Out of all DGC models, Optiprep density gradient model with 5 layers and centrifugation at 200xg (O3) yielded maximum enrichment (72.4%&plusmn;1.38). In conclusion, O3 poses to be a promising model for enrichment of X spermatozoa in buffalo bull semen.</div>

<div>Five Layered Optiprep based Density Gradient Model is a Promising Model for Enrichment of Viable X Chromosome Bearing Spermatozoa in Bubalus bubalis</div>

<div style="text-align: justify;">Drying is a complex phenomenon and study of drying kinetics and modelling is very important for describing the moisture movement with respect to time and predicting the dryer performance. Considering this fact, vacuum drying characteristics of cherry pepper was studied at different drying temperatures (50, 60 and 70oC). Cherry pepper were dried from initial moisture content of about 400% (dry basis) to 13 &ndash; 14.5% (dry basis) at different temperatures at 630 mm Hg vacuum. Time required to dry cherry peppers at 50, 60 and 70p C plate temperatures were 19 h, 9.75 h and 8 h respectively. Moisture reduction of cherry pepper at various temperatures was modelled using thin-layer models viz. Lewis, Page, Modified Page and Henderson &amp; Pabis model. Based on highest value of coefficient of determination, lowest values of reduced chi square and root mean square error, Modified Page model was found to be the best fit. Moisture diffusivity increased from 6.27 &times; 10-10 to 1.9&times; 10-9m2s-1 as plate temperature increased from 50 &ndash; 70oC. Activation energy was estimated to be 50.98 kJkgmol-1.</div>

Modelling of vacuum drying of cherry pepper

<div style="text-align: justify;">To full fill the demands of increasing population for agricultural products, increases pressure on land, water, and other natural resources, to fulfils this demands and to take decision about agricultural product requires information about production, productivity &nbsp;of crop also for proper management and carried out intercultural operations &nbsp;need advanced information about crop phenology, pest and diseases presently it is possible to generate such advanced information through well validated crop growth simulation models such as CERES, WOFOST, SUCROS, and APSIM. These models provided such advanced information based on integrate the effects of different factors viz., increasing temperature, soil productivity, also consider changes in climatic on productivity. The present paper describes the review of research work done on crop simulation model as well as covers detailed information about WOFOST model.&nbsp;</div>

Use of WOFOST model in agriculture- A review&nbsp;

<div>More than 10 million laborer have been displaced from their usual workplaces during the suddenly announced lockdown by the government of India in 2020 in order to prevent and control the spread of one of the deadliest diseases of our times namely; COVID 19, popularly known as Sars Corona Virus in March - June 2020; as per the official figures provided by the GOI. There has not been a single sector that remained unaffected from the devastating impacts of COVID-19, not even agriculture. The impact of lockdown on agriculture is hard to measure as it involves a complex relationship between multiple direct and indirect factors like labour availability, lack of supply of raw materials from the agro-industrial sector etc. The lockdown period created severe economic implications (negative) for farmers (small, marginal and large), landless laborer and all the other agricultural stakeholders who had to face new challenges for earning their livelihood. The direct loss to the agriculture sector was estimated to multi-corers by various government officials while the indirect losses may be many folds of the direct loss. The marginal income of laborers in the agriculture sector was believed to be coming close to zero due to lockdown conditions. In addition to this, smart investments, improved technologies and standardized model frameworks must be designed for the agriculture sector to combat the COVID 19 impact. The current analytical review is focused on all the major factors associated with the agriculture sector that have been highly impacted by the COVID-19 pandemic, ranging from production, storage to procurement and selling. The lockdown has choked off almost all economic activities. In urban areas, COVID-19 forced widespread loss of jobs and incomes for informal workers. Estimated by the Centre for Monitoring Indian Economy, unemployment shot up from 8.4% in mid-March to 23% in the first week of April 2020 further soaring to 30.9% by the end of April, 2020. We have also looked into the possible strategies that can be taken into consideration by the government as well as those associated with the agricultural-food sector. This pandemic has emerged several new challenges to the agricultural sector but has given us time to think and strategize things for better management in future. Suggestions have also been made to adopt alternate approaches and work in this newly created world with the ability of better resource handling.</div>

​Impact of COVID-19 Lockdown on Indian Agriculture: A Review

<div>Background: The determination of the soil moisture characteristic is a tedious, lengthy and costly laboratory methods. However, for the specific soil texture, once it is known, the soil moisture at various tension can be simulated through modelling approach which eliminates the requirements of performing the experiments every time. Therefore, the attempt was made for the determinations of the soil moisture characteristics during the year-2019 and validating the various models&rsquo; using these empirical data. 
&nbsp;&nbsp; 
Methods: The present research covers the experimentation during the year 2019 for determination of the soil moisture characteristics and fitting the obtained empirical data to mathematical frames of the various models. The moisture characteristics was obtained by measuring different moisture content values at different suction values through two experiments viz. wetting cycle (Absorption phase) and drying cycle (Desorption phase). The desorption curve was obtained by using the pressure plate apparatus and the wetting curve was measured through the capillary rise open tube method. 
&nbsp; 
Result: The saturation, field capacity, permanent wilting, residual moisture content, void ratio and saturated hydraulic conductivity were found as 43.5%v/v, 25.88%v/v, 12.05%v/v, 8.1%v/v. 0.77 and 0.2808 m/day respectively. Among the fitted models, the van Genuchten model was found best fit to observe data to simulate the desorption and sorption phase of the soil moisture retention characteristics. The soil moisture retention characteristics of the sorption and desorption phases indicated a hysteresis of approximately two log cycles.&nbsp;</div>

Validation of Models for Simulating the Soil Moisture Characteristics

<div>Background: E-learning is now being used in a variety of industries, including agriculture. The use of information and communication technologies (ICTs) is seen as essential for overcoming the barriers that a developing country faces in all areas and closing the digital divide. Farmers must be prepared with the most recent breakthroughs in ICTs in order to take advantage of new opportunities in the global market. 
 
Methods: By designing an e-learning module and providing farmers with a self-learning framework, the study focuses on the use of ICT instruments in climate-smart horticulture. The psychological factors in this study were investigated using the E-Learning Acceptance Model (ELAM), which was derived from the Technology Acceptance Model (TAM). A quantitative survey of 200 farmers were conducted. Structural equation modelling (SEM) was used to test the research hypotheses. 
 
Result: ELAM has enough predictive ability to explain farmers&rsquo; behavioural intention to utilise an e-learning module in a real world. In total, the result supports five ELAM hypotheses. The SEM findings indicate that ELAM is a valid model. In ELAM, partial mediation was also observed.</div>

Acceptance of an E-learning Module on Climate-smart Horticulture: A Structural Equation Model

Background: Wheat quality and safety are crucial for global food security and regional agricultural economies. Conventional analytical methods for assessing grain composition and quality-while accurate-are often time-consuming, destructive and resource-intensive. In contrast, near-infrared spectroscopy (NIR) has emerged as a rapid, non-destructive alternative that provides detailed chemical and physical insights. Recent advancements in machine learning have enhanced NIR&rsquo;s analytical capabilities by enabling the development of predictive models that accurately categorize, quantify and monitor grain quality parameters. These models-spanning from linear regression methods to intricate neural networks-enable researchers to discern significant patterns from spectral data, even amidst noise or overlapping signals. 
&nbsp; 
Methods: This study used NIR spectroscopy and machine learning models to evaluate wheat quality across multiple Albanian regions during the 2023 harvest. NIR spectra were preprocessed using standard normalization and smoothing techniques. Machine learning models-including PLSR, SVM and random forest-were trained to predict key quality traits such as protein content and moisture. Model performance was validated using cross-validation metrics (RMSE, R&sup2;, accuracy), demonstrating the potential of NIR-ML integration for rapid, non-destructive grain assessment. 
&nbsp; 
Result: Protein content ranged from 9.6% to 15.0%, gluten from 19.4% to 37.5% and starch from 66.3% to 71.5%, indicating consistent nutritional profiles across samples. Sedimentation index values (21.1-57.8 cm&sup3;) and moisture levels (9.8-12.5%) confirmed compliance with EU food safety standards. The integration of NIR spectroscopy with machine learning enabled rapid, non-destructive prediction of wheat quality traits, supporting scalable decision-making in agri-food systems.