<p><strong>Background:</strong> In agriculture, Crop Yield Prediction (CYP) by Deep Learning (DL) models such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN) is an emerging technique that utilizes weather, soil and previous year yield information for different crops. On the other hand, these models often struggle to effectively handle time-series data, which can lead to challenges in capturing temporal relationships between weather, soil and crop yield factors. This can affect the accuracy of predicting crop yields.<br />
<br />
<strong>Methods:</strong>&nbsp;To address this issue, the Fixed-Adaptive Temporal Attention Network (FAT-AttNet) is proposed in this study for CYP using a time-series crop yield dataset, which includes historical information on soil, weather and crop yields. A normalization technique is used to preprocess the dataset, removing irregularities and empty values. Next, the FAT-AttNet model is trained to predict crop yields. This model consists of fixed and adaptive temporal modules. In the fixed temporal module, 18 parallel one-dimensional (1D) CNNs are used to process the stable factors, such as soil data, to capture temporal features. In the adaptive temporal module, 16 parallel two-dimensional (2D) CNNs capture the dynamic relationships among weather, soil and crop growth factors over time. The results from these models are combined using the lateral connection and an attention strategy is applied to adjust the weight of each factor for more accurate predictions. Furthermore, a Fully Connected (FC) layer and an output layer are used to predict crop yields.<br />
<br />
<strong>Result:</strong> The experiments are conducted using an agricultural crop yield in Indian States dataset (ACY-ISD) to evaluate the performance of the FAT-AttNet model for five major crops in Tamil Nadu using the historical data from 2002 to 2023.&nbsp; The results show that the FAT-AttNet model achieves a Mean Absolute Error (MAE) of 0.05, 0.059, 0.061, 0.058 and 0.074 for groundnut, maize, moong, rice and urad yield predictions, respectively. &nbsp;The Root Mean Square Error (RMSE) for the groundnut, maize, moong, rice and urad yield predictions is 0.217, 0.268, 0.245, 0.235 and 0.266, respectively. The correlation coefficients for groundnut, maize, moong, rice and urad yield predictions are 0.862, 0.846, 0.864, 0.860 and 0.859, respectively. The results of FAT-AttCNN models outperform the Improved Optimizer Function with Long Short-Term Memory (IOF-LSTM), CNN-Bidirectional LSTM (BiLSTM), MayFly Algorithm empowered attention-BiLSTM (MFA-BiLSTM) and Spatio-Temporal Attention-based CNN (STACNN) models.<br />
&nbsp;</p>


<p>Fixed-adaptive Temporal Attention Network for Predicting Crop Yield</p>


<div>Groundwater level fluctuation modeling is a prime need for effective utilization and planning the conjunctive use in any basin.The application of Artificial Neural Network (ANN) and hybrid Wavelet ANN (WANN) models was investigated in predicting Groundwater level fluctuations. The RMSE of ANN model during calibration and validation were found to be 0.2868 and 0.3648 respectively, whereas for the WANN model the respective values were 0.1946 and 0.1695. Efficiencies during calibration and validation for ANN model were 0.8862 per cent and 0.8465 per cent respectively, whereas for WANN model were found to be much higher with the respective values of 0.9436 per cent and 0.9568 per cent indicating substantial improvement in the model performance. Hence hybrid ANN model is the promising tool to predict water table fluctuation as compared to ANN model.&nbsp;</div>


<div>Comparative Study between Wavelet Artificial Neural Network (WANN) and Artificial Neural Network (ANN) Models for Groundwater Level Forecasting</div>


<div style="text-align: justify;">Soil salinity is the most important soil property that affects the agriculture productivity. Periodical monitoring of its status is considered a crucial factor in the selection of appropriate agricultural practices to attain a sustainable production. The availability of remote sensing data processed by a somewhat novel method such as artificial neural networks (ANN) offer a potential solution that could easily and affordably replace the in-site monitoring methods. The aim of this work is to use high spectral resolution Sentinel-2 (S2) data for soil salinity prediction utilizing neural networks. The study evaluated three approaches in processing the S2 data for inclusion in the artificial neural network for soil salinity prediction. These approaches included S2 spectral reflectance data, spectral indices and principal component analysis (PCA) of the S2 data. The results revealed that a combination of these approaches including the reflectance data of band 11(shortwave infrared band) of S2, the normalized differential vegetation index (NDVI) and the second PCA (dominated by the near infrared band) gave the best performance when used as input when designing the artificial neural networks to predict the soil salinity. The overall accuracy of this approach has a coefficient of determination (R2) of 0.94 between the actual and predicted soil salinity.</div>

Soil salinity mapping utilizing sentinel-2 and neural networks

<div><strong>Background:&nbsp;</strong><em>Portunus trituberculatus</em> is an important economic crab in the East China Sea. With the increase of tonnage and power of offshore fishing vessels, fishing intensity also increases, which has caused great pressure on <em>P. trituberculatus</em> resources. Protecting <em>P. trituberculatus</em> and achieving sustainable utilisation of resources are urgent problems that need to be solved. Therefore, protection and rational development of <em>P. trituberculatus</em> resources are important to accurately understand its spatial and temporal distribution.<br />
<br />
<strong>Methods:</strong> In this study, the temporal and spatial distribution predictive models of <em>P. trituberculatus</em> in the northern East China Sea were built on the basis of three analysis methods (generalised additive model [GAM], random forest [RF] and artificial neural network [ANN]) using bottom trawl survey data and environmental data from 2006 to 2007. The fitting and prediction performances of these three models were compared.<br />
<br />
<strong>Result:</strong> Season and sea bottom temperature were the most important factors on the distribution of <em>P. trituberculatus</em>. The fitting performance of ANNs was better than those of GAMs and RFs, but its predictive performance was worse than those of GAMs and RFs. Therefore, RFs was the appropriate model in predicting the distribution of <em>P. trituberculatus</em> in the northern East China Sea. The abundance of <em>P. trituberculatus</em> was significantly higher in summer than in other seasons (P&lt;0.01) and generally higher in the northern part of the study area than in the southern part in all seasons.</div>


<p>​Spatial and Temporal Distribution of <em>Portunus trituberculatus</em> in the Northern East China Sea based on Different Modelling Approaches</p>


<div><strong>Background:</strong> Healthy transition from non-lactating pregnant state to non-pregnant lactating state is an important in the profitability of dairying. Though feeding and managemental practices play an important role in the adaptation to transition, animals kept on similar feeding and management exhibit differences in adaptation indicating an underlying genetic cause. In the present study, the sequence of gene <em>SNAI2</em>, which is considered to have an effect on metabolic adaptability has been compared among animals with apparently varying adaptability, as indicated by their &beta;-hydroxy butyric acid (BHBA) concentration.<br />
<br />
<strong>Methods:</strong> During the period from August 2018 to May 2019, blood was collected and serum was separated from 30 pregnant cross bred (belonging to Sunandini genetic group of cross bred cattle of Kerala) dairy cows at fortnightly intervals from four weeks before the predicted day of parturition until four weeks after parturition. Concentration of BHBA was determined. Based on BHBA concentration the animals were sorted into two groups (High BHBA and low BHBA) using cluster analysis. Blood was collected, DNA extracted and&nbsp;<em>SNAI2</em> gene amplified using custom synthesised primers. Amplicons from representative animals of each group were sequenced. The sequences obtained were aligned and compared using clustal-&omega;.<br />
<br />
<strong>Result:</strong> The comparison of the sequence of <em>SNAI2</em> gene amongst the animals having high BHBA and those with low BHBA revealed two variations between the groups, one at promoter region, 61 bp upstream to the gene and other was at exonic region at 1560 bp. <em>In silico</em> structural analysis revealed difference in protein structure. The changes observed in the gene <em>SNAI2</em> between the sets of animals grouped based on BHBA has to be studied on a larger population to ascertain the suitability of them being used as markers of genetic selection for metabolic adaptability, which in turn can increase the profitability of dairying.</div>


<p>Molecular Markers for Metabolic Adaptation in Dairy Cows: <em>SNAI2</em> Gene Variations</p>


<div>Duck virus enteritis (DVE) is an acute, contagious herpes viral disease of ducks, geese and swans and members of the family Anatidae under the order Anseriformes. As per the recent taxonomic classification by ICTV, DEV has been classified into the genus Mardivirus, subfamily Alpha-herpesvirinae of the family Herpesviridae. Vaccination is the only option for the prevention and control of Duck plague. In India vaccination is done with chicken embryo adapted live virus which has many shortcomings. So, in this present situation a safe and potent vaccine development is the need of the hour. The use of chicken embryo fibroblast and a certified cell line may, probably, be the best option to achieve this. Therefore, the present study was undertaken for adaptation and propagation of local strain of duck plague virus in various cell culture systems. &nbsp;During the study a wild strain of DPV (DP/As-Km/0019) which was isolated in Duck Embryo Fibroblast, available in the Department of Microbiology was selected. The selected wild strain was used for adaptation in various cell culture systems viz. Chicken embryo fibroblast cell culture (CEF), Vero cell line and QT-35 cell line. The virus was passaged up to 12th passage levels and the presence of viral antigen was demonstrated by appearance of cytopathic effect (CPE), by Polymerase Chain Reaction (PCR) and by Sandwich ELISA. PCR was able to detect virus from all the cell cultures from 5th passage onwards and virus titre was detected at 10th and 12th passage level by S-ELISA. It was observed that various cell culture systems can be a good candidate for propagation of DPV and further study is required to study its immunogenicity and its feasibility as a vaccine candidate.</div>


<div>Adaptation of wild strain of duck plague virus in cell culture systems</div>


<strong>Background: </strong>In contemporary world food crop production is under pressure due to change in climate. In developing nation climate change is a treat both in food crop production and food security. Analysing farmers&rsquo; climate change adaptation measures and understanding the barriers provides clear guidance to address constraints that impede food crop producers&rsquo; adaptation.<br />
&nbsp;<br />
<strong>Methods: </strong>A stratified random sampling technique was used to sample 200 food crop producers for primary data gathering. The multinomial logit model was used to determine the factors that affect the selection of adaptation measures to climate change and factor analysis was used to identify factors that impede food crop producers&rsquo; ability to adapt to climate change.<br />
&nbsp;<br />
<strong>Result: </strong>The result of the multinomial logit model shows that various socio-economic factors&nbsp;(family size, education, climate change awareness, farming experience, nonfarm income, farm size, distance to farmland, extension services and access to credit) influence farmers&rsquo; choices regarding climate change adaptation strategies in the study area. The result of the varimax rotate principal component analysis found four factors that are detrimental to food crop producers in adapting to climate change. These principal constraints are institution and government, technology and inputs, information and knowledge and belief, culture and participation as factors that hinder farmers from adapting to climate change.&nbsp;Thus, there is room for government and development partners to strengthen the adaptive capacities of farmers by resolving problems related to institutions, government policy, technology, inputs availability and information regarding climate change to minimize the potential impact and loss in the future.&nbsp;<br />
&nbsp;

<p>Climate Change Adaptation Measures and Constraints among Smallholder Food Crop Farmers in Sayo and Dale Sedi District, Ethiopia</p>


<div><strong>Background:</strong> Dnipropetrovsk region of Ukraine is located in the northern steppe subzone, where livestock is actively developing, including dairy farming. Cows, imported from other ecological and climatic conditions undergo appropriate acclimatization to new conditions of exploitation. The current research was based on the assessment of the adaptive properties of Holstein cows of different ages to manage and control the level of their milk productivity and reproductive function during exploitation.<br />
<br />
<strong>Methods: </strong>All researches were carried out on the milk complex of &ldquo;Agro-Soyuz&rdquo;. The information base was data on productive qualities in individual cards of cows, results of assessment of zootechnical and veterinary accounting. To achieve this goal, an analysis was conducted from the first to the seventh lactation of Holstein cows.<br />
<br />
<strong>Result:</strong> Our researches allowed establishing the adaptability of Holstein cows of different ages in terms of ecological plasticity of the northern steppe of Ukraine. With a slight imbalance of the organism and the environment cows show high productive qualities at unsatisfactory reproductive function. This work will be a complementary the comprehensive study the adaptation of Holstein cows in different climatic conditions.</div>


<div>Assessment of the Adaptive Stability of the Holstein Cows in the Conditions of the Ecological Plasticity in Northern Steppe of Ukraine</div>


<div><strong>Background:</strong> Variety development is a continuous process that caters for the ever changing farmer crop growing conditions. Changing climatic conditions, soil fertility conditions, crop disease and pest regimes as well as farmer agronomic practices require that new varieties adapted to new practices be availed to growers so that they continue to get high yields. Initial variety development processes are carried out by the breeder, usually on station and usually involves aggregation of traits of interest into a genotype with little or no information about the response of the genotype to different farmer cropping situations. However, before the varieties can be recommended to growers, they need to be evaluated in multi-environment trials (MET) in order to identify varieties with broad adaptation for general recommendation and those with specific adaptation for targeted environment production. &nbsp;<br />
<br />
<strong>Methods:</strong> In order to evaluate the adaptation and stability of newly developed tobacco varieties to three growing locations in Zimbabwe, seven varieties were evaluated in a randomised complete block design with three replicates at Kutsaga Research Station near Harare, Trelawney and Tengwe over three seasons ranging from 2013 to 2015. &nbsp;<br />
<br />
<strong>Result:</strong> The study results showed significant differences among the varieties and locations tested for saleable yield (P&lt;0.05). Of all the varieties tested, T76 was the most stable showing consistently high performance across the seasons and locations tested followed by T75. However, ETH03 was the least stable variety of them all. Unlike what is currently believed in the tobacco industry in Zimbabwe, the variety K RK26 is no longer the most broadly adapted. Based on the study results, the varieties, T76, T75 and ETH06 are stable and, therefore, recommended for growing across the whole of the tobacco farming belt in Zimbabwe.</div>


<div style="text-align:justify">Stability and Adaptation of New Tobacco Varieties to Three Growing Areas under Rain Fed Conditions in Zimbabwe</div>


<p>This review article provides a comprehensive overview of Holstein Friesian dairy cattle&rsquo;s physiological adaptation in Balochistan, a harsh environment that poses significant challenges to animal production. The article reviews various physiological responses and adaptations of Holstein Friesian dairy cattle to thermal stress and water scarcity, which are two of the most significant challenges the animals face in this region. It also highlights several key physiological responses that occur in Holstein Friesian dairy cattle when exposed to thermal stress, such as increased respiratory rate, pulse rateand rectal temperature. Additionally, milk production, somatic cell count (SCC), blood metabolitesand heart rate were identified as valuable indicators for assessing the animal&rsquo;s thermoregulatory mechanisms and detecting the impact of thermal stress. Moreover, adaptations of the sweat gland characteristics, metabolism processes and reduced metabolic requirements were also discussed. This review also highlighted the effect of altitude, hair coatand breed differences on the animals&rsquo; physiological adaptation. The authors stressed the significance of understanding the animals&rsquo; physiological responses to harsh environmental conditions and the importance of measuring these responses accurately in enhancing the animal&rsquo;s productivity and welfare. This review concludes with recommendations for improving the adaptability and performance of Holstein Friesian dairy cattle in Balochistan. Suggestions include implementing crossbreeding programs with indigenous breeds, improving management practices, utilizing physiological parameters to monitor animal health and conducting further research to identify genetic variations that improve animal adaptability. The authors emphasize the significance of these recommendations to increase farmers&rsquo; income, enhance food securityand contribute to the socio-economic development of the region. In conclusion, this review article provides valuable insights into Holstein Friesian dairy cattle&rsquo;s physiological adaptation in Balochistan and can be useful for stakeholders in the dairy industry, policymakersand researchers concerned with improving the sustainability and profitability of animal agriculture in harsh environments.</p>


Fixed-adaptive Temporal Attention Network for Predicting Crop Yield

Comparative Study between Wavelet Artificial Neural Network (WANN) and Artificial Neural Network (ANN) Models for Groundwater Level Forecasting

Soil salinity mapping utilizing sentinel-2 and neural networks

Spatial and Temporal Distribution of Portunus trituberculatus in the Northern East China Sea based on Different Modelling Approaches

Molecular Markers for Metabolic Adaptation in Dairy Cows: SNAI2 Gene Variations

Adaptation of wild strain of duck plague virus in cell culture systems

Climate Change Adaptation Measures and Constraints among Smallholder Food Crop Farmers in Sayo and Dale Sedi District, Ethiopia

Assessment of the Adaptive Stability of the Holstein Cows in the Conditions of the Ecological Plasticity in Northern Steppe of Ukraine

Stability and Adaptation of New Tobacco Varieties to Three Growing Areas under Rain Fed Conditions in Zimbabwe

Holstein Friesian Dairy Cattle Physiological Adaptation in Balochistan: A Review