COVID-19 caused unprecedented disruption globally, infecting approximately 40 million individuals in India and claiming more than 500,000 lives. India’s gross domestic product (GDP) contracted by a record 23.9% in the quarter ending June 2020 as a result of prolonged shutdowns and restrictions on transportation and mobility. Rural and farm-based livelihoods, already under multiple biotic and abiotic pressures, were severely impacted. To assess the socioeconomic vulnerability—encompassing exposure, sensitivity, and adaptive capacity—of farm-based livelihoods affected by COVID-19, a composite livelihood vulnerability index (LVI) was developed using the Intergovernmental Panel on Climate Change (IPCC) framework. The study adopted a concurrent mixed-methods design. Secondary cross-sectional quantitative data from government sources were complemented by qualitative data gathered through in-depth interviews (IDIs) and focus group discussions (FGDs) conducted with farming households across the sampled districts. The quantitative component covered a randomly selected sample of 20% of the rural districts from the five highest COVID-19-affected Indian states: Uttar Pradesh (Northern), Karnataka (Southern), West Bengal (Eastern), Maharashtra (Western), and Assam (North-Eastern). The adaptive capacity component of the framework includes natural, physical, financial, human, social, and emotional capital. The results of the study suggested that the average composite vulnerability index value was 0.104. Of the 30 districts assessed, 26 (86.66%) were found to be vulnerable. The farming population (7.1%), the literacy rate (6.8%), and the rural population (3.04%) were the strongest contributors to adaptive capacity. West Bengal required improvements in physical, financial, and emotional capital. Assam reported the lowest levels of physical, financial, and human capital. Maharashtra exhibited the highest level of exposure, while Uttar Pradesh reported the highest level of sensitivity due to extreme climatic events, pest burden, and low crop diversity. In conclusion, it is suggested to institutionalize the longitudinal monitoring of both quantitative vulnerability indices and qualitative community well-being indicators across these states, integrating climate vulnerability models for proactive shock-proofing of farm livelihoods.

Classification in agricultural systems are quite useful for planning for which decision trees like Classification And Regression Trees (CART) can be used effectively. Additionally, data in reality involves fuzziness that necessitates development of CART which can handle them. As against crisp boundaries between which elements are members and non-members of a particular set, fuzzy set theory offers degree of membership anywhere between 0 and 1 to each set element. Fuzzy based CART has been dealt with in this study considering agricultural ergonomics data with response variable taking levels as presence/ absence of discomfort for labourers during farm operation. The associated variables were both categorical: farm machinery load, operation modes, percent aerobic capacity of farm labourers and continuous: difference between working/ resting heart rates, oxygen consumption during farm operation. The data was divided into training and test sets for model building and validation respectively. Membership function for each variable has been defined with the aid of linguistic variables, using which all the variables were fuzzified. The conventional CART was obtained and complexity parameter was used to prune the tree. The set of ‘if-then’ rules obtained from this CART formed the knowledge base for the fuzzy inference system (FIS) to build conventional Fuzzy CART. The inputs were given to FIS and the outputs for making decisions were defuzzified into crisp values indicating the degree of discomfort. For comparison, those values greater than 0.5 were taken as presence of discomfort, absence otherwise. As an improvement to this Fuzzy CART, the bias due to simultaneous selection of the split variable and the split point in CART was overcome by using separate selection procedures, while other steps remained the same. This proposed Fuzzy CART model was found to be outperforming the existing CART approaches viz., conventional CART, a certain modified CART (method obtained by earlier workers wherein separate selection procedures for split variable and split point as mentioned above were employed in conventional CART) and Fuzzy CART methods when the results were compared using the correct classification rate. Even though model based logistic regression outperformed the proposed Fuzzy CART, the latter has many advantages over the former. Thus it has been demonstrated that Fuzzy CART can be used as a viable alternative for classification purposes in agricultural domain.

Background:Malnutrition continues to be a major global health challenge affecting millions of vulnerable populations across countries. Despite their critical contribution to agricultural productivity, limited evidence exists regarding the dietary diversity and nutritional status of rural labourers in South India. Therefore, the present study aimed to assess dietary diversity and its associated factors among rural labourers in South India. Methods:A community-based cross-sectional study was conducted among 320 rural labourers (men aged 15-54 years and women aged 15-49 years, excluding pregnant and lactating women) and those who were actively engaged in farming and household activities. Respondents were selected using a multistage random sampling method. Data were collected through a structured interview schedule, and the collected data were entered into Excel and analyzed using R Studio (v4.2.2). The dietary diversity score was computed based on the 24-h recall method. Nutritional status was analyzed using the body mass index (BMI), mid-upper arm circumference (MUAC), and calf circumference. Pearson's chi-squared test was used to determine the association between dietary diversity and nutritional status at a significance level of p < 0.05. Results:The findings of this study revealed that the dietary diversity among rural labourers was limited, with heavy reliance on locally available staple foods. In Andhra Pradesh, the majority of men (63.75%) and women (78.75%) had medium dietary diversity; however, men had relatively better diversity, with 21.25% attaining high dietary diversity compared to only 1.25% of women. Comparatively, in Telangana, the majority of men (68.75%) and women (52.50%) were also in the medium dietary diversity category. Although a larger portion of women (30.00%) were in the lowest category, 17.50% of women had high dietary diversity. This reduced the gender gap that existed in Andhra Pradesh. A significant association was observed between dietary diversity and nutritional status of rural labourers (p < 0.05). Conclusion:The study highlighted the low dietary diversity and the existence of undernutrition among rural labourers in South India. This emphasises the need for nutrition education, the promotion of household and community nutrition gardens, and greater awareness of balanced diets, all of which could help improve dietary intake. Furthermore, implementing nutrition and health awareness programmes together with anthropometric indices can aid policymakers in assessing the effectiveness of the Public Distribution System. These efforts can be the basis for the development of targeted interventions that will not only change food consumption patterns but also improve the nutritional status of rural labourers.

Drought is a persistent environmental challenge with profound impacts on water resources, agriculture, and ecosystems, particularly in semi-arid regions. This study investigates the spatial and temporal dynamics of drought in the Southern Telangana Zone (STZ) using the Standardized Precipitation Evapotranspiration Index (SPEI) across 12 districts over the past 44 years. Results highlight considerable variability in drought intensity and frequency, with extreme value distribution analysis indicating an increasing risk of severe drought events in the future. To enhance predictive capability, several time series models were developed, including ARIMA, STARMA, and a novel two-stage STARMA-TDNN framework that integrates spatiotemporal linear modeling with nonlinear machine learning. The proposed triangular fuzzy STARMA-TDNN model achieved the highest efficiency, reducing training and testing mean squared error by more than 70 % compared to alternative approaches. While ARIMA captured only temporal linear patterns and STARMA addressed linear spatiotemporal dependencies, the two-stage STARMA-TDNN framework effectively represented both linear and nonlinear spatiotemporal drought dynamics. The Diebold-Mariano test further confirmed the statistical superiority of the two-stage model. These findings underscore the potential of advanced hybrid models for reliable drought forecasting and provide a scientific basis for location-specific drought management strategies in the STZ.

Rice is one of the most important cereal crops which supports food security to billions of people across the world. However, it is vulnerable to several insect-pest infestations which significantly damage the crop and reduce the overall yield. Traditional pest management practices aim to minimize damage of crops relying on manual field inspection, which are labour-intensive, time consuming, and prone to human error. With recent advances in deep learning, automated detection frameworks like YOLO networks, have emerged as promising tools for real-time insect-pest detection for crops. In this study, we proposed an improved lightweight network named YOLODWSimAM, built upon the baseline YOLOv11 architecture. In the proposed network, a simple parameter-free attention module (SimAM) and a depthwise convolution (DWConv) are integrated into a lightweight unified block, DW-SimAM, which enhances the network's feature extraction capability with reduced trainable parameters. An insect-pest dataset, consisting of 1721 images, was acquired from different rice fields and annotated with bounding boxes to locate the instances of insect-pests within the images. With only 1.93 million trainable parameters and 4.9 GFLOPs, the proposed YOLO-DWSimAM network achieved an mAP@50 of 0.851 on the test dataset, outperforming the baseline YOLOv11 architecture by 1.19%. Additionally, the proposed YOLODWSimAM network demonstrated strong performance on the edge device, especially Raspberry Pi 4, for rice insect-pest detection, achieving average inference speed of 0.67 s and FPS of 1.49 using input images of size 640 & times; 640. These findings validated that the proposed network achieved higher detection accuracy while being computationally efficient, making it suitable for real-time insect-pest management in resource-constrained agricultural environment.

The Autoregressive Integrated Moving Average (ARIMA) model requires appropriate selection of autoregressive (p), differencing (d), and moving average (q) orders for accurate forecasting. Conventional order selection methods, such as grid search and stepwise information-criterion approaches, can be computationally expensive and prone to suboptimal solutions. This study proposes ARIMA–Spider Monkey Optimization (ARIMA–SMO), an automated framework that employs Spider Monkey Optimization to identify optimal ARIMA orders. In the proposed approach, each spider monkey represents a candidate ARIMA (p,d,q) configuration, and model fitness is evaluated using a combination of statistical goodness-of-fit and forecasting accuracy. The local and global leader mechanisms, together with adaptive subgroup restructuring, balance exploration and exploitation of the search space. The method was evaluated using agricultural production time series from India and compared with Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Bayesian Optimization (BO)-based ARIMA models. Across all six-production series, ARIMA–SMO consistently achieved the lowest forecasting errors while requiring less computational time than the competing approaches. For the total food grains series, ARIMA–SMO reduced the test RMSE to 35.75 compared with 43.96 (GA), 39.84 (PSO), and 37.12 (BO). The results demonstrate that ARIMA–SMO is an effective and computationally efficient framework for automatic ARIMA order selection and time-series forecasting.

Meteorological drought, a recurrent manifestation of climate variability, poses significant challenges to sustainable water resource management and agricultural planning in India. This study investigates the comparative performance of stochastic and artificial intelligence (AI)-based models for forecasting meteorological drought using monthly precipitation data (1981–2021) from Sagar and Chhatarpur districts of Madhya Pradesh, India. The primary objective is to identify the most reliable model capable of capturing complex temporal dependencies in the Standardized Precipitation Index (SPI) series. A suite of models, including Auto-Regressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) networks, were employed. The LSTM demonstrated superior predictive accuracy, achieving reductions in root mean square error (RMSE) of 71.4

Accurate detection of wheat spikes and reliable yield prediction are critical for optimizing crop production and resource management. This study presents an integrated framework for spike detection and yield estimation using pseudo-RGB images derived from hyperspectral data. A YOLOv8 model was trained on 1,050 images, achieving high precision, recall, and mean average precision values. The bounding boxes and masks generated byYOLOv8 were used to quantify spike count and spike area, while six vegetation indices were extracted from hyperspectral images acquired at the booting stage. Three multiple linear regression models were developed for yield prediction: one based on spike features, another on vegetation indices, and a third combining both. The combined model achieved the highest accuracy, with a five-fold cross-validation R2of 0.902 +/- 0.007, RMSE of 1.739 +/- 0.133 g,and MAE of 1.289 +/- 0.066 g. Compared with previous approaches, the proposed framework demonstrated improved performance, highlighting the value of integrating spike morphology and spectral data for yield prediction. Overall, the study shows that hyperspectral imaging can simultaneously provide morphological and physiological traits, reducing reliance on high-resolution RGB data in wheat phenotyping

Heatwaves are extreme climatic events that have become increasingly frequent and intense due to climate change, posing significant threats to ecosystems, agriculture, and human health. Timely understanding and proactive management of heatwaves are crucial for mitigating their impacts on environment. The Heatwave Magnitude Index daily (HWMId) was calculated using daily temperature data collected across various districts of Telangana, India, from January 1960 to December 2022 to assess the intensity and duration of heatwave events. The study employs various statistical techniques including linear regression, Mann–Kendall test, Modified Mann–Kendall (MMK) test, and Innovative Trend Analysis (ITA) to assess both the direction and intensity of trends. The results indicate a statistically significant increasing trend in heatwave magnitude across most districts. The MMK test confirmed significant upward trends in all districts. ITA showed significant increasing trends at different significance levels (10

IntroductionTeaching effectiveness is a critical determinant of learning quality, skill development, and academic performance in agricultural higher education. However, empirically grounded assessments remain limited in Indian agricultural universities, where challenges related to pedagogy, student engagement, and institutional support persist. This study develops a multidimensional, statistically derived Teaching Effectiveness Index (TEI) to evaluate student-perceived teaching effectiveness across three premier agricultural institutions.MethodsData were collected from 180 postgraduate students using a structured questionnaire comprising 75 sub-indicators across three dimensions: Pedagogical Proficiency, Learning Engagement, and Educational Environment Dynamics. Principal Component Analysis (PCA) was used to derive empirical weights for constructing the TEI, and institutional differences were assessed through non-parametric tests. The Analytic Hierarchy Process (AHP) was applied in parallel to identify and prioritize student-perceived constraints affecting teaching effectiveness.ResultsThe Indian Agricultural Research Institute (IARI) achieved the highest TEI score (0.74), followed by GBPUAT and BHU (0.71 each). PCA indicated that innovative teaching strategies, technology integration, meaningful internships, and resource adequacy contributed most strongly to teaching effectiveness. AHP analysis ranked research-related constraints as the most critical barriers (priority weight = 0.267), followed by knowledge-development (0.229) and course-related constraints (0.206).DiscussionProminent challenges included the non-provision of research funds, inadequate laboratory facilities, limited software-related guidance, and insufficient practical exposure. This study demonstrates the value of integrating PCA-based empirical weighting with AHP-based prioritization to produce a comprehensive, scalable framework for evaluating teaching effectiveness. The findings underscore the need for targeted reforms to enhance pedagogical innovation, strengthen research and digital infrastructure, and expand experiential learning opportunities in agricultural universities.

Rainfall is a critical climatic factor influencing ecosystems, agriculture, and water resources, particularly in India, where agriculture relies heavily on rain-fed conditions. The fluctuations in this climatic element hold significant importance for researchers and policymakers as this influence decision-making processes. This research aims to analyze the precipitation patterns in Bundelkhand region consisting of parts of Uttar Pradesh and Madhya Pradesh states of India, during 1951 to 2023 and project future trends using time series (TS) clustering methods. TS clustering, which identifies patterns in climatic data through techniques like Singular Spectrum Analysis (SSA), offers valuable insights into the trends, seasonality, and autocorrelations of rainfall data. By clustering these patterns, the study seeks to enhance understanding of rainfall variability, providing a basis for improved agricultural planning and decision-making. Additionally, the projections of the rainfall have also been done for future 24 months. The result clearly identifies two different zones (clusters) in the Bundelkhand region and in both the zones (Southern and Northern), a decrease in rainfall patterns has been noted over time. Total rainfall is more in Southern part as well as fluctuations in rainfall is less as compared to Northern part. The yearly rainfall in the Bundelkhand region is strongly irregular throughout the period, unevenly spread across the months; and highly concentrated in one third of the year.

Accurate forecasting of agricultural commodity prices is crucial for maintaining market stability, effective risk management, and informed decision-making, particularly in developing economies with high price volatility and heterogeneous market structures. Traditional statistical models and recurrent deep learning approaches often struggle to capture nonlinear dynamics, abrupt fluctuations, and long-range temporal dependencies in agricultural price series. To overcome these limitations, this study proposes a CNN-Transformer hybrid architecture that combines the local feature extraction of Convolutional Neural Networks (CNNs) with the global dependency modelling of Transformer self-attention mechanisms, specifically designed to address limitations of existing hybrid models such as sequential bottlenecks, vanishing gradients, and limited scalability. The framework is evaluated on weekly potato prices from four structurally diverse Indian markets-Azadpur, Ludhiana, Dehradun, and Farrukhabad, covering varying data lengths and volatility regimes. Systematic hyperparameter tuning and extensive experiments demonstrate that the CNN-Transformer consistently outperforms established benchmarks, including CNN, LSTM, Bi-LSTM, GRU, CNN-LSTM, and standalone Transformer models, across RMSE, MAE, and MAPE metrics.

The complex nature of agricultural price data, characterized by perishability, seasonality, and non-stationarity, often renders conventional forecasting models inadequate. To address these challenges, this study proposes two hybrid learning frameworks: Stacked Autoencoder-based Deep Learning (SAE-DL) and Denoising Stacked Autoencoder-based Deep Learning (DSAE-DL). These models represent a significant departure from existing deep learning (DL) models, such as Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), 1D Convolutional Neural Network (1D CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). Unlike these standard models, which process raw input directly and often struggle with data volatility, our proposed hybrid approach integrates an autoencoder bottleneck to perform hierarchical feature extraction and dimensionality reduction prior to forecasting. The SAE-DL model focuses on capturing the underlying compressed representation of the price series, while the DSAE-DL introduces a stochastic denoising mechanism to specifically reconstruct core features from noisy data and outliers. Empirical analysis using a real-world onion price dataset reveals that the proposed DSAE-DL models, particularly the DSAE-RNN configuration, consistently outperform all other models across metrics, including RMSE, MAE, and MAPE. The Diebold-Mariano (DM) test further confirms that both proposed hybrid frameworks, SAE-DL and DSAE-DL, significantly improve prediction accuracy compared to standalone DL models. These findings highlight the superior robustness of hybrid autoencoder-based architectures in contending with market volatility.

Accurate and strategic price forecasting plays a crucial role in enabling stakeholders to make well-informed decisions and effectively navigate the complexities of market uncertainties. Price data is inherently complex, and conventional models often fall short in capturing its intricate patterns and variations. To address these challenges, models that can capture both linear and nonlinear relationships are necessary. Hybrid models have emerged as a robust solution to capture linear and nonlinear patterns in complex datasets, making them particularly effective at addressing the complexities of price prediction. This study highlights the efficiency of hybrid models in price modelling using the price data of pomegranate, which is recognized for its significant nutritional and economic importance in the horticultural sector. Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Root Mean Square Percentage Error (RMSPE), and Median Absolute Percentage Error (Median APE) used to assess the model performance. The findings reveal that hybrid models, such as ARIMA-SVR in Bangalore, ARIMA-ANN in Chennai and Hyderabad, and ARIMA-RF in the Trivandrum market consistently outperform the benchmark models. These hybrid approaches combine the strengths of conventional and machine learning techniques, providing more reliable and accurate predictions for the distinct data characteristics of each region.

Rainfall is a critical climatic factor influencing ecosystems, agriculture, and water resources, particularly in India, where agriculture relies heavily on rain-fed conditions. Fluctuations in this climatic element hold significant importance for researchers and policymakers as these influences decision-making processes. The study aims to analyze precipitation patterns in the Bundelkhand region, Awhich includes parts of Uttar Pradesh and Madhya Pradesh in India, from 1951 to 2023, Aand to project future trends using time series (TS) Aclustering methods. TS clustering, which identifies patterns in climatic data using techniques like Singular Spectrum Analysis (SSA), Aoffers valuable insights into trends, seasonality, and autocorrelations of rainfall data. By clustering these patterns, the study seeks to enhance understanding of rainfall variability, providing a basis for improved agricultural planning and decision-making. The projections of the rainfall have also been made for the next 24 months. The result identifies two different zones (clusters) in the Bundelkhand region, and in both zones (Southern and Northern), a decrease in rainfall patterns has been noted over time. Total rainfall is higher in the southern part, and fluctuations in rainfall are less compared to the northern part. The yearly rainfall in the Bundelkhand region is highly irregular throughout the period, unevenly distributed across the months, and highly concentrated in one-third of the year.

Deep learning-based methods have shown promise for automated leaf detection and counting, particularly in rosette species. However, automated leaf counting remains limited for orchids such as Dendrobium nobile, which have a complex non-rosette architecture, alternate phyllotaxy, overlapping leaves, and view-dependent occlusion. This study developed an automated leaf-counting framework for D. nobile using YOLOv5-based object detection and translated the selected model into a GUI-based desktop application, DnLC (Dendrobium nobile Leaf Counter). A DSLR camera captured high-resolution whole-plant images while each pot was manually rotated to acquire 16 multi-view frames over 360°. Roboflow was used to annotate 766 whole-plant images, generating approximately 10,490 leaf annotations. The dataset was divided into training, validation, and test subsets to evaluate YOLOv5 variants under transfer-learning and training-from-scratch strategies. Standard detection metrics, computational cost, and an Average Rank-based model-selection approach were used to assess model performance. Among the evaluated variants, YOLOv5l provided the most balanced performance and was integrated into DnLC for automated image loading, leaf detection, bounding-box visualization, and leaf-count estimation. Software-level validation on 354 independent unseen D. nobile images using CVPPP Leaf Counting Challenge metrics showed close agreement with manual counts, with DiC of − 0.95 ± 1.45, |DiC| of 1.15 ± 1.30, MAE of 1.10, MSE of 3.00, MAPE of 8.44%, and PA of 43.91%. Overall, DnLC provides a standardized, non-destructive leaf-counting tool for D. nobile phenotyping, supporting greenhouse growth monitoring, treatment-response evaluation, and high-throughput plant screening.

This study used time-scaled crop productivity for spatial comparisons among leading cereal producers, as it measures crop output per hectare per day and accounts for the number of days required to reach the same output level across regions. The results indicated that rice's per-hectare crop productivity in India (4.22 t/ha) was lower than in Bangladesh (4.89 t/ha), but it surpassed Bangladesh's by 20 kg/ha/day when the new metrics were used. Similarly, for wheat, India (3.53 t/ha) ranked third after China (5.85 t/ha) and Russia (3.55 t/ha); however, in terms of its time-scaled productivity, India and China leads with 24 kg/ha/day followed by Australia (14 kg/ha/day) and Russia (12 kg/ha/day). For maize, its ranked the same in both per-hectare and time-scaled crop productivity. Structural break analysis was used to identify significant shifts in rice, wheat, and maize output in India from 1950-51 to 2020-21 and to link these changes to technological progress, institutional factors, and policy reforms. Results showed that over the past 70 years, rice and wheat outputs experienced five structural breaks, while maize had four, corresponding to key technological and policy changes.