The growing demand for food grains amidst resource constraints necessitates advancements in crop management. Artificial intelligence, particularly machine learning and deep learning, is revolutionizing agricultural practices by enabling data-driven, precise, and sustainable solutions. This review synthesizes advancements in artificial intelligence applications across key domains, including crop yield prediction, precision irrigation, soil fertility mapping, insect pest and disease forecasting, and foodgrain quality assessment. Artificial intelligence algorithms efficiently process vast datasets from unmanned aerial vehicles, ground vehicles, and satellites, enabling precise and timely interventions. Artificial intelligence-driven tools automate pest detection and classification, optimize irrigation with minimal human input, generate high-resolution soil fertility maps, and enhance foodgrain quality assessment through rapid defect and contaminant detection. Artificial intelligence-powered precision irrigation integrates real-time soil moisture data and weather predictions for optimized water usage. Similarly, artificial intelligence-driven soil fertility mapping not only enables high-resolution assessments but also facilitates real-time monitoring of nutrient dynamics, supporting sustainable land management. In pest and disease detection, artificial intelligence systems combining image processing and real-time analytics demonstrate promise for early intervention. Artificial intelligence integration into foodgrain quality assessment leverages hyperspectral imaging and predictive models to enhance grading, adulteration detection, and contaminant screening, contributing to food safety and market competitiveness. Furthermore, advancements in transfer learning and data augmentation have improved artificial intelligence adoption in regions with limited datasets. While artificial intelligence technologies promise to boost agricultural productivity and sustainability, their efficacy and scalability hinges on data quality, diversity, and availability. Graphical Abstract

Rapeseed-mustard (Brassica spp.) is one of the important edible oilseeds crops in India. The same level of weather condition impacts the growth and establishment of rapeseed-mustard plant differently in different stages of crop which lead to large intra-seasonal yield variations. Hence it is essential to give weightage to weekly weather conditions while fitting predictive model. In this present study, path-coefficient based weighted index was proposed along with existing unweighted and correlation based weighted index. The performance of penalized regression models viz. Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net (ENET) were compared with Multiple Linear Regression (MLR) for predicting rapeseed-mustard yield using weather-indices. The results revealed that the path-coefficient based weighting of weather parameters to the yield were stable than correlation based weighted-indices. Path-coefficient based weighted indices of maximum temperature, minimum temperature and windspeed were important variables in projection of yield. The performance of MLR was poor during validation of model due to overfitting issue. The performance of penalized models was stable in both calibration and validation of the model. The LASSO and ENET models that accompanied with coefficient shrinkage and variable selection were found to be the best fitted models for predicting Rapeseed-Mustard yield.