Machine learning (ML) is transforming traditional farming practices by enabling data-driven decisions that enhance crop yields, reduce resource waste, and promote environmental sustainability. This review explores ML applications in agriculture, with a focus on crop disease detection, yield prediction, pest management, and irrigation optimisation. Techniques such as convolutional neural networks (CNNs) for image-based diagnostics and regression models for forecasting are examined. Benefits include early intervention to minimise losses, precise resource allocation, and reduced chemical usage, while challenges like data scarcity and computational demands are addressed. By integrating multisource data from drones, satellites, and sensors, ML fosters resilient agricultural systems capable of addressing global food security amid climate variability.
Kaur et al. (Mon,) studied this question.