Applications of machine learning and deep learning in agriculture: A comprehensive review

Abstract

The digitalization of agriculture has increasingly integrated artificial intelligence (AI), machine learning (ML), and deep learning (DL) to address the challenges arising from population growth, climate change (CC), and resource limitations. This study provides a comprehensive review of the potential applications of AI techniques across various stages of agricultural production, with a particular focus on innovations that align with climate-smart agricultural practices. The review encompasses research conducted from 2018–2024, emphasizing the use of ML and DL in areas such as crop selection, land monitoring and management, water, soil and nutrient management, weed control, harvest and post-harvest practices, pest and insect management, and soil management. The findings underscore that ML and DL facilitate the analysis of complex datasets, enabling data-driven decision-making, reducing reliance on subjective expertise, and improving farm management strategies. Despite challenges such as data availability, model interpretability, scalability, security concerns, and user interface design, which hinder the widespread adoption of ML and DL methodologies, collaborative efforts among stakeholders can help overcome these barriers. This review concludes that ongoing advancements in ML and DL present significant opportunities to enhance agricultural productivity, sustainability, and resilience. By leveraging data-driven insights and innovative technologies, the agricultural sector can transition toward more efficient, environmentally sustainable, and economically viable practices, contributing to global food security and environmental preservation.