Artificial Intelligence for Sustainable Agriculture: A Systematic Literature Review of Applications, Resource Optimization, and Sustainability Outcomes

Abstract

Artificial Intelligence (AI) has increasingly emerged as an important technology for supporting sustainable agricultural practices and improving the efficiency of agricultural resource management. This systematic literature review examines the role of AI in sustainable agriculture, focusing on its major applications, contributions to resource optimization, and reported sustainability outcomes. The review analysed literature published between 2020 and 2025 using a systematic review approach guided by the PRISMA 2020 framework. The analysis focused on three interconnected dimensions: AI applications in agricultural production and management, optimization of agricultural resources, and environmental, agricultural, and economic sustainability outcomes. The findings indicate that AI is widely applied to crop monitoring, yield prediction, disease and pest detection, smart irrigation, soil and nutrient management, precision farming, and agricultural automation. The synthesis further shows that AI can support more efficient use of water, fertilizers, pesticides, energy, labor, and other agricultural inputs by enabling data-driven prediction and decision-making. These improvements are associated with potential gains in agricultural productivity, resource efficiency, environmental protection, and economic performance. However, the sustainability benefits of AI remain influenced by data quality, implementation costs, digital infrastructure, technical skills, model interpretability, and unequal access to technology. Overall, the review identifies a pathway in which AI applications support data-driven decisions, resource optimization, agricultural efficiency, and ultimately sustainability outcomes. Future research should therefore emphasize practical implementation, accessibility, cost-effectiveness, responsible AI, and long-term sustainability impacts, particularly in diverse agricultural and smallholder farming contexts.