Systematic review of artificial intelligence in precision agriculture for smallholder farmers
TL;DR
This review provides a holistic view of AI-driven precision agriculture by synthesising evidence on technical performance, socio-economic and policy considerations and highlights the importance of context-sensitive, inclusive and farmer-friendly AI technologies to drive equitable and sustainable digital agriculture.
Abstract
The application of Artificial Intelligence (AI) technologies in precision agriculture has potential to enhance agricultural productivity and farm management, especially in smallholder settings. The research seeks to explore the use, benefits and barriers of AI technologies in smallholder farming. Through a systematic review of 50 peer-reviewed research papers sourced from major academic databases, the study reveals common themes focusing on the application of technologies, barriers to adoption, and facilitating factors in the use of AI in smallholder farming. This review highlights the major applications of AI in agriculture, such as machine learning-based disease diagnosis, yield modeling, smart irrigation, and decision support. Analysis suggests that these tools hold great promise for boosting farm productivity through early disease diagnosis, optimal use of agricultural inputs, data-driven decision making, and increased sustainability. But adoption of AI technologies by smallholder farmers is highly variable. The research also shows that the adoption is heavily dependent on behavioural and socio-economic factors such as farmers’ attitudes, trust, digital skills, infrastructure, and cost. Furthermore, implementation is constrained by structural factors such as lack of connectivity, skills, extension services, ethical considerations and data management. Likewise, enablers such as human-centred design, improved advisory and extension services, policies, and inclusive and collaborative innovation systems can also boost adoption and effectiveness. This review provides a holistic view of AI-driven precision agriculture by synthesising evidence on technical performance, socio-economic and policy considerations. It offers a conceptual basis for future empirical studies, and highlights the importance of context-sensitive, inclusive and farmer-friendly AI technologies to drive equitable and sustainable digital agriculture.