AI-driven agricultural economics and farm decision support systems

Résumé fourni par la source

AI is bringing transformational change to agricultural economics by facilitating data-driven decision-making in farm production, resource management, financial planning, and marketing. The combination of the recent advances in machine learning (ML), deep learning (DL), computer vision, Internet of Things (IoT), remote sensing (RS), robotics, cloud computing, and big data analytics has enabled Farm Decision Support Systems (FDSS) for enhancing crop management, input-use efficiency, decreasing production cost, and increasing profit. AI-based systems also facilitate crop choice, irrigation and nutrient management, pests and diseases forecasting, yield prediction, price forecasting and market analysis, helping to reduce production risk under climate and market uncertainties. Novel technologies such as generative AI, Large Language Models, digital twins, blockchain, reinforcement learning and explainable AI further enhance decision accuracy, automation and supply chain transparency. AI is also advancing climate-smart agriculture through precision input management, diminished use of resources and GHG emissions, and enhanced climate variability resiliency. Nevertheless, adoption is still limited by lack of digital infrastructure, poor data quality, high cost of implementation, limited technical capacity, algorithmic transparency and data governance issues, particularly in developing countries. This review focuses on and recent advances in AI-enhanced agricultural economics and FDSS, highlighting key technologies, economic model applications, implementation challenges, ethical issues, and future research directions. To summarize, responsible AI deployment can enable economically feasible, climate-resilient, environmentally sustainable agriculture, promote food security, and advance evidence-based agricultural policy making.