An Overview of Artificial Intelligence-Driven Intelligent Agronomy for Sustainable Productivity and Agri-Finance Transformation
Abstract
This review investigates how Artificial intelligence (AI) can improve agriculture's sustainability, production and finances. It uses AI-powered forecasting models to improve farm management, resource allocation and decision-making. Using time-series analysis, machine learning, deep learning, and hybrid models, agricultural data like weather, soil moisture, satellite imagery and market patterns is turned into information. Resource efficiency and inefficiency are improved via irrigation, pest control, production projections and market demand estimates. This review highlights how AI models help open-field, hydroponic and vertical farms. Depending on conditions and crop type, irrigation water use can be reduced by 25%, crop yields increased by 8-18%, and energy use reduced by 20%. In agricultural finance, AI forecasts financial risks, yield variability and loan approval. Although these benefits exist, fragmented data, model transferability between domains, and visible AI interpretations impede widespread adoption. To further intelligent agronomy, this review suggests boosting data quality, model flexibility and AI interpretability. With research and collaboration, AI can make agriculture more sustainable, efficient, financially inclusive and ecologically friendly. The review links AI-enabled agronomic advancements to Sustainable Development Goals, highlighting their significance in resilient, resource-efficient and climate-responsive agriculture.
