Climate change is increasingly disrupting agricultural systems through erratic rainfall, heatwaves, and soil degradation, leading to significant yield losses, particularly in vulnerable regions. GeoAI, integrating geospatial technologies with artificial intelligence, has emerged as a promising approach to support Climate-Smart Agriculture and improve decision-making. This study aims to evaluate the role of GeoAI in enhancing crop productivity, resource-use efficiency and climate resilience while addressing socio-economic barriers to its adoption. A comprehensive synthesis of recent literature and case studies was conducted, focusing on GeoAI applications that integrate remote sensing (Sentinel, Landsat), UAV data, IoT sensors, and machine learning/deep learning models (e.g., CNN, LSTM, Random Forest, SVM). Key performance metrics such as yield prediction accuracy, input optimization, and environmental benefits were analyzed. GeoAI applications improve agricultural outcomes by enabling site-specific management, early stress detection, and adaptive planning. These technologies achieve yield gains of 12-28%, reduce inputs (fertilizer, water, chemicals) by 15-40%, and enhance resilience through predictive analytics and digital twins. However, adoption is constrained by high costs, data ownership concerns, and limited technical literacy among smallholders. GeoAI represents a transformative pathway toward sustainable and resilient agriculture. Scaling its adoption requires supportive policies, inclusive digital infrastructure, and capacity-building initiatives to bridge the digital divide and ensure equitable benefits.
Hayat et al. (Wed,) studied this question.