Integrating Geoai and Remote Sensing for Precision Environmental Resource Management in Cross River State, Nigeria.

Environmental Resource Management (ERM) involves the sustainable use and protection of natural resources like land, water, and forests to ensure long-term ecological balance and human welfare. It increasingly demands data-driven precision for these sustainable outcomes. This study explores the integration of Geospatial Artificial Intelligence (GeoAI) and remote sensing in optimising land, water, and forest resource management in Cross River State, Nigeria. The research aims to demonstrate how integrating GeoAI with satellite data can improve environmental resource management by detecting land-use changes, mapping degradation patterns, and supporting evidence-based policy. Using satellite imagery (Sentinel-2 (10 m resolution) and Landsat 8 OLI imagery (2015–2024), which were obtained from the USGS Earth Explorer), machine learning, and GIS-based analytics, the research models spatial patterns of deforestation, soil degradation, and water quality in the Cross River Basin. Deep learning algorithms were applied to detect land-use transitions and predict ecosystem vulnerability under various climate scenarios. Results reveal that between 2015 and 2024, forest cover declined by 14.8%, while agricultural and urban areas expanded by 11.2% and 3.6%, respectively. The RF model identified degradation hotspots mainly in Ikom, Boki, and Obubra LGAs, correlating strongly with agricultural encroachment and logging routes. These demonstrate that GeoAI-enabled models achieved over 90% accuracy in classifying vegetation cover and identifying at-risk zones for intervention. The framework also supports participatory decision-making through intelligent mapping dashboards accessible to policymakers. This paper concludes that GeoAI provides a robust, scalable solution for adaptive environmental management, offering early warning systems and dynamic conservation planning tools. It is recommended that governments should invest in national-scale GeoAI infrastructure and training and promote open access to high-resolution environmental data. JOURNAL OF ENVIRONMENTAL AND TOURISM EDUCATION (JETE), Vol. 9 No. 1 (2026): Volume 9, number 1, June 2026