Advances in artificial intelligence and geomatics technology for the transformation of global agri-food systems: A review
TL;DR
The results indicate a growing adoption of Machine Learning (ML) algorithms, remote sensing technologies, and geospatial platforms such as Google Earth Engine (GEE), highlighting AI and GT as central components of Smart Agriculture.
Abstract
The world’s rapidly growing population is driving up food demand and placing significant pressure on natural resources, posing major challenges to agricultural sustainability. Ensuring food security requires integrating innovative technologies that enhance productivity while reducing environmental impacts. In this context, the convergence of Artificial Intelligence (AI) and Geomatics Technology (GT) has emerged as a key approach for the intelligent management of agricultural systems, enabling improved monitoring, analysis, and modelling of both productive and environmental processes. This study aims to explore recent trends in the combined application of AI and GT in sustainable agriculture by systematically reviewing scientific publications retrieved from Scopus and Web of Science (WoS) covering 2004 to 2025. The review focuses on identifying sustainable agricultural practices and environmental strategies, and on their contributions to sectoral sustainability. The methodology integrates a bibliometric analysis of 326 publications with a PRISMA-based systematic review of 83 eligible studies, including an in-depth synthesis of the 40 studies classified under the Environmental Monitoring and Climate Change category. Bibliometric mapping was performed using VOSviewer, while quantitative evidence synthesis supported the regional comparative analyses. The results indicate a growing adoption of Machine Learning (ML) algorithms, remote sensing technologies, and geospatial platforms such as Google Earth Engine (GEE), highlighting AI and GT as central components of Smart Agriculture. Sustainable practices are primarily classified into Smart Agriculture (25%), Environmental Monitoring and Climate Change (48%), and Decision-Making processes (27%). Asia and North America lead in technological adoption, whereas Latin America and Oceania face limitations related to infrastructure and data accessibility. The integration of AI and GT enhances climate resilience, supports ecosystem conservation, and contributes to achieving the Sustainable Development Goals (SDGs). These findings provide a robust scientific and technological foundation for advancing the global transition towards more sustainable and adaptive agri-food systems.
