Review of artificial intelligence in the agricultural cadastre: transforming agro-territorial management for global sustainability

At the global level, sustainable agro-territorial management depends on cadastral systems that ensure proper land use and protect land rights. Faced with persistent challenges, such as the delimitation and optimisation of agricultural plots, Artificial Intelligence (AI) is emerging as a disruptive tool. Its ability to analyse satellite images and geospatial data enables the automation of plot delimitation, identification of land-use patterns, prediction of crop yields, and monitoring of territorial changes, redefining the future of the agricultural cadastre. This study explores AI applications in agricultural cadastre through a systematic review and bibliometric mapping of publications indexed in Scopus and Web of Science (WoS) for territorial sustainability. A keyword search was conducted to find scientific documents related to the study topic. In addition, AI contributions to agricultural planning activities that integrate the agricultural cadastre are analysed. The primary scientific contributors to agricultural cadastral management are Germany, China, the United States, India, and the Czech Republic. Germany and India lead the way in the use of Machine Learning (ML). At the same time, the USA, Slovenia, and Rwanda showed the highest representation of Deep Learning (DL), applying technologies such as satellite imagery, Unmanned Aerial Vehicles (UAV), Synthetic Aperture Radar (SAR), and Light Detection and Ranging (LiDAR) in urban and rural environments. AI has revolutionised key processes, including land management (29.03%), agricultural production estimation (25.81%), cadastral boundary delimitation (19.35%), tenure and fragmentation analysis (12.90%), and land valuation and irrigation (6.45% each). The direct impact of AI on the Sustainable Development Goals (SDGs) includes optimising the use of natural resources (SDG 15), improving agricultural productivity (SDG 2 and SDG 12), strengthening food security (SDG 1), and promoting transparent territorial governance (SDG 16). Across the studies reviewed, rural applications achieved an average precision of approximately 82%, demonstrating the capacity of AI-based approaches to support agricultural cadastre optimisation, sustainable territorial planning, and data-driven decision-making in public administration and rural development contexts. These contributions are primarily reflected in three interconnected domains: cadastral management and updating, land-use and land-value analysis, and the development of policies that promote sustainable agricultural planning.