Agricultural land use dynamics and their associated driving factors represent highly complex systems of flows that are subject to non-linearities, sensitivities, and uncertainties across spatial and temporal scales. This project is developing a novel explainable AI framework that learns the complex spatial and temporal relationships between social, economic and environmental driving factors and historic agricultural land use change. The framework is being designed to be transparent, data-driven and spatially-explicit by using probabilistic inference and explicit “if-then” rules. The explainable AI-rules will be characterised and refined through the framework using machine learning and parameter optimisation. This exploratory study will demonstrate proof-of-concept for selected regions in the UK and provide greater understanding of the state and dynamics of agricultural land use systems and how they can be influenced by policy and management decisions.