A healthy soil supports life on Earth through maintaining ecosystems that provide food, feed and fibre whilst supporting Earth system functions such as waste recycling, climate, flood, and water regulation. The intensification of anthropogenic activities and climate challenges pose serious threats to soil health (Hassani et al., 2021), exacerbating the processes of soil degradation that are putting at risk soil management, biodiversity, and food security. This project thus aims at enhancing our understanding of the state and changes of soils by combining AI-driven methods with a comprehensive series of climate, land, and remote sensing data. We employ machine learning methods to analyze the relationships between soil health indicators and a wide range of climatic parameters, and chemical, physical, and biological soil attributes in Europe. Capitalizing on the LUCAS topsoil database (2009-2018) and digital soil mapping techniques, we aim to develop AI-driven predictive models to quantify soil degradation under a wide range of boundary conditions. The proposed framework will enable us to understand, document and respond to soil changes in ecosystems under different land management and climate scenarios. This contributes to devising necessary action plans for sustainable soil management. 
This research is part of the project AI4SoilHealth (Accelerating collection and use of soil health information using AI technology to support the Soil Deal for Europe and EU Soil Observatory) funded by Horizon Europe (Grant No. 101086179).
Hassani, A., Azapagic, A., Shokri, N. (2021). Global Predictions of Primary Soil Salinization Under Changing Climate in the 21st Century, Nat. Commun., 12, 6663. https://doi.org/10.1038/s41467-021-26907-3