One-third of the Earth's land surface has undergone degradation, with the United Nations estimating that over 2.6 billion people are affected by its consequences, costing countries up to $10.6 trillion (7.8 trillion GBP) annually due to losses in "ecosystem services." Unhealthy soil is a primary cause of land degradation, leading to severe consequences such as biodiversity loss, dust storms, and reduced crop yields, which in turn impact Earth's climate and water cycle regulation, socio-economic activities, food security, and population migration.

However, emerging intelligent technologies such as artificial intelligence, satellite remote sensing, and big data analytics are bringing new opportunities for soil protection. These tools can monitor soil health in real time, enabling stakeholders to make more informed soil protection decisions.

As a professor of Earth hydrology informatics, the research team used artificial intelligence to create the first global soil salinization map under different climate scenarios. Soil salinization, a significant cause of soil degradation, can occur naturally or due to human activities. With increasing climate uncertainty, the model helps identify areas vulnerable to salinization. AI analysis predicts that by 2100, arid regions in South America, southern and western Australia, Mexico, the southwestern United States, and South Africa will become major hotspots for soil salinization.

In another study, the team utilized satellite data, AI, and big data tools to investigate the interaction between soil salinity and soil organic carbon. Soil organic carbon is a critical component of healthy soil, and the analysis showed a generally negative correlation between salinity levels and soil organic carbon content—higher salinity leads to lower soil organic carbon. These two studies highlight the transformative potential of AI and big data analytics in understanding soil degradation, aiding in better land management through more effective mitigation policies and sustainable land use planning.

Large-scale land reclamation can transform degraded soils. In China's Loess Plateau, centuries of deforestation and unsustainable farming have caused severe ecological challenges, with the highly erodible loess leading to more frequent floods, droughts, and dust storms. In the 1990s, the Chinese government invested in reforestation and sustainable agriculture, launching the Loess Plateau Watershed Rehabilitation Project with a total investment of $150 million, partly funded by the World Bank and approved in 1994, aimed at promoting agricultural development and income growth across 15,600 square kilometers of land in the Yellow River tributaries.

In Ethiopia's Tigray region, the EthioTrees project, launched in 2016, addresses land degradation through community-based reforestation, fencing to restrict grazing, and reinvestment of funds raised through climate financing mechanisms. Despite challenges such as drought and limited financial resources, these large-scale restoration projects have transformed the landscape and lives of local residents.

However, projects in the Loess Plateau and Tigray are complex and costly, requiring extensive coordination across regions and sectors to ensure comprehensive effectiveness. Artificial intelligence can support these successful but resource-intensive restoration efforts and scale them up. Additionally, participation in the EU Commission-funded "AI4SoilHealth" project promotes the application of AI in monitoring and quantifying soil health in Europe, demonstrating how data-driven initiatives can provide timely, actionable information to governments, farmers, and other stakeholders, supporting more sustainable land management policies. By combining satellite imagery with precise soil characteristic data from different regions, AI can develop robust, scalable models that transcend geographical boundaries, helping to protect people, businesses, and ecosystems from future extreme events.