Application of machine learning in soil heavy metals pollution assessment in the southeastern Tibetan plateau

The Tibetan Plateau, a globally significant ecological region, is experiencing escalating pollution from heavy metals (HMs). This study applies a machine learning approach based on the self-organizing map hyper-clustering, alongside advanced methodologies such as Positive Matrix Factorization (PMF), Incremental Spatial Autocorrelation, and Bivariate Local Indicators of Spatial Association (BiLISA), to analyze the ecological risk of soil HMs in representative watersheds of the southeastern Tibetan Plateau, focusing on spatial pattern clustering, pollutant source identification, and interaction risk assessment. The results indicated higher HMs concentrations in the middle and downstream areas. A comprehensive ecological risk assessment integrating the Improved Potential Ecological Risk Index, Enrichment Factor, Contamination Factor, and Geo-accumulation Index identified Cd, Pb, and As as the primary pollutants of concern. By combining PMF with Mantel analysis, pollution was attributed to geological background, agricultural activities, traffic emissions, and atmospheric deposition. The BiLISA method revealed significant spatial interactions among HMs, with the composite pollution of As and Cd occupying the largest proportion in High (As)-High (Cd) aggregation zones, underscoring the need for integrated management strategies. This study offers novel insights into the spatial pollution patterns and source apportionment of soil HMs, providing an advanced analytical framework for their precise control and ecological restoration.