Spatial prediction and interactive driving source identification of regional soil arsenic elements based on integrated learning architecture

Key Points

• Spatial prediction of soil arsenic helps identify regions at risk due to contaminant sources.
• Key evidence shows significant correlations in arsenic levels across various soil types, indicating spatial variability.
• Analysis using integrated learning architecture enables precise identification of interactive driving sources impacting soil arsenic content.
• Findings support the need for targeted interventions in regions affected by arsenic contamination.