A COM-Based Decision Tree Model Integrated with GIS for Assessment of Soil Heavy Metals Pollution

A COM-based decision tree model was integrated with Geographical Information Systems (GIS) to assess the soil Cu pollution in Fuyang, Zhejiang, China. The integration of the decision tree model with ArcGIS Engine 9.2 using a COM implementation in Microsoft^® Visual Basic 6.0 provided an approach for assessing the spatial distribution of soil Cu content with high predictive accuracy. The decision tree model (CART) accuracy of assigning samples to the right Cu classes is 85.37% and 82.00%, the Kappa coefficient is 0.8182 and 0.7698 respectively for training data and test data. This is a great improvement comparing with ordinary Kriging method for the spatial autocorrelation of the study area severely destroyed by human activities. The integrated approach also allows for relatively easy, fast, and cost-effective estimation of spatially distributed soil heavy metals pollution. The methods and results described in this study are also valuable for understanding the relationship between heavy metals pollution risk and environmental factors.