A geographically weighted neural network model for digital soil mapping of heavy metal copper in coastal cities
Year: 2024
Type: article
Abstract: Assessing the spatial distribution of soil heavy metals is vital for mitigating risks of human health and ensuring the sustainable use of soil resources. This study proposed geographically weighted neural network model (GWNN), designed based on the concept of geographically weighted regression (GWR) to address the spatial autocorrelation of soil toxic element copper (Cu), and incorporated convolutional neural network (CNN) to capture the nonlinear relationships between Cu and environmental covariates. The GWNN model was compared with GWR, extreme gradient boosting (XGBoost) and artificial neural network (ANN). XGBoost was employed to select important environmental covariates and spatial autocorrelation of Cu concentrations was assessed using Moran’s I. The model’s performance was assessed using 10-fold cross-validation, and prediction uncertainty was quantified with 50 bootstrap models. The results indicated the temperature covariates were the most important indicator in predicting soil Cu concentrations. GWNN model outperformed with R² of 0.60 and low uncertainty, compared to GWR, XGBoost and ANN. The spatial distribution of Cu showed a trend of high in the north and low in the south, consistent with spatial clusters identified by local Moran’s I. Overall, GWNN model demonstrated improved mapping accuracy and prediction performance, offering a potential approach for digital soil mapping applications.
Source: Journal of Hazardous Materials
Institutions: Shenzhen University, Hong Kong Polytechnic University
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
SDG: Life on land
Open Access status: hybrid
Estimated APC paid: $4,340
Awards: G1796439359, G1856854668
OpenAlex ID: W4403707668