Simultaneously mapping the 3D distributions of multiple heavy metals in an industrial site using deep learning and multisource auxiliary data

• Published in: Journal of hazardous materials Vol. 480; p. 136000
• Main Authors: Peng, Yuxuan, Zhao, Yongcun, Chen, Jian, Xie, Enze, Yan, Guojing, Zou, Tingrun, Xu, Xianghua
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 30.09.2024
• Subjects: Convolution Neural Networks; Multi-task learning; Soil pollution; Three-dimensional prediction; Convolution Neural Networks; Soil pollution; Three-dimensional prediction; Multi-task learning
• ISSN: 0304-3894; 1873-3336; 1873-3336
• DOI: 10.1016/j.jhazmat.2024.136000

Three-dimensional (3D) distributions of multiple soil pollutants in industrial site are crucial for risk assessment and remediation. Yet, their 3D prediction accuracies are often low because of the strong variability of pollutants and availability of 3D covariate data. This study proposed a patch-based multi-task convolution neural network (MT-CNN) model for simultaneously predicting the 3D distributions of Zn, Pb, Ni, and Cu at an industrial site. By integrating neighborhood patches from multisource covariates, the MT-CNN model captured both horizontal and vertical pollution information, and outperformed the widely-used methods such as random forest (RF), ordinary Kriging (OK), and inverse distance weighting (IDW) for all the 4 heavy metals, with R2 values of 0.58, 0.56, 0.29 and 0.23 for Zn, Pb, Ni and Cu, respectively. Besides, the MT-CNN model achieved more stable predictions with reasonable accuracy, in comparison with the single-task CNN model. These results highlighted the potential of the proposed MT-CNN in simultaneously mapping the 3D distributions of multiple pollutants, while balancing the model training, maintaining and accuracy for low-cost rapid assessment of soil pollution at industrial sites. [Display omitted] •An MT-CNN model for simultaneous 3D prediction of soil pollutants was developed.•The MT-CNN model outperformed traditional ML models and interpolation methods.•The inclusion of multisource covariate data benefited the 3D mapping.•MT-CNN is efficient for rapidly mapping multiple pollutants in industrial sites.