An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data

Sparse borehole sampling at contaminated sites results in sparse and unevenly distributed data on soil pollutants. Traditional interpolation methods may obscure local variations in soil contamination when applied to such sparse data, thus reducing the interpolation accuracy. We propose an adaptive g...

Full description

Saved in:
Bibliographic Details
Main Authors: Huan Tao, Ziyang Li, Shengdong Nie, Hengkai Li, Dan Zhao
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/7/1348
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246477944094720
author Huan Tao
Ziyang Li
Shengdong Nie
Hengkai Li
Dan Zhao
author_facet Huan Tao
Ziyang Li
Shengdong Nie
Hengkai Li
Dan Zhao
author_sort Huan Tao
collection DOAJ
description Sparse borehole sampling at contaminated sites results in sparse and unevenly distributed data on soil pollutants. Traditional interpolation methods may obscure local variations in soil contamination when applied to such sparse data, thus reducing the interpolation accuracy. We propose an adaptive graph convolutional network with spatial autocorrelation (ASI-GCN) model to overcome this challenge. The ASI-GCN model effectively constrains pollutant concentration transfer while capturing subtle spatial variations, improving soil pollution characterization accuracy. We tested our model at a coking plant using 215 soil samples from 15 boreholes, evaluating its robustness with three pollutants of varying volatility: arsenic (As, non-volatile), benzo(a)pyrene (BaP, semi-volatile), and benzene (Ben, volatile). Leave-one-out cross-validation demonstrates that the ASI-GCN_RC_G model (ASI-GCN with residual connections) achieves the highest prediction accuracy. Specifically, the <i>R</i> for As, BaP, and Ben are 0.728, 0.825, and 0.781, respectively, outperforming traditional models by 58.8% (vs. IDW), 45.82% (vs. OK), and 53.78% (vs. IDW). Meanwhile, their RMSE drop by 36.56% (vs. Bayesian_K), 38.02% (vs. Bayesian_K), and 35.96% (vs. IDW), further confirming the model’s superior precision. Beyond accuracy, Monte Carlo uncertainty analysis reveals that most predicted areas exhibit low uncertainty, with only a few high-pollution hotspots exhibiting relatively high uncertainty. Further analysis revealed the significant influence of pollutant volatility on vertical migration patterns. Non-volatile As was primarily distributed in the fill and silty sand layers, and semi-volatile BaP concentrated in the silty sand layer. At the same time, volatile Ben was predominantly found in the clay and fine sand layers. By integrating spatial autocorrelation with deep graph representation, ASI-GCN redefines sparse data 3D mapping, offering a transformative tool for precise environmental governance and human health assessment.
format Article
id doaj-art-2fb5f433e40441e1ba01698005e82aea
institution Kabale University
issn 2073-445X
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-2fb5f433e40441e1ba01698005e82aea2025-08-20T03:58:30ZengMDPI AGLand2073-445X2025-06-01147134810.3390/land14071348An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole DataHuan Tao0Ziyang Li1Shengdong Nie2Hengkai Li3Dan Zhao4Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences (CAS), Beijing 100101, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaCivil and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaCivil and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaKey Laboratory of Environmental Damage Identification and Restoration, Ministry of Ecology and Environment, Beijing 100041, ChinaSparse borehole sampling at contaminated sites results in sparse and unevenly distributed data on soil pollutants. Traditional interpolation methods may obscure local variations in soil contamination when applied to such sparse data, thus reducing the interpolation accuracy. We propose an adaptive graph convolutional network with spatial autocorrelation (ASI-GCN) model to overcome this challenge. The ASI-GCN model effectively constrains pollutant concentration transfer while capturing subtle spatial variations, improving soil pollution characterization accuracy. We tested our model at a coking plant using 215 soil samples from 15 boreholes, evaluating its robustness with three pollutants of varying volatility: arsenic (As, non-volatile), benzo(a)pyrene (BaP, semi-volatile), and benzene (Ben, volatile). Leave-one-out cross-validation demonstrates that the ASI-GCN_RC_G model (ASI-GCN with residual connections) achieves the highest prediction accuracy. Specifically, the <i>R</i> for As, BaP, and Ben are 0.728, 0.825, and 0.781, respectively, outperforming traditional models by 58.8% (vs. IDW), 45.82% (vs. OK), and 53.78% (vs. IDW). Meanwhile, their RMSE drop by 36.56% (vs. Bayesian_K), 38.02% (vs. Bayesian_K), and 35.96% (vs. IDW), further confirming the model’s superior precision. Beyond accuracy, Monte Carlo uncertainty analysis reveals that most predicted areas exhibit low uncertainty, with only a few high-pollution hotspots exhibiting relatively high uncertainty. Further analysis revealed the significant influence of pollutant volatility on vertical migration patterns. Non-volatile As was primarily distributed in the fill and silty sand layers, and semi-volatile BaP concentrated in the silty sand layer. At the same time, volatile Ben was predominantly found in the clay and fine sand layers. By integrating spatial autocorrelation with deep graph representation, ASI-GCN redefines sparse data 3D mapping, offering a transformative tool for precise environmental governance and human health assessment.https://www.mdpi.com/2073-445X/14/7/1348soil pollutiongraph neural networksparse samples3D spatial interpolationcontaminated site
spellingShingle Huan Tao
Ziyang Li
Shengdong Nie
Hengkai Li
Dan Zhao
An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
Land
soil pollution
graph neural network
sparse samples
3D spatial interpolation
contaminated site
title An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
title_full An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
title_fullStr An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
title_full_unstemmed An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
title_short An Adaptive Graph Convolutional Network with Spatial Autocorrelation for Enhancing 3D Soil Pollutant Mapping Precision from Sparse Borehole Data
title_sort adaptive graph convolutional network with spatial autocorrelation for enhancing 3d soil pollutant mapping precision from sparse borehole data
topic soil pollution
graph neural network
sparse samples
3D spatial interpolation
contaminated site
url https://www.mdpi.com/2073-445X/14/7/1348
work_keys_str_mv AT huantao anadaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT ziyangli anadaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT shengdongnie anadaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT hengkaili anadaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT danzhao anadaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT huantao adaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT ziyangli adaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT shengdongnie adaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT hengkaili adaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata
AT danzhao adaptivegraphconvolutionalnetworkwithspatialautocorrelationforenhancing3dsoilpollutantmappingprecisionfromsparseboreholedata