文献类型：期刊文献

英文题名：A novel four-dimensional prediction model of soil heavy metal pollution: Geographical explanations beyond artificial intelligence "black box

作者：Wang, Qi[1] Li, Cangbai[2] Hao, Dongmei[3] Xu, Yafei[3] Shi, Xuewen[3] Liu, Tongxu[1] Sun, Weimin[1] Zheng, Zelong[4] Liu, Jianfeng[5] Li, Wanqi[3] Liu, Wengang[3] Zheng, Jiaxue[6] Li, Fangbai[1]

第一作者：Wang, Qi

通信作者：Li, FB[1]

机构：[1]Guangdong Acad Sci, Inst Ecoenvironm & Soil Sci, Natl Reg Joint Engn Res Ctr Soil Pollut Control &, Guangdong Key Lab Integrated Agroenvironm Pollut C, Guangzhou 510650, Peoples R China;[2]Guangdong Univ Technol, Sch Ecol Environm & Resources, Key Lab City Cluster Environm Safety & Green Dev, Minist Educ, Guangzhou 510006, Peoples R China;[3]Lanzhou Univ, Sch Management, Lanzhou 730099, Peoples R China;[4]South China Univ Technol, Guangzhou Peoples Hosp 1, Sch Med, Guangzhou 510180, Peoples R China;[5]Chinese Acad Forestry, Res Inst Forestry, Beijing 100091, Peoples R China;[6]Dongbei Univ Finance & Econ, Sch Data Sci & Artificial Intelligence, Dalian 116025, Peoples R China

年份：2023

卷号：458

外文期刊名：JOURNAL OF HAZARDOUS MATERIALS

收录：;EI(收录号：20232714330009);Scopus(收录号：2-s2.0-85163437601);WOS:【SCI-EXPANDED(收录号:WOS:001034972300001)】；

基金：The current work was financially supported by the Guangdong Outstanding Youth Foundation (2020B1515020020) , the Natural Sci- ence Foundation of China (42277479) , the Guangdong Academy of Sciences (GDAS) Project of Science and Technology Development (2020GDASYL-20200104020) .

语种：英文

外文关键词：Soil pollutant; Prediction; Artificial intelligence; Geographical explanation; Ensemble learning; TreeSHAP

摘要：The current artificial intelligence (AI)-based prediction approaches of soil pollutants are inadequate in estimating the geospatial source-sink processes and striking a balance between the interpretability and accuracy, resulting in poor spatial extrapolation and generalization. In this study, we developed and tested a geographically inter-pretable four-dimensional AI prediction model for soil heavy metal (Cd) contents (4DGISHM) in Shaoguan city of China from 2016 to 2030. The 4DGISHM approach characterized spatio-temporal changes in source-sink pro-cesses of soil Cd by estimating spatio-temporal patterns and the effects of drivers and their interactions of soil Cd at local to regional scales using TreeExplainer-based SHAP and parallel ensemble AI algorithms. The results demonstrate that the prediction model achieved MSE and R2 values of 0.012 and 0.938, respectively, at a spatial resolution of 1 km. The predicted areas exceeding the risk control values for soil Cd across Shaoguan from 2022 to 2030 increased by 22.92% at the baseline scenario. By 2030, enterprise and transportation emissions (SHAP values 0.23 and 0.12 mg/kg, respectively) were the major drivers. The influence of driver interactions on soil Cd was marginal. Our approach surpasses the limitations of the AI "black box" by integrating spatio-temporal source -sink explanation and accuracy. This advancement enables geographically precise prediction and control of soil pollutants.