Knowledge Management System Of Guangzhou Institute of Geochemistry,CAS
Sun, Yishan1,2,3; Chen, Shuisen1,4; Jiang, Hao1; Qin, Boxiong1,4; Li, Dan1,4; Jia, Kai1,4; Wang, Chongyang1 | |
Towards interpretable machine learning for observational quantification of soil heavy metal concentrations under environmental constraints | |
Source Publication | SCIENCE OF THE TOTAL ENVIRONMENT |
ISSN | 0048-9697 |
2024-05-20 | |
Volume | 926Pages:12 |
DOI | 10.1016/j.scitotenv.2024.171931 |
Language | 英语 |
WOS Research Area | Environmental Sciences & Ecology |
Abstract | Monitoring heavy metal concentrations in soils is central to assessing agricultural production safety. Satellite observations permit inferring concentrations from spectrum, thereby contributing to the prevention and control of soil heavy metal pollution. However, heavy metals exhibit weak spectral responses, particularly at low and medium concentrations, and are predominantly influenced by other soil components. Machine learning (ML)driven modelling can produce predictions but lacks interpretability. Here, we present an interpretable ML framework for concentration quantification modelling and investigated the contributions of spectral and environmental factors-pH and organic carbon-to the estimation of metals with multiple concentration gradients, as analysed through SHAP (SHapley Additive exPlanations) data derived from four learning-based scenarios. The results indicated that scenarios SHC (spectral, pH, and organic carbon) and SH (spectral and pH) were the most optimal for chromium (Cr) [RPD = 1.42, Adj R2 = 0.62], and cadmium (Cd) [RPD = 1.80, Adj R2 = 0.80]. Under environmental constraints, the spectral predictability for Cr and Cd was improved by 67 % and 87 %, respectively. We concluded that interpretable modelling, utilising both spectral and soil environmental factors, holds significant potential for estimating heavy metals across concentration gradients. It is recommended that samples with higher organic carbon content and lower pH be selected to enhance Cr and Cd predictions. An advanced grasp of interpretable predictions facilitates earlier warning of heavy metal contamination and guides the formulation of robust sampling strategies. |
Keyword | Pollutants Remote sensing Hyperspectral Satellite Interpretability Prediction |
WOS ID | WOS:001286036700001 |
Indexed By | SCI |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.gig.ac.cn/handle/344008/78664 |
Collection | 中国科学院广州地球化学研究所 |
Corresponding Author | Chen, Shuisen |
Affiliation | 1.Guangdong Acad Sci, Guangzhou Inst Geog, Guangdong Engn Technol Res Ctr Remote Sensing Big, Guangdong Prov Key Lab Remote Sensing & Geog Infor, Guangzhou 510070, Peoples R China 2.Chinese Acad Sci, Guangzhou Inst Geochem, Guangzhou 510640, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Shaoguan ShenBay Low Carbon Digital Technol Co Ltd, Guangdong Inst Carbon Neutral Shaoguan, Joint Lab Low Carbon Digital Monitoring, Shaoguan 512026, Peoples R China |
Recommended Citation GB/T 7714 | Sun, Yishan,Chen, Shuisen,Jiang, Hao,et al. Towards interpretable machine learning for observational quantification of soil heavy metal concentrations under environmental constraints[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2024,926:12. |
APA | Sun, Yishan.,Chen, Shuisen.,Jiang, Hao.,Qin, Boxiong.,Li, Dan.,...&Wang, Chongyang.(2024).Towards interpretable machine learning for observational quantification of soil heavy metal concentrations under environmental constraints.SCIENCE OF THE TOTAL ENVIRONMENT,926,12. |
MLA | Sun, Yishan,et al."Towards interpretable machine learning for observational quantification of soil heavy metal concentrations under environmental constraints".SCIENCE OF THE TOTAL ENVIRONMENT 926(2024):12. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment