A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models

Heavy metal contamination in paddies poses a serious threat to ecological and human health. Current researches about heavy metal pollution mainly focus on source apportionment, while robust and accurate predictions on its spatial distribution and driving mechanisms is still lacking. Herein, we devel...

Full description

Saved in:
Bibliographic Details
Main Authors: Unurnyam Jugnee, Le Jiao, Sainbayar Dalantai, Lili Huo, Yi An, Bayartungalag Batsaikhan, Undrakhtsetseg Tsogtbaatar, Munguntuul Ulziibaatar, Boldbaatar Natsagdorj
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844025009995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078151452917760
author Unurnyam Jugnee
Le Jiao
Sainbayar Dalantai
Lili Huo
Yi An
Bayartungalag Batsaikhan
Undrakhtsetseg Tsogtbaatar
Munguntuul Ulziibaatar
Boldbaatar Natsagdorj
author_facet Unurnyam Jugnee
Le Jiao
Sainbayar Dalantai
Lili Huo
Yi An
Bayartungalag Batsaikhan
Undrakhtsetseg Tsogtbaatar
Munguntuul Ulziibaatar
Boldbaatar Natsagdorj
author_sort Unurnyam Jugnee
collection DOAJ
description Heavy metal contamination in paddies poses a serious threat to ecological and human health. Current researches about heavy metal pollution mainly focus on source apportionment, while robust and accurate predictions on its spatial distribution and driving mechanisms is still lacking. Herein, we developed a general methodological framework to predict and assess heavy metal pollution of paddies in Hunan province, China, by employing Random Forest (RF), Extra Trees Regressor (ETR), Extreme Gradient Boost Regression (XGBR), and Gradient Boosting Regression Tree (GBRT). Results demonstrated that RF performed superiorly in predicting As (R2 = 0.706), Cr (R2 = 0.746), Cu (R2 = 0.705), and Hg (R2 = 0.73), while the ETR showed good performance in predicting Cd (R2 = 0.521), Zn (R2 = 0.404), and Pb (R2 = 0.625). GBRT performed well in predicting Ni (R2 = 0.61). The Shapley additive explanations suggested significant differences in the driving factors and their contributions to prediction models for each heavy metal. Climate variables were potentially valuable predictors of heavy metal content. The visualized spatial distribution of Pollution Load Index showed that 79.8 % of the study area was moderately polluted and the remaining 20.2 % was in a severe polluted state. The soil pollution state worsened from the west to the east of the study area. These findings provide valuable information on effective soil pollution control and soil conservation efforts.
format Article
id doaj-art-b81353d549dc4ca58cc1944ffca6fd37
institution DOAJ
issn 2405-8440
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-b81353d549dc4ca58cc1944ffca6fd372025-08-20T02:45:38ZengElsevierHeliyon2405-84402025-02-01114e4261910.1016/j.heliyon.2025.e42619A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning modelsUnurnyam Jugnee0Le Jiao1Sainbayar Dalantai2Lili Huo3Yi An4Bayartungalag Batsaikhan5Undrakhtsetseg Tsogtbaatar6Munguntuul Ulziibaatar7Boldbaatar Natsagdorj8Division of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, Mongolia; School of Natural Sciences, National University of Mongolia, Ulaanbaatar, 210646, MongoliaAgro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Tianjin, 300191, China; China-Mongolia Joint Laboratory for Multi-source Monitoring and Spatiotemporal Succession of Agricultural Environment, Tianjin, 300191, China; Xiangtan Experimental Station of Agro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Xiangtan, 411100, ChinaDivision of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, MongoliaAgro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Tianjin, 300191, China; China-Mongolia Joint Laboratory for Multi-source Monitoring and Spatiotemporal Succession of Agricultural Environment, Tianjin, 300191, China; Xiangtan Experimental Station of Agro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Xiangtan, 411100, ChinaAgro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Tianjin, 300191, China; China-Mongolia Joint Laboratory for Multi-source Monitoring and Spatiotemporal Succession of Agricultural Environment, Tianjin, 300191, China; Xiangtan Experimental Station of Agro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Xiangtan, 411100, China; Corresponding author. Agro-Environmental Protection Institute, Ministry of Agriculture and Rural Affairs, Tianjin, 300191, China.Division of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, Mongolia; China-Mongolia Joint Laboratory for Multi-source Monitoring and Spatiotemporal Succession of Agricultural Environment, Tianjin, 300191, China; Corresponding author. Division of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, MongoliaDivision of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, MongoliaDivision of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, MongoliaDivision of Environmental and Natural Resources Management, Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, 15170, MongoliaHeavy metal contamination in paddies poses a serious threat to ecological and human health. Current researches about heavy metal pollution mainly focus on source apportionment, while robust and accurate predictions on its spatial distribution and driving mechanisms is still lacking. Herein, we developed a general methodological framework to predict and assess heavy metal pollution of paddies in Hunan province, China, by employing Random Forest (RF), Extra Trees Regressor (ETR), Extreme Gradient Boost Regression (XGBR), and Gradient Boosting Regression Tree (GBRT). Results demonstrated that RF performed superiorly in predicting As (R2 = 0.706), Cr (R2 = 0.746), Cu (R2 = 0.705), and Hg (R2 = 0.73), while the ETR showed good performance in predicting Cd (R2 = 0.521), Zn (R2 = 0.404), and Pb (R2 = 0.625). GBRT performed well in predicting Ni (R2 = 0.61). The Shapley additive explanations suggested significant differences in the driving factors and their contributions to prediction models for each heavy metal. Climate variables were potentially valuable predictors of heavy metal content. The visualized spatial distribution of Pollution Load Index showed that 79.8 % of the study area was moderately polluted and the remaining 20.2 % was in a severe polluted state. The soil pollution state worsened from the west to the east of the study area. These findings provide valuable information on effective soil pollution control and soil conservation efforts.http://www.sciencedirect.com/science/article/pii/S2405844025009995Heavy metalHunan provinceMachine learningPaddy soilPollution prediction
spellingShingle Unurnyam Jugnee
Le Jiao
Sainbayar Dalantai
Lili Huo
Yi An
Bayartungalag Batsaikhan
Undrakhtsetseg Tsogtbaatar
Munguntuul Ulziibaatar
Boldbaatar Natsagdorj
A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
Heliyon
Heavy metal
Hunan province
Machine learning
Paddy soil
Pollution prediction
title A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
title_full A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
title_fullStr A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
title_full_unstemmed A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
title_short A general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
title_sort general methodological framework for predicting and assessing heavy metal pollution in paddy soils using machine learning models
topic Heavy metal
Hunan province
Machine learning
Paddy soil
Pollution prediction
url http://www.sciencedirect.com/science/article/pii/S2405844025009995
work_keys_str_mv AT unurnyamjugnee ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT lejiao ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT sainbayardalantai ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT lilihuo ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT yian ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT bayartungalagbatsaikhan ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT undrakhtsetsegtsogtbaatar ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT munguntuululziibaatar ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT boldbaatarnatsagdorj ageneralmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT unurnyamjugnee generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT lejiao generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT sainbayardalantai generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT lilihuo generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT yian generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT bayartungalagbatsaikhan generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT undrakhtsetsegtsogtbaatar generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT munguntuululziibaatar generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels
AT boldbaatarnatsagdorj generalmethodologicalframeworkforpredictingandassessingheavymetalpollutioninpaddysoilsusingmachinelearningmodels