机器学习耦合多源变量预测农田重金属分布与生态风险

打开文本图片集

关键词：机器学习；多源变量；风险评估；空间预测；土壤重金属

中图分类号：X53；X826 文献标志码：A 文章编号：1672-2043（2025）11-2783-13 doi：10.11654/jaes.2025-0458

Abstract：Todntifyesatialaratioracteristicsofayetalsndeirotetialologicalissintisudyd 1166farmlandsoilmpsiTisanCityangdongProvince，teasueconcentratiosofeametals（Cr，b，As，Hgd）d obtain17co-factors.Usingrecusivefeatureelimination（RFE），theOmostinfluentialfactorswereidentifidandcombinedwiththree machinelearningmodels（F，VM，AN）toselectthebestpredictionodel.Geoaccuulatioidexasthusedtoseslion risk and generate a distribution map.The RF model performs the best， with R2 values above 0.940 on the training set and 0.583-0.766 on the test set（except for Cr）.In contrast， the SVM model had R2 values ranging from 0.275-0.533 on the training set and from 0.226-0.461 on the test set. The ANN model had R2 values ranging from 0.156-0.587 on the training set and from O.183-0.489 on the test set. SHAP analysisdentifdyctrsiuengpedictiosreciiatioghtlghttesitydsacetploidetalnCdd Pb;precipitatiodistacetoexploiedmetalinsanddistaetoidustrlenterprssforAsadHg.Thsudyareaadntong pollution，but Cd and Hg showed moderate pollution over 5.6% and 35.5% of the area，respectively，indicating a need for focused pollution control.TheRFodelshowedexcelentpredictioperfomancewithstronggeneralizationandaplicationpotential.Soilaymetalin TaishanCitywereifuencdbyothnaturaandnthropogenicfactors，ithCdandHgeingtheaiplltants，rimarilyistritedn thesouthwestandnortherareas.Theseresultshighlighttheneedtoprioritizetheseregionsforpolutioncontrolandremediation.

Keywords：machine learning; multi-source variable; risk assessment; spatial prediction; soil heavy metals

重金属因具有不可被生物降解、在环境中毒性强且持久性高等特征，已成为全球重点关注的污染物。（剩余20236字）