Soil Cadmium Prediction and Health Risk Assessment of an Oasis on the Eastern Edge of the Tarim Basin Based on Feature Optimization and Machine Learning

被引：0
|
作者：
Liu, Jing-Yu [1 ,2 ]
Li, Ruo-Yi [3 ]
Liang, Yong-Chun [1 ]
Liu, Lei [1 ]
Yin, Fang [4 ]
Tang, Su [2 ]
He, Lin-Sen [4 ]
Zhang, Yi [5 ]
机构：
[1] School of Earth Science and Resources, Chang’an University, Xi’an
[2] Center of Urumqi Comprehensive Survey Natural Resources, China Geological Survey, Urumqi
[3] China Aero Geophysical Survey and Remote Sensing Center for Natural Resources, Beijing
[4] School of Land Engineering, Chang’an University, Xi’an
[5] Xi’an Mineral Resources Survey Centre, China Geological Survey, Xi’an
来源：
Huanjing Kexue/Environmental Science | 2024年 / 45卷 / 08期
关键词：
cadmium（Cd）; content prediction; feature optimization; health risk assessment; machine learning;
D O I：
10.13227/j.hjkx.202308010
中图分类号：
学科分类号：
摘要：
Soil heavy metal pollution poses a serious threat to food security，human health，and soil ecosystems. Based on 644 soil samples collected from a typical oasis located at the eastern margin of the Tarim Basin，a series of models，namely，multiple linear regression（LR），neural network（BP），random forest（RF），support vector machine（SVM），and radial basis function（RBF），were built to predict the soil heavy metal content. The optimal prediction result was obtained and utilized to analyze the spatial distribution features of heavy metal contamination and relevant health risks. The outcomes demonstrated that：① The average Cd content in the study area was 0.14 mg·kg-1，which was 1.17 times the soil background value of Xinjiang，making it the primary factor of soil heavy metal contamination in the area. Additionally，the carcinogenicity risk coefficients of Cd for both adults and children were less than 10-4，indicating that there were no significant long-term health risks for humans in the area. ② The estimation accuracies of the five inversion models were compared，and the validation set of the RF model had an R2 value of 0.763 7，which was the highest among the five models. Additionally，the RMSE，MAE，and MBE of the RF model were the smallest among the five models. Therefore，the predicted values of the RF model were most consistent with the measured values of the soil Cd content. The predicted map of soil Cd distribution derived from the RF model coincided best with the interpolation map. ③ The RF model outperformed the other four models in predicting health risks associated with the soil Cd element for both adults and children，resulting in better prediction results. Comparatively，the predicted values of the LR model in the validation set varied greatly，leading to unreliable results. It was demonstrated that the RF was the best model for predicting soil Cd content and evaluating health risks in the study area，considering its superior generalization capability and anti-overfitting ability. © 2024 Science Press. All rights reserved.
引用
收藏
页码：4802 / 4811
页数：9
相关论文
共 44 条
  • [1] Yang X L，, Cheng J，, Franks A E，, Et al., Loss of microbial diversity weakens specific soil functions， but increases soil ecosystem stability［J］, Soil Biology and Biochemistry, (2023)
  • [2] Zhu Y G, Li G，, Zhang G L，, Et al., Soil security：from Earth’ s critical zone to ecosystem services［J］, Acta Geographica Sinica, 70, 12, pp. 1859-1869, (2015)
  • [3] Zhang Y X，, Song B，, Zhou Z Y., Pollution assessment and source apportionment of heavy metals in soil from lead-Zinc mining areas of south China ［J］, Journal of Environmental Chemical Engineering, 11, 2, (2023)
  • [4] Huang Y，, Wang L Y，, Wang W J，, Et al., Current status of agricultural soil pollution by heavy metals in China：a meta-analysis ［J］, Science of the Total Environment, 651, P2, pp. 3034-3042, (2019)
  • [5] Liang J H, Tian Y Q, Fei Y，, Et al., Source apportionment and potential ecological risk assessment of soil heavy metals in typical industrial and mining towns in North China［J］, Environmental Science, 44, 10, pp. 5657-5665, (2023)
  • [6] Conoscenti C，, Sheshukov A Y., Regional variability of terrain index and machine learning model applications for prediction of ephemeral gullies［J］, Geomorphology, (2023)
  • [7] Huang Y Y，, Molavi Nojumi M，, Ansari S, Et al., Evaluating the use of machine learning for moisture content prediction in base and subgrade layers［J］, Road Materials and Pavement Design, 24, 12, pp. 2910-2928, (2023)
  • [8] Sridevy S，, Raj M N，, Kumaresan P，, Et al., Mapping of soil properties using machine learning techniques［J］, International Journal of Environment and Climate Change, 13, 8, pp. 684-700, (2023)
  • [9] Zhang Y F, Pan Z Q, Chen D J., Estimation of cropland nitrogen runoff loss loads in the Yangtze River Basin based on the machine learning approaches［J］, Environmental Science, 44, 7, pp. 3913-3922, (2023)
  • [10] Zhang P，, Yin Z Y，, Jin Y F., State-of-the-art review of machine learning applications in constitutive modeling of soils［J］, Archives of Computational Methods in Engineering, 28, 5, pp. 3661-3686, (2021)
12345