Predicting geogenic groundwater fluoride contamination throughout China

Hongxing Liu , Hailong Cao , Xianjun Xie , Yanxin Wang


Received June 07, 2021,Revised , Accepted July 06, 2021, Available online August 02, 2021

Volume 34,2022,Pages 140-148

Endemic fluorosis exists in almost all provinces of China. The long-term ingestion of groundwater containing high concentrations of fluoride is one of the main causes of fluorosis. We used artificial neural network to model the relationship between groundwater fluoride concentrations from throughout China and environmental variables such as climatic, geological. and soil parameters as proxy predictors. The results show that the accuracy and area under the receiver operating characteristic curve of the model in the test dataset are 80.5% and 0.86%, respectively, and climatic variables are the most effective predictors. Based on the artificial neural network model, a nationwide prediction risk map of fluoride concentrations exceeding 1.5 mg/L with a 0.5 × 0.5 arc minutes resolution was generated. The high risk areas are mainly located in western provinces of Xinjiang, Tibet, Qinghai, and Sichuan, and the northern provinces of Inner Mongolia, Hebei and Shandong. The total number of people estimated to be potentially at risk of fluorosis due to the use of untreated high fluoride groundwater as drinking water is about 89 million, or 6% of the population. The high fluoride groundwater risk map helps the authorities to prioritize areas requiring mitigation measures and thus facilitates the implementation of water improvement and defluoridation projects.

Copyright © Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences. Published by Elsevier B.V. and Science Press. All rights reserved.京ICP备05002858号-3