干旱区生态环境知识资源中心(Arid): Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: Comparison of random forest, logistic regression and artificial neural network

Arid

DOI	10.1016/j.apgeochem.2021.105054
	Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: Comparison of random forest, logistic regression and artificial neural network
	Nafouanti, Mouigni Baraka; Li, Junxia; Mustapha, Nasiru Abba; Uwamungu, Placide; AL-Alimi, Dalal
通讯作者	Li, JX (corresponding author), China Univ Geosci, State Key Lab Biogeol & Environm Geol, Wuhan 430074, Peoples R China.
来源期刊	APPLIED GEOCHEMISTRY
ISSN	0883-2927
EISSN	1872-9134
出版年	2021
卷号	132
英文摘要	Groundwater fluoride is posing a health risk to humans, and analyzing groundwater quality is time-wasting and expensive. Statistical methods provide a valuable approach to study the spatial distribution of groundwater fluoride. Random Forest (RF), Artificial Neural Network (ANN), and Logistic Regression (LR) were used in this study for groundwater fluoride prediction in Datong Basin. The groundwater chemistry of 482 groundwater samples was collected and used to figure out the performance of three statistical technologies and extract the main factors controlling the enrichment of fluoride in groundwater. The data was separated into two parts for the statistical analysis, 80% for training and 20% for testing. The Chi-squared was applied to select the most relevant variables, and TDS, Cl- , NO3-, Na+, HCO3- , SO42-, K+, Zn, Ca2+, and Mg2+ were selected as best inputs for the fluoride prediction. Models were evaluated using the confusion matrix and The receiver operating characteristic area under the curve ROC (AUC). The results suggest that within ten input variables, the accuracies of RF, ANN, and LR were 0.89, 0.85, and 0.76, respectively. The mean decrease in impurity (MDI) and permutation feature demonstrates that eight of ten parameters, including TDS, Cl- , NO3-, Na+, HCO3-, SO42-, Ca2+ and Mg2+ are the variables influencing the groundwater fluoride in the study area. RF exhibited the best model with high conformity and confidence in predicting groundwater fluoride contamination in the study area.
英文关键词	Groundwater Fluoride Random forest Artificial neural network Logistic regression
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000689281700002
WOS关键词	NITRATE POLLUTION ; ETHIOPIAN RIFT ; THAR DESERT ; GEOCHEMISTRY ; MACHINE ; WATER ; INTELLIGENCE ; SELECTION ; DISTRICT ; MODELS
WOS类目	Geochemistry & Geophysics
WOS研究方向	Geochemistry & Geophysics
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/362479
作者单位	[Nafouanti, Mouigni Baraka; Li, Junxia; Mustapha, Nasiru Abba] China Univ Geosci, State Key Lab Biogeol & Environm Geol, Wuhan 430074, Peoples R China; [Li, Junxia] China Univ Geosci, China Lab Basin Hydrol & Wetland Ecorestorat, Wuhan 430074, Peoples R China; [Mustapha, Nasiru Abba] Fed Univ Dutse, Dept Environm Sci, Dutse, Jigawa State, Nigeria; [Uwamungu, Placide] State Key Lab Geol Proc & Mineral Resources China, Wuhan 430074, Peoples R China; [AL-Alimi, Dalal] China Univ Geosci, Sch Comp Sci, Wuhan 430074, Peoples R China
推荐引用方式 GB/T 7714	Nafouanti, Mouigni Baraka,Li, Junxia,Mustapha, Nasiru Abba,et al. Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: Comparison of random forest, logistic regression and artificial neural network[J],2021,132.
APA	Nafouanti, Mouigni Baraka,Li, Junxia,Mustapha, Nasiru Abba,Uwamungu, Placide,&AL-Alimi, Dalal.(2021).Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: Comparison of random forest, logistic regression and artificial neural network.APPLIED GEOCHEMISTRY,132.
MLA	Nafouanti, Mouigni Baraka,et al."Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: Comparison of random forest, logistic regression and artificial neural network".APPLIED GEOCHEMISTRY 132(2021).