干旱区生态环境知识资源中心(Arid): A Modeling Comparison of Groundwater Potential Mapping in a Mountain Bedrock Aquifer: QUEST, GARP, and RF Models

Arid

DOI	10.3390/w12030679
	A Modeling Comparison of Groundwater Potential Mapping in a Mountain Bedrock Aquifer: QUEST, GARP, and RF Models
	Moghaddam, Davoud Davoudi 1; Rahmati, Omid 2; Haghizadeh, Ali 1; Kalantari, Zahra 3,4
通讯作者	Kalantari, Zahra
来源期刊	WATER
EISSN	2073-4441
出版年	2020
卷号	12 期号:3
英文摘要	In some arid regions, groundwater is the only source of water for human needs, so understanding groundwater potential is essential to ensure its sustainable use. In this study, three machine learning models (Genetic Algorithm for Rule-Set Production (GARP), Quick Unbiased Efficient Statistical Tree (QUEST), and Random Forest (RF)) were applied and verified for spatial prediction of groundwater in a mountain bedrock aquifer in Piranshahr Watershed, Iran. A spring location dataset consisting of 141 springs was prepared by field surveys, and from this three different sample datasets (S1-S3) were randomly generated (70% for training and 30% for validation). A total of 10 groundwater conditioning factors were prepared for modeling, namely slope percent, relative slope position (RSP), plan curvature, altitude, drainage density, slope aspect, topographic wetness index (TWI), terrain ruggedness index (TRI), land use, and lithology. The area under the receiver operating characteristic curve (AUC) and true skill statistic (TSS) were used to evaluate the accuracy of models. The results indicated that all models had excellent goodness-of-fit and predictive performance, but that RF (AUC(mean) = 0.995, TSSmean = 0.89) and GARP (AUC(mean) = 0.957, TSSmean = 0.82) outperformed QUEST (AUC(mean) = 0.949, TSSmean = 0.74). In robustness analysis, RF was slightly more sensitive than GARP and QUEST, making it necessary to consider several random partitioning options for preparing training and validation groups. The outcomes of this study can be useful in sustainable management of groundwater resources in the study region.
英文关键词	spatial modeling machine-learning algorithms distribution models
类型	Article
语种	英语
国家	Iran ; Sweden
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000529249500064
WOS关键词	DECISION-TREE MODEL ; WEIGHTS-OF-EVIDENCE ; SPATIAL PREDICTION ; LOGISTIC-REGRESSION ; SUSCEPTIBILITY ASSESSMENT ; STATISTICAL-MODELS ; LANDSLIDE HAZARDS ; RIVER-BASIN ; GIS ; AREA
WOS类目	Environmental Sciences ; Water Resources
WOS研究方向	Environmental Sciences & Ecology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/318531
作者单位	1.Lorestan Univ, Agr & Nat Resources Fac, Dept Watershed Management, Khorramabad 6815144316, Iran; 2.AREEO, Soil Conservat & Watershed Management Res Dept, Kurdistan Agr & Nat Resources Res & Educ Ctr, Sanandaj 6616936311, Iran; 3.Stockholm Univ, Dept Phys Geog, SE-10691 Stockholm, Sweden; 4.Stockholm Univ, Bolin Ctr Climate Res, SE-10691 Stockholm, Sweden
推荐引用方式 GB/T 7714	Moghaddam, Davoud Davoudi,Rahmati, Omid,Haghizadeh, Ali,et al. A Modeling Comparison of Groundwater Potential Mapping in a Mountain Bedrock Aquifer: QUEST, GARP, and RF Models[J],2020,12(3).
APA	Moghaddam, Davoud Davoudi,Rahmati, Omid,Haghizadeh, Ali,&Kalantari, Zahra.(2020).A Modeling Comparison of Groundwater Potential Mapping in a Mountain Bedrock Aquifer: QUEST, GARP, and RF Models.WATER,12(3).
MLA	Moghaddam, Davoud Davoudi,et al."A Modeling Comparison of Groundwater Potential Mapping in a Mountain Bedrock Aquifer: QUEST, GARP, and RF Models".WATER 12.3(2020).