干旱区生态环境知识资源中心(Arid): Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region

Arid

DOI	10.1016/j.jafrearsci.2021.104244
	Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region
	El Bilali, Ali; Taleb, Abdeslam; Brouziyne, Youssef
通讯作者	El Bilali, A (corresponding author), Hassan II Univ Casablanca, Fac Sci & Tech Mohammedia, Casablanca, Morocco.
来源期刊	JOURNAL OF AFRICAN EARTH SCIENCES
ISSN	1464-343X
EISSN	1879-1956
出版年	2021
卷号	181
英文摘要	Groundwater level fluctuation is a nonlinear and non-stationary system as it depends on several factors in the time and space scales. Conceptual models require several physical parameters whose estimation is delicate in poorly monitored areas. However, data-based models may be valuable for modelling and forecasting groundwater level over short and long terms. To that end, four machine learning models, namely: Support Vector Regression, k- Nearest Neighbour (k-NN), Random Forest (RF), and Artificial Neural Network (ANN), are trained, validated, and compared for predicting groundwater level (GWL) at seven piezometers on alluvial groundwater of Tanobart aquifer in Morocco. The results revealed that the ANN models succeeded properly in simulating GWL at five piezometers out of the total seven piezometers considered in this study (NSE = 0.69 to 0.8); the RF was satisfactory at five piezometers (NSE = 0.41 to 0.72) and SVR at three piezometers (NSE = 0.57 to 0.81); the k-NN was the poorest model among all the investigated models (NSE = 1.05 to 0.15). The uncertainty analysis showed that the selected models are accurate overall; the SVR model showed the best forecasting accuracy with the smallest 95% interval prediction error (0.25 m and 0.11 m) at one piezometer. This study provides new insight to forecast the GWL under a semi-arid context such Tanobart aquifer in Khemesset province, Morocco.
英文关键词	Alluvial groundwater Random forest Artificial neural network Support vector regression Tanobart Morocco
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000660988700003
WOS关键词	HYDROLOGICAL-ECONOMIC MODEL ; CLIMATE-CHANGE ; GROUNDWATER RESOURCES ; WATER MANAGEMENT ; PREDICTION ; MINERALIZATION ; VULNERABILITY ; SALINITY ; ANFIS ; BASIN
WOS类目	Geosciences, Multidisciplinary
WOS研究方向	Geology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/350646
作者单位	[El Bilali, Ali; Taleb, Abdeslam] Hassan II Univ Casablanca, Fac Sci & Tech Mohammedia, Casablanca, Morocco; [Brouziyne, Youssef] Mohammed VI Polytech Univ, Int Water Res Inst, Benguerir, Morocco
推荐引用方式 GB/T 7714	El Bilali, Ali,Taleb, Abdeslam,Brouziyne, Youssef. Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region[J],2021,181.
APA	El Bilali, Ali,Taleb, Abdeslam,&Brouziyne, Youssef.(2021).Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region.JOURNAL OF AFRICAN EARTH SCIENCES,181.
MLA	El Bilali, Ali,et al."Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region".JOURNAL OF AFRICAN EARTH SCIENCES 181(2021).