A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China
Study region: Mu Us Sandy Land, China. Study focus: The groundwater table in unconfined aquifers is often a subdued replica of the topography or land surface. In hilly terrain, spatial interpolation methods are prone to errors such as higher interpolation water level than the ground surface due to s...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Journal of Hydrology: Regional Studies |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214581822002026 |
| _version_ | 1811211735571365888 |
|---|---|
| author | Pinzeng Rao Yicheng Wang Yang Liu Xiaoya Wang Yukun Hou Shibing Pan Fang Wang Dongsheng Zhu |
| author_facet | Pinzeng Rao Yicheng Wang Yang Liu Xiaoya Wang Yukun Hou Shibing Pan Fang Wang Dongsheng Zhu |
| author_sort | Pinzeng Rao |
| collection | DOAJ |
| description | Study region: Mu Us Sandy Land, China. Study focus: The groundwater table in unconfined aquifers is often a subdued replica of the topography or land surface. In hilly terrain, spatial interpolation methods are prone to errors such as higher interpolation water level than the ground surface due to sparse observation wells. Meanwhile, in ridge areas, groundwater depth can easily be overestimated with limited groundwater observations. To address these issues, this paper proposes a framework to learn groundwater depth using related groundwater variables based on the extreme gradient boosting (XGB) machine learning method. Moreover, the groundwater level map is drawn based on the predicted groundwater depths and elevation data.New Hydrological Insights for the RegionThe results obtained by the XGB algorithm are compared with those of common interpolation methods (including inverse distance weighting, ordinary kriging, and collaborative ordinary kriging) and machine learning methods (including multiple linear regression, geographically weighted regression, support vector regression, and random forest). The results showed that the XGB using the Tweedie loss function performs best in learning groundwater depth compared with interpolation methods and other machine learning methods, and almost completely overcomes the effects of imbalanced data. The topographic factors such as elevation, topographic position index, and topographic roughness index are key factors for groundwater depth. This study provides a reference for improving regional GL mapping, especially in areas of complex terrain. |
| first_indexed | 2024-04-12T05:16:59Z |
| format | Article |
| id | doaj.art-93c831193ed74a3d831cad7b8e67e49b |
| institution | Directory Open Access Journal |
| issn | 2214-5818 |
| language | English |
| last_indexed | 2024-04-12T05:16:59Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Hydrology: Regional Studies |
| spelling | doaj.art-93c831193ed74a3d831cad7b8e67e49b2022-12-22T03:46:36ZengElsevierJournal of Hydrology: Regional Studies2214-58182022-10-0143101189A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, ChinaPinzeng Rao0Yicheng Wang1Yang Liu2Xiaoya Wang3Yukun Hou4Shibing Pan5Fang Wang6Dongsheng Zhu7State Key Laboratory of Hydroscience and Engineering, Department of Hydraulic Engineering, Tsinghua University, Beijing 100084, China; State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaChina Communication Construction Company Second Harbor Consultants Co., Ltd, Wuhan 430060, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, China; Corresponding author.State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaStudy region: Mu Us Sandy Land, China. Study focus: The groundwater table in unconfined aquifers is often a subdued replica of the topography or land surface. In hilly terrain, spatial interpolation methods are prone to errors such as higher interpolation water level than the ground surface due to sparse observation wells. Meanwhile, in ridge areas, groundwater depth can easily be overestimated with limited groundwater observations. To address these issues, this paper proposes a framework to learn groundwater depth using related groundwater variables based on the extreme gradient boosting (XGB) machine learning method. Moreover, the groundwater level map is drawn based on the predicted groundwater depths and elevation data.New Hydrological Insights for the RegionThe results obtained by the XGB algorithm are compared with those of common interpolation methods (including inverse distance weighting, ordinary kriging, and collaborative ordinary kriging) and machine learning methods (including multiple linear regression, geographically weighted regression, support vector regression, and random forest). The results showed that the XGB using the Tweedie loss function performs best in learning groundwater depth compared with interpolation methods and other machine learning methods, and almost completely overcomes the effects of imbalanced data. The topographic factors such as elevation, topographic position index, and topographic roughness index are key factors for groundwater depth. This study provides a reference for improving regional GL mapping, especially in areas of complex terrain.http://www.sciencedirect.com/science/article/pii/S2214581822002026Groundwater level mappingGroundwater depthExtreme gradient boostingImbalanced distribution |
| spellingShingle | Pinzeng Rao Yicheng Wang Yang Liu Xiaoya Wang Yukun Hou Shibing Pan Fang Wang Dongsheng Zhu A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China Journal of Hydrology: Regional Studies Groundwater level mapping Groundwater depth Extreme gradient boosting Imbalanced distribution |
| title | A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China |
| title_full | A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China |
| title_fullStr | A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China |
| title_full_unstemmed | A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China |
| title_short | A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China |
| title_sort | comparison of multiple methods for mapping groundwater levels in the mu us sandy land china |
| topic | Groundwater level mapping Groundwater depth Extreme gradient boosting Imbalanced distribution |
| url | http://www.sciencedirect.com/science/article/pii/S2214581822002026 |
| work_keys_str_mv | AT pinzengrao acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yichengwang acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yangliu acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT xiaoyawang acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yukunhou acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT shibingpan acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT fangwang acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT dongshengzhu acomparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT pinzengrao comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yichengwang comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yangliu comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT xiaoyawang comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT yukunhou comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT shibingpan comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT fangwang comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina AT dongshengzhu comparisonofmultiplemethodsformappinggroundwaterlevelsinthemuussandylandchina |