Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis
Aflaj (plural of falaj) are tunnels or trenches built to deliver groundwater from its source to the point of consumption. Support vector machine (SVM) and extreme gradient boosting (XGB) machine learning models were used to predict groundwater aflaj potential in the Nizwa watershed in the Sultanate...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5425 |
| _version_ | 1797466569460154368 |
|---|---|
| author | Khalifa M. Al-Kindi Saeid Janizadeh |
| author_facet | Khalifa M. Al-Kindi Saeid Janizadeh |
| author_sort | Khalifa M. Al-Kindi |
| collection | DOAJ |
| description | Aflaj (plural of falaj) are tunnels or trenches built to deliver groundwater from its source to the point of consumption. Support vector machine (SVM) and extreme gradient boosting (XGB) machine learning models were used to predict groundwater aflaj potential in the Nizwa watershed in the Sultanate of Oman (Oman). Nizwa city is a focal point of aflaj that underlies the historical relationship between ecology, economic dynamics, agricultural systems, and human settlements. Three hyperparameter algorithms, grid search (GS), random search (RS), and Bayesian optimisation, were used to optimise the parameters of the XGB model. Sentinel-2 and light detection and ranging (LiDAR) data via geographical information systems (GIS) were employed to derive variables of land use/land cover, and hydrological, topographical, and geological factors. The groundwater aflaj potential maps were categorised into five classes: <i>deficient</i>, <i>low</i>, <i>moderate</i>, <i>high</i>, and <i>very high</i>. Based on the evaluation of accuracy in the training stage, the following models showed a <i>high</i> level of accuracy based on the area under the curve: Bayesian-XGB (0.99), GS-XGB (0.97), RS-XGB (0.96), SVM (0.96), and XGB (0.93). The validation results showed that the Bayesian hyperparameter algorithm significantly increased XGB model efficiency in modelling groundwater aflaj potential. The highest percentages of groundwater potential in the <i>very high</i> class were the XGB (10%), SVM (8%), GS-XGB (6%), RS-XGB (6%), and Bayesian-XGB (6%) models. Most of these areas were located in the central and northeast parts of the case study area. The study concluded that evaluating existing groundwater datasets, facilities, current, and future spatial datasets is critical in order to design systems capable of mapping groundwater aflaj based on geospatial and ML techniques. In turn, groundwater protection service projects and integrated water source management (IWSM) programs will be able to protect the aflaj irrigation system from threats by implementing timely preventative measures. |
| first_indexed | 2024-03-09T18:41:39Z |
| format | Article |
| id | doaj.art-00626a793d814aa9b2b90c5bffcdb736 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:41:39Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-00626a793d814aa9b2b90c5bffcdb7362023-11-24T06:38:49ZengMDPI AGRemote Sensing2072-42922022-10-011421542510.3390/rs14215425Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and AnalysisKhalifa M. Al-Kindi0Saeid Janizadeh1UNESCO Chair of Aflaj Studies, Archaeohydrology, University of Nizwa, Nizwa P.O. Box 33, OmanDepartment of Watershed Management Engineering and Sciences, Faculty of Natural Resources and Marine Science, Tarbiat Modares University, Tehran 14115-111, IranAflaj (plural of falaj) are tunnels or trenches built to deliver groundwater from its source to the point of consumption. Support vector machine (SVM) and extreme gradient boosting (XGB) machine learning models were used to predict groundwater aflaj potential in the Nizwa watershed in the Sultanate of Oman (Oman). Nizwa city is a focal point of aflaj that underlies the historical relationship between ecology, economic dynamics, agricultural systems, and human settlements. Three hyperparameter algorithms, grid search (GS), random search (RS), and Bayesian optimisation, were used to optimise the parameters of the XGB model. Sentinel-2 and light detection and ranging (LiDAR) data via geographical information systems (GIS) were employed to derive variables of land use/land cover, and hydrological, topographical, and geological factors. The groundwater aflaj potential maps were categorised into five classes: <i>deficient</i>, <i>low</i>, <i>moderate</i>, <i>high</i>, and <i>very high</i>. Based on the evaluation of accuracy in the training stage, the following models showed a <i>high</i> level of accuracy based on the area under the curve: Bayesian-XGB (0.99), GS-XGB (0.97), RS-XGB (0.96), SVM (0.96), and XGB (0.93). The validation results showed that the Bayesian hyperparameter algorithm significantly increased XGB model efficiency in modelling groundwater aflaj potential. The highest percentages of groundwater potential in the <i>very high</i> class were the XGB (10%), SVM (8%), GS-XGB (6%), RS-XGB (6%), and Bayesian-XGB (6%) models. Most of these areas were located in the central and northeast parts of the case study area. The study concluded that evaluating existing groundwater datasets, facilities, current, and future spatial datasets is critical in order to design systems capable of mapping groundwater aflaj based on geospatial and ML techniques. In turn, groundwater protection service projects and integrated water source management (IWSM) programs will be able to protect the aflaj irrigation system from threats by implementing timely preventative measures.https://www.mdpi.com/2072-4292/14/21/5425machine learninggroundwaterhyperparameteralgorithmsaflajOman |
| spellingShingle | Khalifa M. Al-Kindi Saeid Janizadeh Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis Remote Sensing machine learning groundwater hyperparameter algorithms aflaj Oman |
| title | Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis |
| title_full | Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis |
| title_fullStr | Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis |
| title_full_unstemmed | Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis |
| title_short | Machine Learning and Hyperparameters Algorithms for Identifying Groundwater Aflaj Potential Mapping in Semi-Arid Ecosystems Using LiDAR, Sentinel-2, GIS Data, and Analysis |
| title_sort | machine learning and hyperparameters algorithms for identifying groundwater aflaj potential mapping in semi arid ecosystems using lidar sentinel 2 gis data and analysis |
| topic | machine learning groundwater hyperparameter algorithms aflaj Oman |
| url | https://www.mdpi.com/2072-4292/14/21/5425 |
| work_keys_str_mv | AT khalifamalkindi machinelearningandhyperparametersalgorithmsforidentifyinggroundwateraflajpotentialmappinginsemiaridecosystemsusinglidarsentinel2gisdataandanalysis AT saeidjanizadeh machinelearningandhyperparametersalgorithmsforidentifyinggroundwateraflajpotentialmappinginsemiaridecosystemsusinglidarsentinel2gisdataandanalysis |