Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia
Water scarcity is a severe problem in Tunisia, particularly in the northern region crossed by the Medjerda River, where groundwater is a conjoint water resource that is increasingly exploited. The aim of this study is to delineate the groundwater potential zones (GWPZs) in the Lower Valley of the Me...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/1/152 |
_version_ | 1797406441070395392 |
---|---|
author | Fatma Trabelsi Salsebil Bel Hadj Ali Saro Lee |
author_facet | Fatma Trabelsi Salsebil Bel Hadj Ali Saro Lee |
author_sort | Fatma Trabelsi |
collection | DOAJ |
description | Water scarcity is a severe problem in Tunisia, particularly in the northern region crossed by the Medjerda River, where groundwater is a conjoint water resource that is increasingly exploited. The aim of this study is to delineate the groundwater potential zones (GWPZs) in the Lower Valley of the Medjerda basin by using single benchmark machine learning models based on artificial neural network (ANN), random forest (RF), and support vector regression (SVR), and by developing a novel hybrid method, NB-RF-SVR, to reach the highest accuracy of groundwater potential prediction. Each model produced a spatial groundwater potential map (GPM) with the input of 26 groundwater-related factors (GRF) selected by the frequency ratio model and 70% of the transmissivity training data. The models’ effectiveness was assessed using the AUC-ROC curve, sensitivity, specificity, MAE, and RMSE metric indicators. The validation findings revealed that all the models performed successfully for the GWPZ mapping, where the AUC values for the ANN, RF, SVR, and NB-RF-SVR models were estimated as 71%, 79%, 87%, and 92%, respectively. The relative importance of the GWPZs revealed that land use followed by geology and elevation were the most important factors. Finally, these outcomes can provide valuable information for decision makers to effectively manage groundwater in water-stressed regions. |
first_indexed | 2024-03-09T03:26:32Z |
format | Article |
id | doaj.art-7f80278dfff74c34b9e0d90dd93e14eb |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T03:26:32Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-7f80278dfff74c34b9e0d90dd93e14eb2023-12-03T15:02:30ZengMDPI AGRemote Sensing2072-42922022-12-0115115210.3390/rs15010152Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern TunisiaFatma Trabelsi0Salsebil Bel Hadj Ali1Saro Lee2Research Unit Sustainable Management of Water and Soil Resources, Higher School of Engineers of Medjez El Bab (ESIM), University of Jendouba, Jendouba 8189, TunisiaResearch Unit Sustainable Management of Water and Soil Resources, Higher School of Engineers of Medjez El Bab (ESIM), University of Jendouba, Jendouba 8189, TunisiaGeoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro, Yuseong-gu, Daejeon 34132, Republic of KoreaWater scarcity is a severe problem in Tunisia, particularly in the northern region crossed by the Medjerda River, where groundwater is a conjoint water resource that is increasingly exploited. The aim of this study is to delineate the groundwater potential zones (GWPZs) in the Lower Valley of the Medjerda basin by using single benchmark machine learning models based on artificial neural network (ANN), random forest (RF), and support vector regression (SVR), and by developing a novel hybrid method, NB-RF-SVR, to reach the highest accuracy of groundwater potential prediction. Each model produced a spatial groundwater potential map (GPM) with the input of 26 groundwater-related factors (GRF) selected by the frequency ratio model and 70% of the transmissivity training data. The models’ effectiveness was assessed using the AUC-ROC curve, sensitivity, specificity, MAE, and RMSE metric indicators. The validation findings revealed that all the models performed successfully for the GWPZ mapping, where the AUC values for the ANN, RF, SVR, and NB-RF-SVR models were estimated as 71%, 79%, 87%, and 92%, respectively. The relative importance of the GWPZs revealed that land use followed by geology and elevation were the most important factors. Finally, these outcomes can provide valuable information for decision makers to effectively manage groundwater in water-stressed regions.https://www.mdpi.com/2072-4292/15/1/152groundwater potentialmachine learningnovel hybridMedjerda |
spellingShingle | Fatma Trabelsi Salsebil Bel Hadj Ali Saro Lee Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia Remote Sensing groundwater potential machine learning novel hybrid Medjerda |
title | Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia |
title_full | Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia |
title_fullStr | Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia |
title_full_unstemmed | Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia |
title_short | Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia |
title_sort | comparison of novel hybrid and benchmark machine learning algorithms to predict groundwater potentiality case of a drought prone region of medjerda basin northern tunisia |
topic | groundwater potential machine learning novel hybrid Medjerda |
url | https://www.mdpi.com/2072-4292/15/1/152 |
work_keys_str_mv | AT fatmatrabelsi comparisonofnovelhybridandbenchmarkmachinelearningalgorithmstopredictgroundwaterpotentialitycaseofadroughtproneregionofmedjerdabasinnortherntunisia AT salsebilbelhadjali comparisonofnovelhybridandbenchmarkmachinelearningalgorithmstopredictgroundwaterpotentialitycaseofadroughtproneregionofmedjerdabasinnortherntunisia AT sarolee comparisonofnovelhybridandbenchmarkmachinelearningalgorithmstopredictgroundwaterpotentialitycaseofadroughtproneregionofmedjerdabasinnortherntunisia |