Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study
Drought is one of many critical problems that could arise as a result of climate change as it has an impact on many aspects of the world, including water resources and water scarcity. In this study, an assessment of hydrological drought in the Gidra River is carried out to characterize dry, normal,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/14/3/387 |
| _version_ | 1797484028639576064 |
|---|---|
| author | Wael Almikaeel Lea Čubanová Andrej Šoltész |
| author_facet | Wael Almikaeel Lea Čubanová Andrej Šoltész |
| author_sort | Wael Almikaeel |
| collection | DOAJ |
| description | Drought is one of many critical problems that could arise as a result of climate change as it has an impact on many aspects of the world, including water resources and water scarcity. In this study, an assessment of hydrological drought in the Gidra River is carried out to characterize dry, normal, and wet hydrological situations by using the Slovak Hydrometeorological Institute (SHMI) methodology. The water bearing coefficient is used as the index of the hydrological drought. As machine and deep learning are increasingly being used in many areas of hydroinformatics, this study is utilized artificial neural networks (ANNs) and support vector machine (SVM) models to predict the hydrological drought in the Gidra River based on daily average discharges in January, February, March, and April of the corresponding year. The study utilized in total 58 years of daily average discharge values containing 35 normal and wet years and 23 dry years. The results of the study show high accuracy of 100% in predicting hydrological drought in the Gidra River. The early classification of the hydrological situation in the Gidra River shows the potential of integrating water management with the deep and machine learning models in terms of irrigation planning and mitigation of drought effects. |
| first_indexed | 2024-03-09T22:56:37Z |
| format | Article |
| id | doaj.art-dfb2e6eba05745ae975ef3fe44d2d02e |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T22:56:37Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-dfb2e6eba05745ae975ef3fe44d2d02e2023-11-23T18:10:51ZengMDPI AGWater2073-44412022-01-0114338710.3390/w14030387Hydrological Drought Forecasting Using Machine Learning—Gidra River Case StudyWael Almikaeel0Lea Čubanová1Andrej Šoltész2Department of Hydraulic Engineering, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, Radlinského 11, 810 05 Bratislava, SlovakiaDepartment of Hydraulic Engineering, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, Radlinského 11, 810 05 Bratislava, SlovakiaDepartment of Hydraulic Engineering, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, Radlinského 11, 810 05 Bratislava, SlovakiaDrought is one of many critical problems that could arise as a result of climate change as it has an impact on many aspects of the world, including water resources and water scarcity. In this study, an assessment of hydrological drought in the Gidra River is carried out to characterize dry, normal, and wet hydrological situations by using the Slovak Hydrometeorological Institute (SHMI) methodology. The water bearing coefficient is used as the index of the hydrological drought. As machine and deep learning are increasingly being used in many areas of hydroinformatics, this study is utilized artificial neural networks (ANNs) and support vector machine (SVM) models to predict the hydrological drought in the Gidra River based on daily average discharges in January, February, March, and April of the corresponding year. The study utilized in total 58 years of daily average discharge values containing 35 normal and wet years and 23 dry years. The results of the study show high accuracy of 100% in predicting hydrological drought in the Gidra River. The early classification of the hydrological situation in the Gidra River shows the potential of integrating water management with the deep and machine learning models in terms of irrigation planning and mitigation of drought effects.https://www.mdpi.com/2073-4441/14/3/387droughtdrought forecastingmachine learningartificial neural networkssupport vector machineswater bearing coefficient |
| spellingShingle | Wael Almikaeel Lea Čubanová Andrej Šoltész Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study Water drought drought forecasting machine learning artificial neural networks support vector machines water bearing coefficient |
| title | Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study |
| title_full | Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study |
| title_fullStr | Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study |
| title_full_unstemmed | Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study |
| title_short | Hydrological Drought Forecasting Using Machine Learning—Gidra River Case Study |
| title_sort | hydrological drought forecasting using machine learning gidra river case study |
| topic | drought drought forecasting machine learning artificial neural networks support vector machines water bearing coefficient |
| url | https://www.mdpi.com/2073-4441/14/3/387 |
| work_keys_str_mv | AT waelalmikaeel hydrologicaldroughtforecastingusingmachinelearninggidrarivercasestudy AT leacubanova hydrologicaldroughtforecastingusingmachinelearninggidrarivercasestudy AT andrejsoltesz hydrologicaldroughtforecastingusingmachinelearninggidrarivercasestudy |