Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models
In this study, we aimed to investigate the hydrological performance of three gridded precipitation products—CHIRPS, RFE, and TRMM3B42V7—in monthly streamflow forecasting. After statistical evaluation, two monthly streamflow forecasting models—support vector machine (SVM) and artificial neural networ...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/20/4147 |
| _version_ | 1797513203071057920 |
|---|---|
| author | Mohammed M. Alquraish Mosaad Khadr |
| author_facet | Mohammed M. Alquraish Mosaad Khadr |
| author_sort | Mohammed M. Alquraish |
| collection | DOAJ |
| description | In this study, we aimed to investigate the hydrological performance of three gridded precipitation products—CHIRPS, RFE, and TRMM3B42V7—in monthly streamflow forecasting. After statistical evaluation, two monthly streamflow forecasting models—support vector machine (SVM) and artificial neural network (ANN)—were developed using the monthly temporal resolution data derived from these products. The hydrological performance of the developed forecasting models was then evaluated using several statistical indices, including NSE, MAE, RMSE, and R<sup>2</sup>. The performance measures confirmed that the CHIRPS product has superior performance compared to RFE 2.0 and TRMM data, and it could provide reliable rainfall estimates for use as input in forecasting models. Likewise, the results of the forecasting models confirmed that the ANN and SVM both achieved acceptable levels of accuracy for forecasting streamflow; however, the ANN model was superior (R<sup>2</sup> = 0.898–0.735) to the SVM (R<sup>2</sup> = 0.742–0.635) in both the training and testing periods. |
| first_indexed | 2024-03-10T06:13:21Z |
| format | Article |
| id | doaj.art-6e565dc456384436a2180d3b71596156 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:13:21Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6e565dc456384436a2180d3b715961562023-11-22T19:54:54ZengMDPI AGRemote Sensing2072-42922021-10-011320414710.3390/rs13204147Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine ModelsMohammed M. Alquraish0Mosaad Khadr1Department of Mechanical Engineering, College of Engineering, University of Bisha, P.O. Box 001, Bisha 61922, Saudi ArabiaDepartment of Civil Engineering, College of Engineering, University of Bisha, P.O. Box 001, Bisha 61922, Saudi ArabiaIn this study, we aimed to investigate the hydrological performance of three gridded precipitation products—CHIRPS, RFE, and TRMM3B42V7—in monthly streamflow forecasting. After statistical evaluation, two monthly streamflow forecasting models—support vector machine (SVM) and artificial neural network (ANN)—were developed using the monthly temporal resolution data derived from these products. The hydrological performance of the developed forecasting models was then evaluated using several statistical indices, including NSE, MAE, RMSE, and R<sup>2</sup>. The performance measures confirmed that the CHIRPS product has superior performance compared to RFE 2.0 and TRMM data, and it could provide reliable rainfall estimates for use as input in forecasting models. Likewise, the results of the forecasting models confirmed that the ANN and SVM both achieved acceptable levels of accuracy for forecasting streamflow; however, the ANN model was superior (R<sup>2</sup> = 0.898–0.735) to the SVM (R<sup>2</sup> = 0.742–0.635) in both the training and testing periods.https://www.mdpi.com/2072-4292/13/20/4147streamflow forecastingartificial neural networksupport vector machineremote sensingsatellite precipitation productsupper Blue Nile River basin |
| spellingShingle | Mohammed M. Alquraish Mosaad Khadr Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models Remote Sensing streamflow forecasting artificial neural network support vector machine remote sensing satellite precipitation products upper Blue Nile River basin |
| title | Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models |
| title_full | Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models |
| title_fullStr | Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models |
| title_full_unstemmed | Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models |
| title_short | Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models |
| title_sort | remote sensing based streamflow forecasting using artificial neural network and support vector machine models |
| topic | streamflow forecasting artificial neural network support vector machine remote sensing satellite precipitation products upper Blue Nile River basin |
| url | https://www.mdpi.com/2072-4292/13/20/4147 |
| work_keys_str_mv | AT mohammedmalquraish remotesensingbasedstreamflowforecastingusingartificialneuralnetworkandsupportvectormachinemodels AT mosaadkhadr remotesensingbasedstreamflowforecastingusingartificialneuralnetworkandsupportvectormachinemodels |