Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method
River water surface extent can be extracted from optical and radar satellite images; this is useful for estimating streamflow from space. The radiation characteristics of open water from the visible and microwave bands are different and provide independent information. In this study, for the purpose...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/21/5184 |
| _version_ | 1797631325714251776 |
|---|---|
| author | Xingcan Wang Wenchao Sun Fan Lu Rui Zuo |
| author_facet | Xingcan Wang Wenchao Sun Fan Lu Rui Zuo |
| author_sort | Xingcan Wang |
| collection | DOAJ |
| description | River water surface extent can be extracted from optical and radar satellite images; this is useful for estimating streamflow from space. The radiation characteristics of open water from the visible and microwave bands are different and provide independent information. In this study, for the purpose of improving streamflow estimation from space for data-sparse regions, a method that combines satellite optical and radar images data for streamflow estimation using a machine learning technique was proposed. The method was demonstratedthrough a case study in the river segment upstream of the Ganzi gauging station on the Yalong River, China. Utilizing the support vector regression (SVR) model, the feasibility of different combinations of water surface area derived from Sentinel-1 synthetic aperture radar images (AREA_SAR), modified normalized difference water index derived from Landsat 8 images (MNDWI), and reflectance ratios between NIR and SWIR channels derived from MODIS images (R<sub>NIR</sub>/R<sub>SWIR</sub>) for streamflow estimation were evaluated through three experiments. In Experiment I, three models using AREA_SAR (Model 1), MNDWI (Model 2), and a combination of AREA_SAR and MNDWI (Model 3) were built; the mean relative error (MRE) and mean absolute error (MAE) of streamflow estimates corresponding to the SVR model using both AREA_SAR and MNDWI (Model 3) were 0.19 and 31.6 m<sup>3</sup>/s for the testing dataset, respectively, and were lower than two models using AREA_SAR (Model 1) or MNDWI (Model 2) solely as inputs. In Experiment II, three models with AREA_SAR (Model 4), R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 5), and a combination of AREA_SAR and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 6) as inputs were developed; the MRE and MAE for the model using AREA_SAR and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 6) were 0.25 and 56.5 m<sup>3</sup>/s, respectively, which outperformed the two models treating AREA_SAR (Model 4) or MNDWI (Model 5) as single types of inputs. In Experiment III, three models using AREA_SAR (Model 7), MNDWI, and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 8) and the combination of AREA_SAR, MNDWI and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 9) were built; combining all three types of satellite observations (Model 9) exhibited the highest accuracy, for which the MRE and MAE were 0.18 and 18.4 m<sup>3</sup>/s, respectively. The results of all three experiments demonstrated that integrating optical and microwave observations could improve the accuracy of streamflow estimates using a data-driven model; the proposed method has great potential for near-real-time estimations of flood magnitude or to reconstruct past variations in streamflow using historical satellite images in data-sparse regions. |
| first_indexed | 2024-03-11T11:22:11Z |
| format | Article |
| id | doaj.art-469bb0d91f314fdc9d86c561b2291e7d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T11:22:11Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-469bb0d91f314fdc9d86c561b2291e7d2023-11-10T15:11:19ZengMDPI AGRemote Sensing2072-42922023-10-011521518410.3390/rs15215184Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning MethodXingcan Wang0Wenchao Sun1Fan Lu2Rui Zuo3Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, Xinjiekouwai Street 19, Beijing 100875, ChinaBeijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, Xinjiekouwai Street 19, Beijing 100875, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, ChinaBeijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, Xinjiekouwai Street 19, Beijing 100875, ChinaRiver water surface extent can be extracted from optical and radar satellite images; this is useful for estimating streamflow from space. The radiation characteristics of open water from the visible and microwave bands are different and provide independent information. In this study, for the purpose of improving streamflow estimation from space for data-sparse regions, a method that combines satellite optical and radar images data for streamflow estimation using a machine learning technique was proposed. The method was demonstratedthrough a case study in the river segment upstream of the Ganzi gauging station on the Yalong River, China. Utilizing the support vector regression (SVR) model, the feasibility of different combinations of water surface area derived from Sentinel-1 synthetic aperture radar images (AREA_SAR), modified normalized difference water index derived from Landsat 8 images (MNDWI), and reflectance ratios between NIR and SWIR channels derived from MODIS images (R<sub>NIR</sub>/R<sub>SWIR</sub>) for streamflow estimation were evaluated through three experiments. In Experiment I, three models using AREA_SAR (Model 1), MNDWI (Model 2), and a combination of AREA_SAR and MNDWI (Model 3) were built; the mean relative error (MRE) and mean absolute error (MAE) of streamflow estimates corresponding to the SVR model using both AREA_SAR and MNDWI (Model 3) were 0.19 and 31.6 m<sup>3</sup>/s for the testing dataset, respectively, and were lower than two models using AREA_SAR (Model 1) or MNDWI (Model 2) solely as inputs. In Experiment II, three models with AREA_SAR (Model 4), R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 5), and a combination of AREA_SAR and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 6) as inputs were developed; the MRE and MAE for the model using AREA_SAR and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 6) were 0.25 and 56.5 m<sup>3</sup>/s, respectively, which outperformed the two models treating AREA_SAR (Model 4) or MNDWI (Model 5) as single types of inputs. In Experiment III, three models using AREA_SAR (Model 7), MNDWI, and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 8) and the combination of AREA_SAR, MNDWI and R<sub>NIR</sub>/R<sub>SWIR</sub> (Model 9) were built; combining all three types of satellite observations (Model 9) exhibited the highest accuracy, for which the MRE and MAE were 0.18 and 18.4 m<sup>3</sup>/s, respectively. The results of all three experiments demonstrated that integrating optical and microwave observations could improve the accuracy of streamflow estimates using a data-driven model; the proposed method has great potential for near-real-time estimations of flood magnitude or to reconstruct past variations in streamflow using historical satellite images in data-sparse regions.https://www.mdpi.com/2072-4292/15/21/5184streamflow estimationoptical satellite imagesSARsupport vector regressionk-fold cross-validation |
| spellingShingle | Xingcan Wang Wenchao Sun Fan Lu Rui Zuo Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method Remote Sensing streamflow estimation optical satellite images SAR support vector regression k-fold cross-validation |
| title | Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method |
| title_full | Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method |
| title_fullStr | Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method |
| title_full_unstemmed | Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method |
| title_short | Combining Satellite Optical and Radar Image Data for Streamflow Estimation Using a Machine Learning Method |
| title_sort | combining satellite optical and radar image data for streamflow estimation using a machine learning method |
| topic | streamflow estimation optical satellite images SAR support vector regression k-fold cross-validation |
| url | https://www.mdpi.com/2072-4292/15/21/5184 |
| work_keys_str_mv | AT xingcanwang combiningsatelliteopticalandradarimagedataforstreamflowestimationusingamachinelearningmethod AT wenchaosun combiningsatelliteopticalandradarimagedataforstreamflowestimationusingamachinelearningmethod AT fanlu combiningsatelliteopticalandradarimagedataforstreamflowestimationusingamachinelearningmethod AT ruizuo combiningsatelliteopticalandradarimagedataforstreamflowestimationusingamachinelearningmethod |