| Project/Area Number |
21K20443
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
0303:Civil engineering, social systems engineering, safety engineering, disaster prevention engineering, and related fields
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
Yin Gaohong 東京大学, 生産技術研究所, 特任研究員 (00906282)
|
|---|
| Project Period (FY) |
2021-08-30 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | GRACE / TWS / Downscaling / Deep Learning / Flood / Drought / TWSA / LSTM / flood and drought / Machine learning |
|---|
| Outline of Research at the Start |
The study propose to downscale GRACE terrestrial water storage (TWSA) using machine learning for flood and drought study. It will provide downscaled TWSA data in both space and time, assimilate TWSA into TE-system, and use downscaled TWSA to extend drought and flood forecasting lead time.
|
| Outline of Final Research Achievements |
Flood and drought are global issue causing devastating damage to the ecosystem, human lives, and economics. Monitoring the sptaio-temporal variation of terrestrial water storage (TWS) is important for water management and hazard mitigation. However, current remote sensing-based TWS data has coarse spatial resolution (300 km), which limits its application to sub-regional scale. The study used a deep learning approach to downscale remote sensing-based TWS in space, providing more details of water mass variation at sub-regional to local scale. The downscaled TWS provides a great opportunity to monitor drought and predict flood with high spatial resolution on a sub-regional to local scales. The outcomes of the study make it possible to extent the application of remote sensing-based TWS to regions such as Japan and South Korea.
|
| Academic Significance and Societal Importance of the Research Achievements |
1. Improve the understanding of the spatiotemporal variation of terrestrial water storage, which is important for water management and related policy making.
2. Monitor and forecast flood and drought on a sub-regional to local scale, which benefits more accurate and targeted hazards mitigation.
|
