Multi-valued Gaussian process regression for immediate Tsunami prediction from water pressure gauges
| Project/Area Number |
20K11949
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2022: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2021: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 機械学習 / スパースモデリング / 深層学習 / 津波高即時予測 / 即時津波高予測 / べき乗則 / 多層パーセプトロン / ガウス過程回帰 / 海底地震 / 能動学習 / 海底地震津波観測網 |
|---|
| Outline of Research at the Start |
津波高の即時予測において，予め津波シミュレーションを多数のシナリオについて計算しデータベースを用いた予測が行われている．従来の最適なシナリオをデータベースから検索して津波予測をする場合，シミュレーションで仮定しているシナリオの仮定は実際のシナリオと乖離してしまう．そこで本研究課題では，シナリオ混合による広範囲の津波高即時予測の精緻化を機械学習によって行い，徳島県での津波予測システムのプロトタイプに組み込みを目指す．
|
| Outline of Final Research Achievements |
In this study, we conducted research to refine the tsunami simulation and to improve the accuracy of immediate prediction of tsunami heights in a wide range by scenario mixing using multi-level Gaussian process regression, and to promote the practical application of the scenario mixing approach. Specifically, first, to improve the accuracy of tsunami height prediction, we conducted tsunami simulations with a non-uniform slip distribution that could exist in reality. Secondly, the maximum tsunami height and the arrival time of the tsunami at the sea bottom pressure sensor off the Kii Peninsula were used to predict the coastal tsunami height with high accuracy by Gaussian process regression. Finally, for emergency response to a major tsunami disaster, we constructed a prediction model for tsunami inundation depth estimation using deep learning to estimate the inundation depth of land for rescue operations.
|
| Academic Significance and Societal Importance of the Research Achievements |
今回構築した津波高予測のための高精度シミュレーション及び、津波高即時予測手法は，高速計算や大規模データベースを必要としない,軽量で堅牢な予測システムを構築できる．現在,大規模な津波予測システムが主流になりつつあるが,大災害時の不測の事態を緩和するためにこのようなスタンドアロン型の予測システムを持つことは有益であると考えている．
|
Report
(4 results)
Research Products
(4 results)
