| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Outline of Final Research Achievements |
The purpose of this study is developing next-generation ground motion prediction equations (GMPE) that are applicable to mega earthquakes and the prediction errors to be small. At first, strong-motion database including mega earthquakes are constructed. Using this database, both of ordinary GMPE with small parameters by regression analysis and artificial neural network (ANN) with many parameters by using deep learning method are evaluated. The prediction errors by the ANN become smaller than those of the ordinary GMPE, while ANN's applicability to extended faults and stability are still to be investigated.
|
