Search

本研究は，沖合観測情報を用いた逆解析手法によるリアルタイム津波予測を提案し，予測精度向上と実用化を目指した最適条件について検討したものである。沖合で観測される津波水位の時系列変動を用いて逆解析を実施し，分割小領域毎の水位変動量を求め，波源域の初期水位変動量と沿岸へ到達する津波波形の推定を試みた。東南海・南海地震を対象に，大阪湾内における到達波形と予測波形を比較したところ，精度の良い結果が得られた。観測時間が長くなれば，再現精度が上がることがわかった。観測点を増やし最適配置をすれば必要観測時間を短縮でき，大阪湾内だけでなく，和歌山下津港にも本手法を適用できることを示した。, A Real-time tsunami prediction method by inverse analysis was established and evaluated its applicability in this study. The inverse analysis of the offshore tsunami data estimates the initial displacements of water surface in the segmented tsunami sources. The estimated initial displacements predict tsunami profiles in inshore points of interests. Optimum conditions for the accuracy improvement were also examined aiming at practical use. Tsunami sources were estimated well compared with the initial displacement of tsunami generated by the Tonankai and Nankai Earthquake model. It was also confirmed that the real-time prediction can apply to predict the tsunami at Shimotsu Port in Wakayama Prefecture as well as in Osaka Bay.

The real-time river stage prediction model is developed, using the artificial neural network model which is trained by the deep learning method. The model is composed of 4 layer feed-forward network. As a network training method, stochastic gradient descent method based on the back propagation method was applied. As a pre-training method, the denoising autoencoder was applied. The developed model is applied to the one catchment of the OOYODO River, one of the first-grade river in Japan. Input of the model is hourly change of water level and hourly rainfall, output data is water level of HIWATASHI. To clarify the suitable configuration of the model, case study was done. The prediction result is compared with the other prediction models, consequently the developed model showed the best performance.