[S-CG60] 機械学習による固体地球科学における現象及び理論の発見に向けて

[SCG60-04] Neural Network-Based Ground Motion Model Learning Site Property from Data

*岡崎 智久¹、岩田 具治^1,2、岩城 麻子³、藤原 広行³、上田 修功¹ (1.理化学研究所革新知能統合研究センター、2.NTTコミュニケーション科学基礎研究所、3.防災科学技術研究所)

キーワード：地震動予測モデル、ニューラル・ネットワーク、サイト特性

We constructed a neural network-based ground motion prediction model estimating spectral accelerations. Instead of specifying physical quantities as site properties, we input site ID and let the network learn the site property from strong motion data. We demonstrated that this model improves the prediction performance by applying it to KiK-net data in Tohoku region of Japan. Moreover, the obtained site property indicates that, for intermediate depth earthquakes, the short-period (< ~1 sec) spectrum is mainly governed by the distance from the volcanic front. This suggests that the proposed model successfully learned not only the ground condition under the individual sites but also propagation path effects known as anomalous seismic intensity in this region.