EFFICIENCY IMPROVEMENT OF PINNS INVERSE ANALYSIS BY EXTRACTING SPATIAL FEATURES OF DATA
-
- DEGUCHI Shota
- 九州大学大学院 工学府土木工学専攻
-
- SHIBATA Yosuke
- 九州大学大学院 工学府土木工学専攻
-
- ASAI Mitsuteru
- 九州大学大学院 工学研究院社会基盤部門
Bibliographic Information
- Other Title
-
- 空間特徴量抽出を援用した PINNs によるパラメータ逆解析の効率化
Description
<p>With the rapid increase in torrential rainfall disasters and associated landslides, the demand for predictive numerical simulations has been growing. Due to computational limits, one needs to introduce approximations, however, the parameters to link detailed and approximated simulations (e.g. drag / bed friction coefficients) are determined empirically, and their applicability remains vague. In this context, this paper presents the application of a deep learning model, PINN (Physics-Informed Neural Network) to inverse analysis. This work assumes a scenario where one has an access to limited data (which is the case for real-site observation), and proposes utilizing data’s spatial features extracted from POD (Proper Orthogonal Decomposition) instead of conventional random number-based method. We found that proposed method supports PINN for faster training convergence and efficient parameter identification.</p>
Journal
-
- Japanese Journal of JSCE
-
Japanese Journal of JSCE 79 (15), n/a-, 2023
Japan Society of Civil Engineers
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390013884655543552
-
- ISSN
- 24366021
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- KAKEN
-
- Abstract License Flag
- Disallowed