UNKNOWN PARAMETER ESTIMATION USING PHYSICS-INFORMED NEURAL NETWORKS WITH NOISED OBSERVATION DATA

• DEGUCHI Shota

  九州大学大学院 工学府建設システム工学専攻

• 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

• 予測に物理的意味を付与した機械学習 PINNs による誤差を含む教師データからのパラメータ推定

Abstract

Due to global warming, torrential rain disasters have been occurring in various places, raising the demand for predictive simulation technology. In order to perform numerical simulations, material parameters are often determined based on observation data or empirical laws. In this context, this work presents the application of a class of neural networks, PINNs (Physics-Informed Neural Networks), to inverse problems. The characteristic of PINNs is its prediction is guaranteed by the informed physical laws, initial, or boundary conditions, by forming the loss function as a combination of predictive and physical loss. Predictive loss is the difference between PINNs prediction and the ground truth, while physical loss is defined by how much PINNs prediction satisfies the physical laws and conditions. This paper investigates the effect of each loss and the performance improvement by introducing a weighting factor, and discusses PINNs applicability to parameter estimation with noised observation data.

Journal

• Journal of Japan Society of Civil Engineers, Ser. A2 (Applied Mechanics (AM))

  Journal of Japan Society of Civil Engineers, Ser. A2 (Applied Mechanics (AM)) 77 (2), I_35-I_45, 2021

  Japan Society of Civil Engineers

Keywords

• physics-informed neural networks
• data-driven science
• supervised learning
• deep learning

Details

• CRID: 1390572404763168768
• NII Article ID: 130008150542
• DOI: 10.2208/jscejam.77.2_i_35
• ISSN: 21854661
• Web Site: https://www.jstage.jst.go.jp/article/jscejam/77/2/77_I_35/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed