Physics informed machine learning: Seismic wave equation
Машинное обучение с учетом физических законов: уравнение сейсмической волны
2020-08-05
SCID: 54.1/jzndkmtn
Discuss with AI
Gaussian processesphysics-informed machine learningphysics-informed neural networksseismic wave equationwave velocity inversion
Figures from the paper
Abstract (AI)
Similar to many fields of sciences, recent deep learning advances have been applied extensively in geosciences for both small- and large-scale problems. However, the necessity of using large training data and the ‘black box’ nature of learning have limited them in practice and difficult to interpret. Furthermore, including the governing equations and physical facts in such methods is also another challenge, which entails either ignoring the physics or simplifying them using unrealistic data. To address such issues, physics informed machine learning methods have been developed which can integrate the governing physics law into the learning process. In this work, a 1-dimensional (1D) time-dependent seismic wave equation is considered and solved using two methods, namely Gaussian process (GP) and physics informed neural networks . We show that these meshless methods are trained by smaller amount of data and can predict the solution of the equation with even high accuracy. They are also capable of inverting any parameter involved in the governing equation such as wave velocity in our case. Results show that the GP can predict the solution of the seismic wave equation with a lower level of error, while our developed neural network is more accurate for velocity (P- and S-wave) and density inversion.
Key Findings
1
Both methods accurately predict seismic-wave solutions and can invert governing-equation parameters, including wave velocity.
2
Gaussian processes achieve lower solution-prediction error, whereas the developed neural network provides more accurate P-wave, S-wave, and density inversion.
3
Gaussian processes and physics-informed neural networks solve the one-dimensional time-dependent seismic wave equation using meshless formulations and relatively small training datasets.
4
Physics-informed machine learning integrates governing physics into seismic-wave modeling, addressing data requirements and black-box limitations of conventional deep learning.
5
The methods demonstrate that incorporating physical laws enables accurate seismic modeling without relying on large datasets or unrealistic physics simplifications.
Research Object
1-dimensional time-dependent seismic wave equation
Research Subject
Accurate solution prediction and inversion of governing parameters, particularly P- and S-wave velocity and density, using physics-informed machine learning
Publication Details
Publication Date
2020-08-05
Journal
Publisher
ISSN
Cited by
190
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest