Some AI methods and their applications
Artificial Intelligence (AI) methods have been widely applied in various fields. This course primarily introduces AI methods related to deep learning and large language model (LLM), as well as their applications in geophysics. We first introduce some approaches based on the latest papers, and then introduce their applications in geophysics, including background knowledge, methods and numerical examples. In addition, during this semester's course, the lecturer will also discuss the solutions to some scientific issues provided by LLM tools. There will be interactive time in each class, and all attendees are welcome to ask questions and communicate with each other.
Lecturer
Date
31st March ~ 23rd June, 2026
Location
| Weekday | Time | Venue | Online | ID | Password |
|---|---|---|---|---|---|
| Tuesday | 13:30 - 16:55 | A3-1-301 | ZOOM 09 | 230 432 7880 | BIMSA |
Prerequisite
Basic knowledge on deep learning methods, seismic rock physics, and the Python language.
Syllabus
1. Introduction to neural network (NN)-based approaches, discussion on current mainstream topics
The Latest Updates on Some Approaches:
2. Physics-informed neural networks (PINNs)
3. Physics-informed Kolmogorov-Arnold networks (PIKANs)
4. Neural operators (NOs)
Transformer-based LLMs:
5. Introduction to Transformer Models
6. Some complex neural network architectures
7. Application in partial differential equations (PDEs) discovery
8. Application in solving parameterized PDEs
The Application in Geophysics Problems:
9. AI-based inversion methods and applications in parameter inversion
10. Establishment of dynamic equations for seismic rock physics
11. Application of AI methods in computational geophysics
12. Some review literatures, Communication, and Interaction
The Latest Updates on Some Approaches:
2. Physics-informed neural networks (PINNs)
3. Physics-informed Kolmogorov-Arnold networks (PIKANs)
4. Neural operators (NOs)
Transformer-based LLMs:
5. Introduction to Transformer Models
6. Some complex neural network architectures
7. Application in partial differential equations (PDEs) discovery
8. Application in solving parameterized PDEs
The Application in Geophysics Problems:
9. AI-based inversion methods and applications in parameter inversion
10. Establishment of dynamic equations for seismic rock physics
11. Application of AI methods in computational geophysics
12. Some review literatures, Communication, and Interaction
Reference
1. The latest published papers related to deep learning methods, as well as some important papers from previous courses.
2. Textbooks related to the Transformer model.
3. The discussion results provided by LLM-based tools, and some notes summarized from papers.
2. Textbooks related to the Transformer model.
3. The discussion results provided by LLM-based tools, and some notes summarized from papers.
Audience
Graduate
, Postdoc
, Researcher
Video Public
No
Notes Public
No
Language
Chinese
Lecturer Intro
Fansheng Xiong (熊繁升) is currently an Assistant Professor of BIMSA. Before that, he received his doctoral degree in 2020 from Tsinghua University, and he was a visiting research assistant at Yale University during 2018-2019. His research interest mainly focuses on solving forward/inverse problems of PDEs based on AI methods, and their application in geophysics (especially seismic rock physics) and computational mathematics. He is PI for grant from National Natural Science Foundation of China, and he has published papers in journals like Journal of Geophysical Research-Solid Earth, Geophysical Journal International, and Geophysics.