BIMSA >
BIMSA Digital Economy Lab Seminar
Seismic wave propagation modeling and parameter inversion using machine learning assisted approaches
Seismic wave propagation modeling and parameter inversion using machine learning assisted approaches
演讲者
时间
2025年10月24日 15:00 至 16:00
地点
A3-2-303
线上
Zoom 435 529 7909
(BIMSA)
摘要
Currently, “AI for Science” is driving a paradigm shift in scientific community, which has significantly impacted the study of forward and inverse problems in exploration geophysics. The main content of this talk is as follows: First, it introduces a model establishing approach that build a framework based on existing knowledge and then predicts unknown factors using machine learning. Next, it presents examples of establishing wave propagation equations and the simplification assisted by machine learning, and the effectiveness of the approach is preliminarily validated by experimental and logging data. Finally, it demonstrates the application in reservoir parameter inversion and joint seismic-resistivity parameter inversion. The approaches and examples discussed in this talk aim to make meaningful explorations into key issues in exploration geophysics.
演讲者介绍
熊繁升，现任北京雁栖湖应用数学研究院助理研究员，曾任北京应用物理与计算数学研究所所聘博士后。先后毕业于中国地质大学(北京)、清华大学，美国耶鲁大学联合培养博士。研究兴趣主要集中于基于机器学习算法(DNN、PINN、DeepONet等)求解微分方程模型正/反问题及其在地球物理波传播问题中的应用，相关成果发表在JGR Solid Earth、GJI、Geophysics等期刊上。