EURO 2025 Leeds
Abstract Submission

55. Model-driven and data-driven inverse problems and intelligent computing

Invited abstract in session MD-35: Nonlinear Optimization Algorithms and Applications: 3, stream Continuous and mixed-integer nonlinear programming: theory and algorithms.

Monday, 14:30-16:00
Room: Michael Sadler LG15

Authors (first author is the speaker)

1. Yanfei Wang
Institute of Geology and Geophysics, Chinese Academy of Sciences

Abstract

Model-driven geophysical inverse problems have played an important role in the field of resource and energy exploration. Taking oil & gas exploration as an example, the basic idea is to establish a geological model and use the model-driven inverse problem-solving method. Based on geophysical data such as seismic waves collected on the surface, the underground geological structure is inverted to accurately infer key information such as the location, thickness and reservoir characteristics of underground oil & gas layers, thereby guiding the rational layout of oil wells and the formulation of mining plans. In recent years, data-driven geophysical inversion and interpretation have attracted a great attention. The basic idea is to directly mine geological rules from the data itself. It can integrate data from different geophysical methods, improving the accuracy and reliability of inversion results. In the exploration of complex geological structures, through data-driven technologies such as machine learning, geological features can be automatically identified, providing more efficient and accurate interpretation results for geophysical applications such as resource exploration and geological disaster prediction. This research takes a special unconventional oil & gas-natural gas hydrate as an example to explore the geophysical inversion modeling and introduce deep-learning methods for interpretation. Finally, the discussion and outlook of this discipline field are presented.

Keywords

Status: accepted

Back to the list of papers