Shengxian Liang

Title: Innovations of Shengxian Liang in Machine Learning and Density Interface Inversion

Introduction

Shengxian Liang is a prominent inventor based in Chengdu, China. He has made significant contributions to the field of machine learning, particularly in the area of density interface inversion methods. His innovative approach combines advanced computational techniques with practical applications in geophysics.

Latest Patents

Shengxian Liang holds a patent for a "Density abrupt interface inversion method and system based on machine learning constraints." This patent discloses a hybrid density abrupt interface inversion method that utilizes machine learning constraints. The method involves constructing an initial basin interface and generating a disturbed basin interface data set. It further includes obtaining a basin interface data set through Hadamard product operations, creating a high-resolution density interface model data set, and optimizing a migration model-based deep learning network. The process culminates in the construction of a stable nonlinear loss function for regularization inversion, resulting in a high-resolution density interface model.

Career Highlights

Shengxian Liang is affiliated with Chengdu University of Technology, where he continues to advance research in his field. His work has garnered attention for its innovative use of machine learning in solving complex geophysical problems. With a focus on practical applications, Liang's contributions are paving the way for new methodologies in density interface inversion.

Collaborations

Shengxian Liang has collaborated with notable colleagues, including Jun Li and Zhengwei Xu. Their joint efforts have further enhanced the research output and innovation in their respective fields.

Conclusion

Shengxian Liang's work exemplifies the intersection of machine learning and geophysical research. His innovative patent and ongoing contributions to the field highlight the importance of interdisciplinary approaches in solving complex scientific challenges.