Xinming Wu

Title: Innovations of Inventor Xinming Wu

Introduction

Xinming Wu is a notable inventor based in Hefei, China. He has made significant contributions to the field of geological modeling and machine learning. With a total of 2 patents, his work focuses on advanced methods for analyzing geological structures using deep learning techniques.

Latest Patents

One of his latest patents is titled "Method of modeling interactive intelligent three-dimensional implicit structure based on deep learning." This innovative method involves generating multiple geological simulation structural models through data simulation technology. It constructs a geological simulation structural model library that features diversified folds and fault characteristics. The process includes acquiring geological fault data and unevenly distributed geological horizon data to create a training sample data set. A neural network is then trained using this data set, allowing for the input of multi-source heterogeneous data from a target region to output a corresponding geological structural model.

Another significant patent is "Using synthetic data sets to train a neural network for three-dimensional seismic fault segmentation." This machine learning system efficiently detects faults from three-dimensional seismic images, treating fault detection as a binary segmentation problem. To address the heavily biased distribution of fault and non-fault samples, a balanced loss function is utilized to optimize model parameters. The system is trained using selected pairs of 3D synthetic seismic and fault volumes, which are automatically generated by introducing folding, faulting, and noise. Remarkably, this machine learning system can accurately detect faults from 3D field seismic volumes acquired from different surveys.

Career Highlights

Xinming Wu has worked with prestigious institutions, including the University of Texas System and the University of Science and Technology of China. His experience in these organizations has contributed to his expertise in geological modeling and machine learning applications.

Collaborations

Throughout his career, Xinming Wu has collaborated with notable professionals such as Sergey Fomel and Yunzhi Shi. These collaborations have further enhanced his research and development efforts in the field.

Conclusion

Xinming Wu's innovative patents and contributions to geological modeling and machine learning demonstrate his significant impact in the field. His work continues to advance the understanding and analysis of geological structures through cutting-edge technology.