I am currently pursuing my Ph.D. in the Department of Computational Mathematics Science and Engineering (CMSE) at Michigan State University, under the guidance of Prof. Songqiao “Shawn” Wei and Prof. Min Chen.
My research is focused on exploring machine learning and high-performance computing techniques, particularly in the context of computational seismic imaging. I’m also interested in how machine learning can be applied to solve other geophysical problems. As part of my research, I’ve developed a high-frequency full waveform inversion (FWI) model for the East Asia and Western Pacific subduction zones (EARA2023, currently under review at GJI).
In addition, I’ve created an advanced seismic arrival time detection system using deep neural networks in the spectrogram domain. This system employs the latest image segmentation approaches (PhaseNet-TF). I have also worked on an end-to-end machine learning workflow to detect minor earthquakes in the Tonga subduction zone, using seismic waveforms recorded by both land-based stations and ocean bottom seismometers (OBSs) (Deep learning for deep earthquakes, insight from Tonga subduction zone, currently under review at GJI).
I’m an active participant in open-source development, and I enjoy working with Python, Go, C/C++, and TypeScript. I’m also interested in Cloud Computing, and I’m currently working on a project to migrate my workflow to the cloud, supported by the MSU Cloud Computing Fellowship. This project involves using advanced tools like Kubeflow on Azure.
Experience