Blaine

SeisML

Research Practicum Advised by Suzan van der Lee

The main goal of this project, which fulfilled a practicum requirement for my MS in AI, was to explored a project structure that allowed for rapid experimentation, with hyperparameter reporting. The codebase I was originally working

A reproduction and generalization of the paper Automating the Detection of Dynamically Triggered Earthquakes via a Deep Metric Learning Algorithm. The goal was to extend the research the research to dynamically triggered tremors. In addition, explored new experiments using the dataset introduced Generalized Seismic Phase Detection with Deep Learning and unsupervised deep clustering with data from SEIS, a seismic instrument deployed as part of the InSight Mars lander, in an attempt to automate Martian seismic event classification.

Developing a baseline phase detection experiment using work and data from the paper Generalized Seismic Phase Detection with Deep Learning. • Experimented with unsupervised deep clustering with data from SEIS, a seismic instrument deployed as part of the InSight Mars lander, in an attempt to automate Martian seismic event classification.

View the code on GitHub