The U.S. Geological Survey invites applications to a Mendenhall research post-doctoral fellowship opportunity to apply machine learning techniques to earthquake forecasting. The goal of this opportunity is to develop machine-learning approaches to improve earthquake forecasting capabilities – namely, to better predict the rate, locations, and sizes of future earthquakes.
The confluence of newly available, modern high-resolution seismic catalogs – composed of millions of earthquake locations, times, and sizes – along with recent advances in supervised and unsupervised machine learning, particularly deep learning techniques, provide a unique opportunity to mine seismic catalogs for deeper levels of earthquake predictability than have previously been found. In their proposal, applicants should describe methods and architectures amenable to extracting relevant features from catalogs of earthquake times and locations, and to generating stochastic representations of future activity.
This post-doctoral opportunity is for recent graduates in computer science, geophysics, seismology, statistics, or related fields. The fellowship provides 2 years of salary and benefits, as well as funding to support the proposed research project.
More information on the opportunity (Mendenhall #22-36) is here: 22-36. Improving earthquake forecasting with machine learning | U.S. Geological Survey
Candidates are encouraged to contact the research advisors to discuss project ideas. Further information on Mendenhall fellowship qualifications is here: Qualifications | U.S. Geological Survey
Applications are due November 1, 2023. This is a remote job opportunity.