DAS & ML Seismic Research Fellow

The Pennsylvania State University; Ferguson Township (PA); On-site; USD 90,000 - 160,000; Full time

Benefits offered by this job

Tuition discount 75%

Comprehensive benefits package

Strong retirement plans

Job summary

Penn State's Department of Geosciences seeks a Research Assistant Professor to advance machine-learning methods for seismic source characterization with distributed acoustic sensing (DAS). The role includes wavefield simulations, synthetic DAS data, deep learning for event detection and location, and moment-tensor estimation, plus publications and mentoring.

The appointment is a term position with renewal based on funding and performance; collaboration with university and national-laboratory

Qualifications

• Ph.D. in geophysics, seismology, applied mathematics, computer science, or related field by date of hire.
• Experience in DAS, seismic modeling, moment-tensor inversion, machine learning, scientific programming, and HPC highly desirable.

Responsibilities

• Conduct physics-based wavefield simulations and generate synthetic DAS datasets.
• Develop deep-learning models for seismic event detection, location, and full moment-tensor estimation.
• Validate methods using field observations from earthquakes and controlled-source experiments.
• Contribute to publications, project reports, and mentoring of students.

Skills

DAS

Seismic modeling

Moment-tensor inversion

Machine learning

Scientific programming

High-performance computing

Education

Ph.D. in geophysics / seismology / related field

Tools

DAS software

HPC

Job description

Penn State's Department of Geosciences seeks a Research Assistant Professor to advance machine-learning methods for seismic source characterization with distributed acoustic sensing (DAS). The role includes wavefield simulations, synthetic DAS data, deep learning for event detection and location, and moment-tensor estimation, plus publications and mentoring.

The appointment is a term position with renewal based on funding and performance; collaboration with university and national-laboratory