Post-doctoral Position in Machine Learning for Subsurface Multiscale Structure and Characterization including Permeability at the University of Pittsburgh

About the role

Join a cutting-edge three-year post-doctoral project funded by the United States Department of Energy Science-informed Machine Learning to Accelerate Real Time subsurface decision making (SMART) LDRD Prime initiative. The successful candidate will develop a breakthrough, laboratory-calibrated AI/ML tool that accurately estimates subsurface permeability from commonly collected geophysical well logs, addressing key challenges in subsurface characterization for energy resources, production efficiency, and recovery optimization.

This position involves collaboration with a multidisciplinary team and leveraging unique datasets from national laboratories.

Responsibilities

• Lead the construction of a fully attributed, machine learning-ready petrophysical database from existing NETL ultrasonic and core measurement archives.
• Develop, train, and deploy deep learning models, including convolutional neural networks (CNNs) and physics-informed neural networks (PINN), to predict rock permeability from ultrasonic acoustic measurements.
• Adapt and retrain existing deep learning frameworks (e.g., PhaseNet) to automate the picking of P and S wave arrivals from ultrasonic waveform data, enhancing speed and consistency.
• Develop and apply generative adversarial networks (GANs) to produce realistic synthetic core data, broadening training datasets for more robust AI/ML models.
• Integrate and validate developed models by applying them to existing wireline log data and potentially new core samples.
• Collaborate closely with NETL scientists and researchers in geophysics, geology, engineering, and computer science.
• Publish research findings in high-impact, peer-reviewed journals and present results at major scientific conferences.

Requirements

• Ph.D. in Geophysics, Geology, Petroleum Engineering, Computer Science, or a closely related field, completed within the last five years.
• United States citizenship.
• Demonstrated experience in applying machine learning or deep learning techniques to scientific problems.
• Proficiency in scientific programming with Python and experience with common ML/DL libraries (e.g., TensorFlow, PyTorch).
• Strong analytical and problem-solving skills.
• Excellent written and oral communication skills, with a demonstrated ability to work both independently and collaboratively.

Preferred Qualifications

• Experience working with geophysical, petrophysical, or well log datasets.
• A strong background in rock physics, acoustics, or seismic data analysis.
• Specific experience with advanced neural network architectures such as CNNs, PINNs, or GANs.
• A track record of scholarly achievement, including first-author publications in peer-reviewed journals.
• Familiarity with high-performance computing environments.

Assignment Category: Full-time regular