I am a current Ph.D. candidate major in Chemical & Petroleum Engineering at the University of Kansas, and working in Dr.Barati’s research group while co-advising by Dr. Chi Zhang in Department of Geology, my current research focuses on pore-scale modeling and reactive transport core flood simulations, specifically, modeling the Low-salinity waterflooding enhanced oil recovery (EOR) in carbonates rock sample at pore scale, which includes multiphase fluid flow in porous media coupled with geochemical reactions. The final model would be the model integration of single/multi-phase flow in porous media, diffusion, electrodynamics and reactions, which will be used in evaluate the internal mechanism of Low-salinity waterflood and other complex processes within petroleum and geophysics research area.

I worked as a Ph.D. intern at Computational Earch Science Group at Oak Ridge National Laboratory (ORNL) from May 2019 to December 2019. My main focus during the internship is an ExaShed project funded by Department of Energy (DOE) BER program, specifically, using machine learning methods to build a robust and efficient predict model to simulate stream discharge in watershed. I am part of an interdisciplinary team developing a predictive model to advance understanding of watershed functions. I have been involved in multiple projects and multiple research groups related to earth science modeling and related AI applications development, including:

• Develop Bayesian Neural Network for uncertainty quantification on watershed data, the model was proved working more efficiently and robust, I will be presenting this work at 2019 ORNL AI EXPO, and writing conference proceedings as well as journal publications in the near future.

• Working with ORNL AI initiative to develop and apply the Stein Variational Policy Gradient (SVPG) algorithms on Reinforcement Learning problems.

• Develop and apply the Long-Short-Term-Memory (LSTM) deep learning algorithms to predict time series earth science data with uncertainty quantified.

Before Ph.D. study, I obtained my Master’s degree in Petroleum Engineering in same department at December 2017, with thesis entitled “Prediction of Capillary Pressure and Relative Permeability Curves using Conventional Pore-scale Displacements and Artificial Neural Networks”, which is mainly about the integration of the artificial neural networks and pore scale modeling.

I received another M.S. in geology and paleontology and B.S. in Geology and resource exploration engineering in Chang’an University before my studies at the University of Kansas.

Research interests

1. Data analytics for petroleum and reservoir engineering
2. Artificial intelligence and related engineering applications
3. Pore-scale modeling
4. Multiphase flow, reactive transport in porous media
5. Electrodynamics
6. Computational Fluid Dynamics (CFD)
7. Lattice Boltzmann Method (LBM)
8. High performance parallel scientific computing (MPI, CUDA)