Physics-Based and Data-Driven Modeling Lab

Bureau of Economic Geology,

Jackson School of Geosciences

The University of Texas at Austin

University Station, Box X, Austin, TX  78712-8924

Phone: (512)-471-2243

Email: sahar.bakhshian@beg.utexas.edu

I am a Research Associate at the  Bureau of Economic Geology, Jackson School of Geosciences, The University of Texas at Austin. My research interests lie at the intersection of chemical engineering, environmental engineering, and geoscience. My primary research concerns the analytical and computational modeling of multi-physics problems as well as applying data science to leverage problems in geoscience and environmental context.

One of the main objectives of my recent research is to develop fast and robust algorithms through scalable parallel schemes to solve fluid dynamics with a particular focus on multiphase flow and transport in porous media. To this end, I have developed a physics-based pore-scale multiphase flow solver with high accuracy and plausible scalability, capable of handling direct fluid flow simulations in porous media with complex geometries. Exploiting parallel computing algorithms and high-performance computing (HPC) provides efficient handling of computationally intensive flow simulations.

On the data science side, my research targets developing deep learning algorithms applicable to environmental sensor data. I explore deep learning networks that are well-suited with detecting and predicting important events, trends, patterns, and anomaly in time-series data. With the availability of Internet of Things (IoT) technologies, it is possible to acquire the sensor data in real-time. Machine Learning and Deep Learning (DL) algorithms can then be used to predict the sensor performance, given enough historical data, and enables automated predictive maintenance.

Thank you for visiting my webpage. In case you are interested in having potential collaboration, please feel free to contact me.