Serveh Kamrava

Assistant Professor

Being committed to solving problems related to earth, energy and environment, research in our group interfaces between Chemical, Environment, and Petroleum Engineering, mathematics and data science. An important strategy in moving toward less emission is improving the efficiency and lifetime of energy storage systems and ideally designing new energy storage systems with improved properties. For early prediction of flow and transport properties, different length, and time scales, as well as different physics across different scales, should be accounted for. In our group we will use machine learning and multiscale modeling methods for solving the above daunting problems. Our group will also focus on developing physics-guided machine learning methods that can integrate physical laws and available data at small- and large-scale systems. We will apply state of the art machine learning techniques to such systems. One objective is to discover the physics when large data is available, and the physical laws are not well known and the other is to find patterns in the data by integrating known physics into data-driven methods.

 

EDUCATION:

  • BS, Sahand University of Technology, Chemical Engineering
  • MS, Texas A&M University, Chemical Engineering
  • PhD, University of Southern California, Chemical Engineering

 

RESEARCH INTERESTS:

  • Machine Learning
  • Fluid Dynamics
  • Chemical Discovery
  • Energy Storage Systems
  • Complex Materials
  • Soft Matter

 

SELECTED PUBLICATIONS:

  • Kamrava, S., Im, J., De Barros, F., & Sahimi, M. (2021) Estimating Dispersion Coefficient in Flow Through Heterogeneous Porous Media by a Deep Convolutional Neural Network. Geophysical Research Letters, doi.org/10.1029/2021GL094443
  • Kamrava, S., Sahimi, M., & Tahmasebi, P. (2021). Simulating fluid flow in complex porous materials: Integrating the governing equations with deep-layered machines. Nature Computational Materials 7(1), 1-9. doi.org/10.1038/s41524-021-00598-2
  • Kamrava, S., Sahimi, M., & Tahmasebi, P. (2021). Physics- and image-based prediction of fluid flow in complex porous membranes and materials by deep learning. Journal of Membrane Science, 119050. doi.org/10.1016/j.memsci.2021.119050
  • Tahmasebi, P., Kamrava, S., Bai, T., & Sahimi, M. (2020). Machine Learning in Geo-and Environmental Sciences: From Small to Large Scale. Advances in Water Resources, 103619. doi.org/10.1016/j.advwatres.2020.103619
  • Kamrava, S., Sahimi, M., & Tahmasebi, P. (2020). Quantifying accuracy of stochastic methods of reconstructing complex materials by deep learning. Physical Review E, 101(4), 043301. doi.org/10.1103/PhysRevE.101.043301
  • Kamrava, S., Tahmasebi, P., & Sahimi, M. (2019). Linking morphology of porous media to their macroscopic permeability by deep learning. Transport in Porous Media: 1-22. doi.org/10.1007/s11242-019-01352-5
  • Kamrava, S., Tahmasebi, P., & Sahimi, M. (2019). Enhancing images of shale formations by a hybrid stochastic and deep learning algorithm. Neural Networks 118: 310-320. doi.org/10.1016/j.neunet.2019.07.009
 

OPEN POSITIONS:

There is an opening for two Ph.D. positions in my group.
Students with background and experience in machine learning and computational fluid dynamics are encouraged to apply. The prospective students need to have knowledge of Python programming language.
Please submit your application (CV and a brief explanation of your programming experience) to Dr. Kamrava (kamrava@mines.edu).
 
The start time will be Spring 2023.

Contact

Room 311 Marquez Hall
303-273-3966

kamrava@mines.edu