Earth Scientist
Earth Scientist


Maruti K. Mudunuru, PhD, is an Earth scientist at Pacific Northwest National Laboratory specializing in artificial intelligence (AI) and machine learning (ML) for subsurface science. He uses Department of Energy (DOE) codes such as PFLOTRAN and informatic tools such as JupyterHub to conduct predictive simulations, data analysis, and modeling for environmental remediation, carbon dioxide storage, and geothermal energy. He also applies PFLOTRAN to the Molecular Observation Network (MONet) datasets developed at the Environmental Molecular Sciences Laboratory, a DOE Office of Science user facility.

His AI/ML research has been highlighted by HPCwire and the Albuquerque Journal newspaper. Mudunuru is also a developer of the GeoThermalCloud, an open-source AI/ML framework for geothermal energy development.

Research Interest

  • Reactive transport, geothermal energy, unconventional oil and gas, geological carbon and hydrogen storage, watershed hydrology.
  • Data processing at sensor (edge computing), Internet of Things (IoT), predictive and sensor analytics, automation using AI/ML.
  • Physics-informed ML, deep learning, structure-preserving methods, multiscale finite element and finite volume methods.
  • Additive manufacturing, computational material science, joint inversion, high-performance computing, cloud computing, scalable data analytics.


  • PhD, civil engineering, University of Houston
  • MS, mechanical engineering, Texas A&M University
  • BS, civil engineering, Indian Institute of Technology Madras

Awards and Recognitions

  • University of Houston, best dissertation award, 2015.
  • International Association of Computational Mechanics and Elsevier, 2016 Robert J. Melosh Medal for the best paper in fundamental research in finite element analysis.
  • R&D 100 Award (Information Technologies Category) and R&D 100 Bronze Medal (Market Disruptor in Services Category), member of the Los Alamos National Laboratory SmartTensors AI Platform team, 2021.


  • Published three patents (US Patent Nos. 11,293,279; 16/948,851; 17/116,163) with Los Alamos National Laboratory and with Chevron, which are currently used in the energy industry.
  • Co-developer of the GeoThermalCloud.


PNNL Publications


  • Mudunuru M., B. Ahmmed, E. Rau, V.V. Vesselinov, and S. Karra. 2023. "Machine Learning for Geothermal Resource Exploration in the Tularosa Basin, New Mexico." Energies 16, no. 7:Art. No. 3098. PNNL-SA-181184. doi:10.3390/en16073098
  • Mudunuru M., B. Ahmmed, L. Frash, and R.M. Frijhoff. 2023. "Deep Learning for Modeling Enhanced Geothermal Systems." In Proceedings of the 48th Workshop on Geothermal Reservoir Engineering, February 6-8, 2023, Stanford, CA, Paper No. SGP-TR-224. Stanford, California:Stanford University. PNNL-SA-181520.
  • Talsma C.J., K. Solander, M. Mudunuru, B.M. Crawford, and M.R. Powell. 2023. "Frost Prediction using Machine Learning and Deep Neural Network Models." Frontiers in Artificial Intelligence 5. PNNL-SA-180159. doi:10.3389/frai.2022.963781.


  • Hills D.J., J. Damerow, B. Ahmmed, N.K. Catolico, S. Chakraborty, C.M. Coward, and R. Crystal-Ornelas, et al. 2022. "Earth and Space Science Informatics Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science." Earth and Space Science 9, no. 4:Art. No. e2021EA002108. PNNL-SA-167274. doi:10.1029/2021ea002108
  • Jagtap N.V., M. Mudunuru, and K.B. Nakshatrala. 2022. "A deep learning modeling framework to capture mixing patterns in reactive-transport systems." Communications in Computational Physics 31, no. 1:188-223. PNNL-SA-159450. doi:10.4208/cicp.OA-2021-0088
  • Mudunuru M., E. Cromwell, H. Wang, and X. Chen. 2022. "Deep Learning to Estimate Permeability using Geophysical Data." Advances in Water Resources 167. PNNL-SA-175440. doi:10.1016/j.advwatres.2022.104272
  • Mudunuru M., K. Son, P. Jiang, G.E. Hammond, and X. Chen. 2022. "Scalable Deep Learning for Watershed Model Calibration." Frontiers in Earth Science 10. PNNL-SA-176859. doi:10.3389/feart.2022.1026479
  • Mudunuru M., V.V. Vesselinov, and B. Ahmmed. 2022. "GeoThermalCloud: Machine Learning for Geothermal Resource Exploration." Journal of Machine Learning for Modeling and Computing 3, no. 4:57-72. PNNL-SA-178322. doi:10.1615/JMachLearnModelComput.2022046445
  • Vesselinov V.V., B. Ahmmed, M. Mudunuru, J.D. Pepin, E.R. Burns, D.L. Siler, and S. Karra, et al. 2022. "Discovering Hidden Geothermal Signatures using Non-Negative Matrix Factorization with Customized k-means Clustering." Geothermics 106. PNNL-SA-167650. doi:10.1016/j.geothermics.2022.102576


  • Ahmmed B., M. Mudunuru, S. Karra, S.C. James, and V.V. Vesselinov. 2021. "A Comparative Study of Machine Learning Models for Predicting the State of Reactive Mixing." Journal of Computational Physics 432. PNNL-SA-157340. doi:10.1016/
  • Ahmmed B., S. Karra, V.V. Vesselinov, and M. Mudunuru. 2021. "Machine Learning to Discover Mineral Trapping Signatures due to CO2 Injection." International Journal of Greenhouse Gas Control 109. PNNL-SA-158891. doi:10.1016/j.ijggc.2021.103382
  • Mudunuru M., and S. Karra. 2021. "Physics-Informed Machine Learning Models for Predicting the Progress of Reactive-Mixing." Computer Methods in Applied Mechanics and Engineering 374. PNNL-SA-157344. doi:10.1016/j.cma.2020.113560
  • Siler D.L., J.D. Pepin, V.V. Vesselinov, M. Mudunuru, and B. Ahmmed. 2021. "Machine learning to identify geologic factors associated with production in geothermal fields: A case-study using 3D geologic data, Brady geothermal field, Nevada." Geothermal Energy 9, no. 1:Article No. 17. PNNL-SA-158884. doi:10.1186/s40517-021-00199-8
  • Srinivasan S., D. O'Malley, M. Mudunuru, M. Sweeney, J.D. Hyman, S. Karra, and L. Frash, et al. 2021. "A machine learning framework for rapid forecasting and history matching in unconventional reservoirs." Scientific Reports 11, no. 1:Ar. No. 21730. PNNL-SA-159040. doi:10.1038/s41598-021-01023-w


  • Ahmmed B., M. Mudunuru, S. Karra, S.C. James, H. Viswanathan, and J. Dunbar. 2020. "PFLOTRAN-SIP: A PFLOTRAN Module for Simulating Spectral-induced Polarization of Electrical Impedance Data." Energies 13, no. 24:6552. PNNL-SA-157259. doi:10.3390/en13246552