Peetak Mitra, Ph.D.
Welcome to my website!
I am a founding scientist at Excarta, a venture-backed, Silicon Valley based startup. At Excarta, our mission is to help make businesses resilient to volatile weather, a consequence of a rapidly warming planet. Read more about us and the quality of our forecasting products on our website.
Before joining the founding team at Excarta, I was a Member of Research Staff/ Research Scientist at the fabled Silicon Valley R&D company Palo Alto Research Center, formerly Xerox PARC. The focus of my work at PARC was in developing Scientific Machine Learning tools and models for various applications including climate, energy, prognostics and personalized healthcare. The work was funded by generous grants from Xerox, DARPA, NASA among other funding agencies.
I earned my Ph.D. from the University of Massachusetts Amherst in June 2021. At UMass, I worked in the area of Machine Learning and predictive fluid modeling and I was advised by David Paul Schmidt. I completed part of my dissertation research at the Los Alamos National Laboratory, where I worked on developing machine learning frameworks to model geophysical turbulence processes, a critical driver of energy exchange in the oceans and atmosphere. I spent the summer of 2020 working (remotely) with TOTAL S.A. R&D, in developing scalable Machine Learning codes using TensorFlow and PyTorch.
The other major thrust of my research during my PhD was within the ICEnet Consortium, an industry-funded data-driven consortium that I co-founded with my doctoral advisor Prof. David P. Schmidt. ICEnet leverages the power of Artificial Intelligence (AI) to develop predictive machine learning algorithms to improve engine design, helping create fuel-efficient engines capable of meeting stricter environmental regulations. Among the partners for ICEnet include leading engine CFD software makers/users such as SIEMENS-CD/Adapco, Cummins, Convergent Science and AVL as well as NVIDIA and MathWorks.
For my early Ph.D. research I worked on developing reduced order models (ROM) for advanced propulsion systems, working in close collaboration with U.S. Department of Energy national laboratories - Argonne National Laboratory and Sandia National Laboratories, in a $2.1 million industry funded project, Spray Combustion Consortium. Models that I have developed have been implemented within commercial software code Converge CFD, and is in use by major automotive engine makers from around the world.
Apart from my research, I was a part of the core-team at Climate Change AI, a volunteer network that catalyzes impactful work at the intersection of machine learning and climate change and until very recently led the monthly newsletters. I co-organized and led workshops at major conferences and events including at NeurIPS 2022, AAAI Fall Symposium 2022 and ICLR 2020.
I serve on the advisory board of the Big Data program at Cal State University - East Bay. I have regularly served as a reviewer for prestigious machine learning journals and conferences such as Nat. Machine Intelligence, and NeurIPS, among others.
Recent News:
Invited Talk: at Oklahoma State University on Scientific Machine Learning and its Industrial Applications.
Paper: AI-enabled climate projections accepted to AAAI Spring Symposium as a contributed talk.
Excarta releases its MVP! More on our website.
Excarta raises preseed from Ubiquity Ventures! [October 2022]
Paper: Transformer work on climate projections, accepted at NeurIPS 2022 workshop (ML4PS).
Talk(s): One at American Physical Society (APS) DFD 2022 conference and 8 abstracts including 4 talks accepted at American Geophysical Union (AGU) conference.
Invited Talk: OpenAI hackathon on climate change. Date: 10/31.
Invited Talk: at the "Machine Learning for Weather and Climate" organized by IMSI, University of Chicago, 10/31 - 11/03
Paper: published in Physics of Fluids, "Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow", October 2022
Invited talk at MIT CLEPS workshop on AI and climate change, 10/06-10/10
Invited talk at the Monterey Data Conference, 08/30
Paper published in International Journal of Multiphase Flow, "The Eulerian Lagrangian Mixing-Oriented (ELMO) Model"
Interview with the Data Stand Up podcast
Paper published in Energies, "Acceleration of Chemical Kinetics Computation with the Learned Intelligent Tabulation (LIT) Method"
Invited talk at 16th U.S. National Congress on Computational Mechanics, 7/21.
Talk on using Coarse Graining for Fluid flow modeling accepted at NVIDIA-GTC 2022, will be available 4/21.
Presented talk at SIAM CSE 2021: Learning Operators from Data Symposium 2021, Dallas, TX, 'Non-Intrusive Machine Learning Models for Fluid Simulations'