PeopleofSuperintelligence

Researcher

Jaideep Pathak

Jaideep Pathak is a senior research scientist at NVIDIA who builds machine learning models for weather and climate. As Edward Ott's physics graduate student at the University of Maryland, College Park, he was lead author of 2018 work that used reservoir computing to predict a chaotic system out to eight Lyapunov times. In 2022, he was first author of FourCastNet, a data-driven global weather model that produces a week-long forecast in less than 2 seconds. Later projects include spherical Fourier neural operators, the StormCast diffusion model, and the ClimSim climate dataset, which won an Outstanding Paper award at NeurIPS 2023. In January 2026, his Stormscope models began forecasting storms directly from satellite and radar observations.

Now at
NVIDIA

Timeline

  1. 2017

    A physics PhD at Maryland

    He studies for a PhD in physics at the University of Maryland, College Park, working on modeling chaotic dynamical systems with machine learning. In 2017, with Zhixin Lu, Brian Hunt, Michelle Girvan and Edward Ott, he coauthors a reservoir computing method that estimates the Lyapunov exponents of a chaotic process from data.

  2. 2018

    Reservoir computing predicts chaos

    As Edward Ott's graduate student, he is lead author of papers that train a reservoir computer on data from the Kuramoto-Sivashinsky equation, a test bed for spatiotemporal chaos. The 2018 PRL paper predicts the system out to eight Lyapunov times, and a hybrid with model-based prediction extends accurate forecasts to 12.

  3. 2022

    The FourCastNet weather model

    Before joining NVIDIA, he works on accelerating scientific models with deep learning and high-performance computing at NERSC, a division of Lawrence Berkeley National Laboratory. In February 2022, he is first author of FourCastNet, a global data-driven weather model at 0.25-degree resolution that generates a week-long forecast in less than 2 seconds.

  4. 2023

    Spherical Fourier neural operators

    In 2023, he coauthors Spherical Fourier Neural Operators, which adapt Fourier neural operators to the sphere and give stable atmospheric rollouts for a year of simulated time. He cowrites an NVIDIA Technical Blog post on the method in July 2023.

  5. 2023

    ClimSim wins at NeurIPS

    He is a coauthor of ClimSim, a dataset of 5.7 billion pairs of input and output vectors for hybrid physics and machine learning climate emulation. The paper receives an Outstanding Paper award at NeurIPS 2023.

  6. 2024

    The StormCast diffusion model

    In August 2024, he is first author of StormCast, a generative diffusion model that emulates NOAA's 3-kilometer HRRR convection-allowing model. It predicts 99 state variables at kilometer scale with a one-hour time step.

  7. January 2026

    Stormscope forecasts from observations

    In January 2026, he is first author of Stormscope, a family of transformer-based generative diffusion models trained on geostationary satellite imagery and ground-based radar over the continental United States. Its forecasts at 10-minute and 6-kilometer resolution compete with operational mesoscale weather models for lead times up to 6 hours.

  8. As of October 2026

    Senior research scientist at NVIDIA

    He is a senior research scientist at NVIDIA, focusing on large-scale machine learning for weather and climate modeling.

Career

  1. NowNVIDIASenior research scientist

Education

  1. University of MarylandPhD

From the biography.

  1. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  4. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes NVIDIA. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.

Sources and credits

Photo: We have no published photo of Jaideep Pathak yet. Send us a free-licensed photo.

  1. Author: Jaideep Pathak | NVIDIA Technical Blog developer.nvidia.com. Checked 21 October 2026.
  2. [1710.07313] Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data arxiv.org. Checked 21 October 2026.
  3. Machine Learning’s ‘Amazing’ Ability to Predict Chaos | Quanta Magazine quantamagazine.org. Checked 21 October 2026.
  4. [2202.11214] FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators arxiv.org. Checked 21 October 2026.
  5. [2306.03838] Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere arxiv.org. Checked 21 October 2026.
  6. Modeling Earth’s Atmosphere with Spherical Fourier Neural Operators | NVIDIA Technical Blog developer.nvidia.com. Checked 21 October 2026.
  7. NeurIPS 2023 Awards neurips.cc. Checked 21 October 2026.
  8. [2408.10958] Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling arxiv.org. Checked 21 October 2026.
  9. [2601.17268] Learning Accurate Storm-Scale Evolution from Observations arxiv.org. Checked 21 October 2026.