PeopleofSuperintelligence

Researcher

Karthik Kashinath

Karthik Kashinath is a principal engineer and scientist at NVIDIA who applies machine learning to weather and climate. A mechanical and aerospace engineer by training, he studied at the Indian Institute of Technology Madras, Stanford and Cambridge, then worked in the Data & Analytics Services Group at NERSC at Lawrence Berkeley National Laboratory, where he led the ClimateNet project on deep learning for extreme weather. He joined NVIDIA in August 2021, and NVIDIA launched its Earth-2 initiative in November 2021. In 2022 he was among the authors of the FourCastNet weather forecasting model, and ClimSim, a climate-emulation dataset he coauthored, received an Outstanding Paper award at NeurIPS 2023. He co-leads NVIDIA's Earth-2 initiative, which builds digital twins of the Earth for weather and climate.

Now at
NVIDIA

Timeline

  1. By 2018

    Engineering degrees and NERSC

    Trained as a mechanical and aerospace engineer, he earns a bachelor's degree at the Indian Institute of Technology Madras, a master's at Stanford University and a Ph.D. at the University of Cambridge. By 2018 he is a member of the Data & Analytics Services Group at NERSC, the National Energy Research Scientific Computing Center at Lawrence Berkeley National Laboratory.

  2. 2018–2021

    ClimateNet at Berkeley Lab

    He leads ClimateNet, a Berkeley Lab project that brings deep learning to weather and climate pattern detection through expert-labeled, community-sourced open datasets, and presents its poster at the American Geophysical Union meeting in December 2018. In 2019, he gives a talk on deep learning recognizing weather and climate patterns at the International Meeting on Statistical Climatology in Toulouse. The ClimateNet paper appears in Geoscientific Model Development in January 2021 with him as an author.

  3. 2021

    Joining NVIDIA for Earth-2

    He joins NVIDIA in August 2021 after leading climate informatics and machine-learning projects at the Big Data Center at NERSC. In November 2021, NVIDIA CEO Jensen Huang launches the Earth-2 initiative, a digital model of the Earth that combines AI, physical simulations and computer graphics, and he co-leads it.

  4. 2022

    The FourCastNet weather model

    In February 2022, he is among the authors of FourCastNet, a global data-driven weather forecasting model that provides short to medium-range predictions at 0.25° resolution. The model matches the forecasting accuracy of the ECMWF Integrated Forecasting System at short lead times for large-scale variables and generates a week-long forecast in less than 2 seconds.

  5. July 2023

    Earth-2 at the Berlin Summit

    In July 2023, he writes NVIDIA's blog post on Jensen Huang's keynote at the Berlin Summit for the Earth Virtualization Engines initiative. The post reports that the Earth-2 team, running FourCastNet in Modulus, generates a thousand different 21-day weather trajectories in one-tenth the time a single trajectory previously took.

  6. 2023

    A NeurIPS Outstanding Paper

    He is one of the authors of ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation, which receives an Outstanding Paper award at NeurIPS 2023. The dataset holds 5.7 billion pairs of multivariate input and output vectors from multi-scale climate simulations, built by a consortium of climate scientists and ML researchers.

  7. November 2025

    Faster CorrDiff downscaling

    In November 2025, he coauthors an NVIDIA technical blog post on CorrDiff, a generative AI downscaling model in the Earth-2 platform. Optimizations to CorrDiff training and inference, incorporated into NVIDIA PhysicsNeMo and Earth2Studio, achieve over a 50x speedup.

  8. As of October 2026

    Principal engineer on Earth-2

    He is a principal engineer and scientist in HPC+AI in Developer Technologies at NVIDIA and co-leads the NVIDIA Earth-2 Initiative. His work uses machine learning to emulate high-resolution weather and climate data, build digital twins, and provide actionable climate information.

Career

  1. NowNVIDIAPrincipal Engineer and Scientist
  2. Office of ScienceMember

Education

  1. IIT MadrasBachelor's degree
  2. Stanford UniversityMaster's degree
  3. University of CambridgePh.D.

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Karthik Kashinath. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. 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.
  3. 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.
  4. 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.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Presenter – Pasc Conference pasc24.pasc-conference.org. Checked 21 October 2026.
  2. ClimateNet Aims to Improve Machine Learning Applications in Climate Science On a Global Scale cs.lbl.gov. Checked 21 October 2026.
  3. Berkeley Lab Deep Learning Expertise Draws Attention at International Climatology Meeting cs-newsarchive.lbl.gov. Checked 21 October 2026.
  4. ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather gmd.copernicus.org. Checked 21 October 2026.
  5. Karthik Kashinath Author Page | NVIDIA Blog blogs.nvidia.com. Checked 21 October 2026.
  6. Mapping The Future: Predicting Climates with Dr. Karthik Kashinath thegadflymagazine.org. Checked 21 October 2026.
  7. FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators arxiv.org. Checked 21 October 2026.
  8. AI, Digital Twins to Unleash Next Wave of Climate Research Innovation blogs.nvidia.com. Checked 21 October 2026.
  9. NeurIPS 2023 Awards neurips.cc. Checked 21 October 2026.
  10. ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation proceedings.neurips.cc. Checked 21 October 2026.
  11. Gen AI Super-Resolution Accelerates Weather Prediction with Scalable, Low-Compute Models developer.nvidia.com. Checked 21 October 2026.
  12. Author: Karthik Kashinath | NVIDIA Technical Blog developer.nvidia.com. Checked 21 October 2026.