PeopleofSuperintelligence

Researcher

Jerry Lin

Jerry Lin is a climate machine-learning researcher who tests how neural-network emulators behave when they run inside physics-based climate models. As a PhD candidate in Michael Pritchard's group at UC Irvine, he co-authored ClimSim, a dataset of 5.7 billion input-output pairs that won an Outstanding Paper award in the NeurIPS 2023 Datasets and Benchmarks track. In 2023 he was first author of "Navigating the Noise", a study of machine-learning design choices using ensembles on the order of 100 hybrid simulations; in 2024 he helped organize an ICML workshop on Machine Learning for Earth System Modeling and a $50,000 Kaggle competition associated with ClimSim. In 2025 he was first author of "Crowdsourcing the Frontier", which tested emulators inspired by the Kaggle winners inside an interactive climate model. He is a postdoctoral associate in Computing & Data Sciences at Boston University.

Timeline

  1. September 2020

    PhD candidate at UC Irvine

    In September 2020, he joins Michael Pritchard's Computational Clouds and Climate Lab at UC Irvine as a PhD candidate in the Department of Earth System Science.

  2. 2023

    ClimSim and a NeurIPS award

    He is among the authors of ClimSim, a dataset of 5.7 billion pairs of input and output vectors for hybrid physics-ML climate emulation. The paper wins an Outstanding Paper award in the Datasets and Benchmarks track at NeurIPS 2023.

  3. September 2023

    Ensembles of hybrid simulations

    In September 2023, he posts "Navigating the Noise" on arXiv as first author. The paper builds a pipeline for ensembles on the order of 100 hybrid climate simulations and shows that removing dropout and switching from a mean squared error to a mean absolute error loss have opposite effects on online error and online stability.

  4. 2024

    An ICML workshop and Kaggle contest

    In 2024, he conceives and co-organizes the Machine Learning for Earth System Modeling workshop at ICML in Vienna. He is also an organizer of the $50,000 Kaggle competition associated with the ClimSim dataset and an active maintainer of ClimSim.

  5. By 2025

    A JAMES study on emulators

    A study he leads with Michael Pritchard appears in the Journal of Advances in Modeling Earth Systems by 2025. It samples the coupled behavior of hybrid physics-ML emulators across thousands of climate simulations to assess which design decisions make hybrid climate models work reliably.

  6. November 2025

    Crowdsourcing the Frontier paper

    In November 2025, he is first author of "Crowdsourcing the Frontier", which reports downstream results of the Kaggle competition. Emulators inspired by the winning teams' architectures are coupled to an interactive climate model, and online stability proves reproducible across multiple diverse architectures.

  7. As of October 2026

    Postdoc at Boston University

    He is a postdoctoral associate in Computing & Data Sciences at Boston University. In May 2025, he plans the move to work under Elizabeth A. Barnes on interpretability tools in machine learning for climate research.

Career

  1. Since 2025Boston UniversityPostdoctoral associate

Education

  1. From 2020University of California, IrvinePhD candidate

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 Boston University. 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. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Boston University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Boston University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Boston University. 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.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

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

  1. Computational Clouds and Climate Lab sites.ps.uci.edu. Checked 21 October 2026.
  2. Earth System Science graduate student helping define the future of climate change modeling webapps.ps.uci.edu. Checked 21 October 2026.
  3. ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation proceedings.neurips.cc. Checked 21 October 2026.
  4. NeurIPS 2023 Outstanding Paper Awards neurips.cc. Checked 21 October 2026.
  5. Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles arxiv.org. Checked 21 October 2026.
  6. Machine Learning for Earth System Modeling: Organizers leap-stc.github.io. Checked 21 October 2026.
  7. Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a $50,000 Kaggle Competition arxiv.org. Checked 21 October 2026.
  8. Jerry Lin | Profiles RNS profiles.bu.edu. Checked 21 October 2026.