CV

You can download my one-page resume as a PDF. My fuller CV is below.

Education

• B.A. in Applied Mathematics, University of California, Berkeley, 2018
• M.S. in Earth System Science, University of California, Irvine, 2022
• Ph.D in Earth System Science, University of California, Irvine, 2025

Work experience

• Postdoctoral Researcher at Boston University (Sep 2025 - Present)
  • Working with Libby Barnes on a new project.
• Graduate Research Assistant @ Computational Clouds and Climate Lab (Sep 2020 - July 2025)
  • Increased sampling of hybrid physics-ML climate simulations by an order-of-magnitude to investigate which design decisions are most conducive to stably accurate coupled behavior and out-of-distribution coupled generalization.
  • Core contributor to ClimSim, which won the equivalent of the best paper award for the NeurIPS Datasets and Benchmarks Track.
• Graduate Research Assistant @ Berkeley Lab (Jun 2024 - Aug 2024)
  • Worked on improving asset-level wind power forecasts in joint partnership with Vayuh.ai
• Public Utilities Regulatory Analyst @ California Public Utilities Commission (Jan - Aug 2020)
  • Conducted hazard rate analysis for utility infrastructure that formed part of CPUC’s counterproposal for Southern California Edison’s proposed energy rate hikes
• Intern @ California Public Utilities Commission (Summer 2017):
  • Created a flexible machine learning pipeline for predicting which customers would be most at risk of defaulting on utility bills
  • Co-led workshops to teach employees how to use R and take over projects I participated in after I left
  • Created standards for future data submission from California utilities
• National Bureau of Economic Research funded Research Assistant (Summer 2016)
  • Created a database of lawyers and law firms specializing in disability insurance with web scraping tools created in R

Publications

Run It Back: Autoregression vs. Video Diffusion for End-Conditioned Weather Trajectories

Lin, J., and Barnes, E. A. (2026). Run It Back: Autoregression vs. Video Diffusion for End-Conditioned Weather Trajectories. NeurIPS 2026 Workshop on Tackling Climate Change with Machine Learning. Accepted, peer reviewed.

Signoff: Bringing Human Accountability Back to Agent-Powered Research

Lin, J., and Barnes, E. A. (2026). Signoff: Bringing Human Accountability Back to Agent-Powered Research. Bay Area Machine Learning Symposium (BayLearn). Accepted symposium paper, peer reviewed.

Extremes on Rewind: Generating 1,000-Member Ensembles Initialized at a Final Condition Permalink

Lin, J., Chien, M.-T., Sakarvadia, M., and Barnes, E. A. (2026). Extremes on Rewind: Generating 1,000-Member Ensembles Initialized at a Final Condition. arXiv:2608.19008. Preprint, under review.

Data-driven integration kernels for interpretable nonlocal operator learning Permalink

Ferretti, S. L., Lin, J., Shamekh, S., Baldwin, J. W., Pritchard, M. S., and Beucler, T. (2026). Data-driven integration kernels for interpretable nonlocal operator learning. Environmental Data Science, 5, e31.

Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a $50,000 Kaggle Competition Permalink

Lin, J., Hu, Z., Beucler, T., Frields, K., Christensen, H., Hannah, W., et al. (2026). Crowdsourcing the frontier: Advancing hybrid physics-ML climate simulation via a $50,000 Kaggle competition. Journal of Advances in Modeling Earth Systems, 18, e2025MS005643.

ClimSim-Online: A Large Multi-Scale Dataset and Framework for Hybrid Physics-ML Climate Emulation Permalink

Published in Journal of Machine Learning Research (JMLR), 2025

Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations Permalink

Published in Journal of Advances in Modeling Earth Systems (JAMES), 2025

Navigating the Noise: Bringing Clarity to ML Parameterization with O(100) Ensembles Permalink

Published in Journal of Advances in Modeling Earth Systems (JAMES), 2025

Climate-invariant machine learning Permalink

Published in Science Advances, 2024

Stress-testing the coupled behavior of hybrid physics-machine learning climate simulations on an unseen, warmer climate Permalink

Published in NeurIPS 2023 Climate Change AI Workshop, 2023

ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation Permalink

Published in NeurIPS 2023 Datasets and Benchmarks Track, 2023

Teaching

• ESS 118: Programming for Environmental Science (Spring 2023 TA)
• ESS 116: Introduction to Data Analysis (Fall 2022 TA)
• ESS 17: Catastrophes (Spring 2022 TA)
• ESS 17: Catastrophes (Fall 2021 TA)

Service and leadership

• Ran a $50,000 Kaggle competition on the ClimSim dataset
• Co-organized a Machine Learning for Earth System Modeling (ML4ESM) Workshop at ICML in 2024
• Core contributor and maintainer to ClimSim’s GitHub repo (May 2023 - Present)
• Professional Development Lead for the Earth System Science Department (Fall 2023 - Present)
• Learning the Earth with Artificial Intelligence and Physics (LEAP) Parameterization Focus Group Lead (Jan 2023 - May 2023)
• Managed a student-run data science course for the Data Science Society at UC Berkeley from Aug 2017 to Dec 2018.

Awards

• Excellence in Leadership Award (Earth System Science Department 2023)

Other

Was briefly interested in devising a voting strategy that took the best parts of plurality and approval voting and generalized them as a “First Choice Weighted Approval Voting System,” and I wrote a preprint of the work with my good friend Peter Butler, which can be found here.