Jhayron S. Pérez-Carrasquilla

Postdoctoral Scholar, UChicago Data Science Institute | UChicago–Argonne Joint Appointment Program | AICE: AI for Climate | Earth System Prediction & Machine Learning

I develop and apply machine learning to improve subseasonal-to-seasonal forecasts and understand the physical processes that shape predictability and uncertainty.

Email Google Scholar GitHub ORCID LinkedIn

About

I am a Postdoctoral Scholar at the UChicago Data Science Institute and Argonne National Laboratory through the UChicago–Argonne Joint Appointment Program, and a member of the AI for Climate Initiative. I develop and apply machine learning to improve Earth system prediction, with an emphasis on subseasonal-to-seasonal forecasts and the physical processes that shape predictability and uncertainty.

I completed my PhD in Atmospheric and Oceanic Science at the University of Maryland, where I studied the precursors, predictability, and long-term trends of North American weather regimes and associated extremes. My research combines Earth system models, reanalyses, and observations with approaches including deep learning, explainable AI, and causal discovery.

A central part of my work is developing data-driven methods to trace how causal influences evolve across space and time before high-impact events. In TraCE-ST, we introduce a probabilistic Lagrangian framework that reconstructs event-conditioned causal trajectories, helping identify drivers of Earth system extremes and generate testable physical hypotheses.

My earlier work spans tropical cyclones, extreme precipitation, air quality, hydrology, and renewable-energy forecasting. I also hold master’s and bachelor’s degrees from the Universidad Nacional de Colombia. Outside research, I enjoy sports, music, movies, and reading.

Research

Predictability across timescales

I study the sources and limits of atmospheric predictability, especially for North American weather regimes at subseasonal-to-seasonal lead times. This work uses machine learning, Earth system reanalyses, and coupled model output to diagnose when and why useful forecast information emerges.

Large-scale circulation and extremes

I analyze how large-scale circulation patterns vary across observations and models, how they shape extreme heat and other impacts, and how their behavior may change in a warming climate.

Causal and interpretable machine learning

I use explainable AI and causal discovery methods to connect predictive models with physical interpretation, including work on dynamical precursors of extreme events from gridded Earth system data.

Applied forecasting experience

Before and alongside my PhD, I worked on applied forecasting problems involving air quality, streamflow, meteorological variables, renewable-energy resources, and hurricane risk products for public and private-sector decision-making.

Subseasonal prediction Weather regimes Extreme events Machine learning Causal discovery Large ensembles Reanalysis Satellite and radar data

Publications

Selected experience

Postdoctoral Scholar
UChicago Data Science Institute, AICE: AI for Climate Initiative | Chicago, IL | 2026–Present
  • Developing interpretable generative AI frameworks for subseasonal-to-seasonal forecasting of extreme events.
  • Working on uncertainty quantification and reduction in regional climate projections.
PhD, Atmospheric and Oceanic Science
University of Maryland, Department of Atmospheric and Oceanic Science | 2022–2026
  • Developed machine-learning methods to diagnose sources of subseasonal predictability in North American weather regimes.
  • Analyzed weather regime variability and long-term changes using reanalysis data, climate model output, and large ensembles.
ASP Graduate Visitor
US NSF National Center for Atmospheric Research | Boulder, CO | 2024
  • Studied changes in North American weather regimes and associated surface extremes using Earth system model ensembles.
Research Scientist and Software Developer
Corporación Clima S.A.S. | Medellín, Colombia | 2020–2021
  • Developed machine-learning forecasts for meteorological, hydrological, energy-sector, and insurance-sector applications.
  • Built automated hurricane risk reports using National Weather Service model output.
Research Scientist
SIATA Early Warning System of the Aburrá Valley | Medellín, Colombia | 2018–2021
  • Developed machine-learning forecasts of air quality and analyzed drivers of convection and poor air quality.
  • Led atmospheric sampling campaigns and communicated scientific results with public-sector and community stakeholders.

Awards and honors

Connect

Contact: jhayron@uchicago.edu