About
I’m a PhD candidate in Atmospheric and Oceanic Science at the University of Maryland, where I develop and apply machine-learning methods to better understand and predict Earth system variability. My research focuses on predictability across timescales—from subseasonal forecasting to longer-term climate variability and change—with interests in large-scale circulation, tropical variability, and extreme events, while emphasizing process-oriented understanding.
Across academic, public-sector, and applied research settings, I’ve worked on problems spanning subseasonal prediction, air quality, extreme events, renewable-energy forecasting, and climate risk. My work combines Earth system models, reanalyses, observations, and data-driven methods—including tree-based models, deep learning, explainable AI, and causal discovery—to study both sources of predictability and uncertainty.
I contribute to international efforts at the intersection of climate science and AI, including the WCRP Fresh Eyes on CMIP initiative and the AMS Committee on AI Applications to Environmental Science. I was also an ASP Graduate Visitor at US NSF NCAR, where I studied large-scale circulation changes and associated extremes. Broadly, I’m interested in using scientific insight and machine learning to tackle challenging questions of prediction and uncertainty in a complex and changing Earth system.
I earned a bachelor’s degree in engineering and a master’s degree in water resources 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.
Publications
- Furtado, J. C., Molina, M. J., Arcodia, M. C., Anderson, W., Beucler, T., Callahan, J. A., Ciasto, L., Gensini, V., L’Heureux, M., Pegion, K., Pérez-Carrasquilla, J. S., Sonnewald, M., Takahashi, K., Xiang, B., & Zimmerman, B. (2026). Setting the Standard: Recommended Practices for Data Preprocessing in Data-Driven Climate Prediction. Bulletin of the American Meteorological Society, BAMS-D-24-0292.1. Web access.
- Wichrowski, L., Pérez-Carrasquilla, J. S., & Molina, M. J. (2026). Weather regime diversity, transitions, and trends using hexagonal self-organizing maps. Journal of Geophysical Research: Atmospheres, 131(8), e2025JD044874. Web access.
- Pérez-Carrasquilla, J. S., Molina, M. J., Mayer, K. J., Dagon, K., Fasullo, J. T., & Simpson, I. R. (2025). Observed and modeled amplification of the frequency, duration, and extreme heat impacts of the Pacific trough regime. Earth’s Future, 13(12), e2025EF007140. Web access.
- Pérez-Carrasquilla, J. S., & Molina, M. J. (2025). An Earth-system-oriented view of the S2S predictability of North American weather regimes. Artificial Intelligence for the Earth Systems, 4(3), 240075. Web access.
- Molina, M. J., McGovern, A., Pérez-Carrasquilla, J. S., Li, X., & Tanamachi, R. L. (2025). Using Generative Artificial Intelligence Creatively in the Classroom and Research: Examples and Lessons Learned. Bulletin of the American Meteorological Society, 106(11), E2346–E2357. Web access.
- In press Katzenberger, A., Pérez-Carrasquilla, J. S., Gemmell, K., Galytska, E., Leclerc, C., P., P., Roy, I., Varuolo-Clarke, A., Tošić, M., & Črnivec, N. (2025). Developing Guidelines for Working with Multi-Model Ensembles in CMIP. Earth System Dynamics. Web access.
- Preprint Yang, A., Kadawedduwa, N., Wang, T., Sharma, S., Wisinski, E. F., Pérez-Carrasquilla, J. S., Hall, K. J., Calhoun, D., Starfeldt, J., Canty, T. P., & Molina, M. J. (2025). Reconstructing Tornadoes in 3D with Gaussian Splatting. arXiv preprint, arXiv:2506.18677. Web access.
- Chen, J., Yang, S., Fang, X., Lin, S., Pérez-Carrasquilla, J. S., Cai, F., Chen, W., & Wu, J. (2024). A novel index for depicting ENSO transition with application in ENSO–East Asian summer monsoon relationship. Environmental Research Letters, 19(12), 124066. Web access.
- Pérez-Carrasquilla, J. S., Montoya, P. A., Sánchez, J. M., Hernández, K. S., & Ramírez, M. (2023). Forecasting 24 h averaged PM2.5 concentration in the Aburrá Valley using tree-based machine learning models, global forecasts, and satellite information. Advances in Statistical Climatology, Meteorology and Oceanography, 9(2), 121–135. Web access.
- Conference proceeding Pérez-Carrasquilla, J. S., & Hoyos, C. D. (2021). Characterization of the Thermodynamics, Life Cycle and Influence Over the Mean Flow of Inner Core Processes in Tropical Cyclones: Observational and Idealized Modelling Approach. 34th Conference on Hurricanes and Tropical Meteorology. Web access.
- Master’s thesis Pérez-Carrasquilla, J. S. (2021). Intensificación rápida de ciclones tropicales: análisis de su variabilidad espacio-temporal y su respuesta a dinámicas del núcleo interno y forzamiento externo. Universidad Nacional de Colombia. Web access.
- Hoyos, C. D., Ceballos, L. I., Pérez-Carrasquilla, J. S., Sepúlveda, J., López-Zapata, S. M., Zuluaga, M. D., & Zapata, M. (2019). Meteorological conditions leading to the 2015 Salgar flash flood: lessons for vulnerable regions in tropical complex terrain. Natural Hazards and Earth System Sciences, 19(11), 2635–2665. Web access.
Selected experience
- Develop machine-learning methods to diagnose sources of subseasonal predictability in North American weather regimes.
- Analyze weather regime variability and long-term changes using reanalysis data, climate model output, and large ensembles.
- Studied changes in North American weather regimes and associated surface extremes using Earth system model ensembles.
- Developed machine-learning forecasts for meteorological, hydrological, energy-sector, and insurance-sector applications.
- Built automated hurricane risk reports using National Weather Service model output.
- 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
- 2026. Best Student Oral Presentation, American Meteorological Society’s 39th Conference on Climate Variability and Change.
- 2025. Atmospheric and Oceanic Science Prize for Publication Excellence, University of Maryland.
- 2025. Dr. Eugene Rasmusson Graduate Student Fellowship, The Graduate School, University of Maryland.
- 2025. Dr. Ann G. Wylie Dissertation Fellowship, The Graduate School, University of Maryland.
- 2025. Travel award for the Summer CESM Workshop, NSF NCAR.
- 2024. Dr. Richard Payne Graduate Fellowship, College of Computer, Mathematical and Natural Sciences, University of Maryland.
- 2024. Best Student Oral Presentation (2nd place), American Meteorological Society’s 23rd Conference on Artificial Intelligence for Environmental Science.
- 2024. US NSF NCAR Advanced Study Program Graduate Student Fellowship.
- 2022–Present. Exploratory Allocation on NSF NCAR High-Performance Computing systems.
- 2021. College of Computer, Mathematical, and Natural Sciences Dean’s Fellowship, University of Maryland.
- 2020. Facultad de Minas Scholarship, Universidad Nacional de Colombia.
Connect
Contact: jspecar@gmail.com; jhayron@umd.edu