Noemi Vergopolan

Noemi Vergopolan

Computational Hydrology

Princeton University

About Me

I am a computational hydrologist, engineer, and scientist working on solutions for water resources and climate. My research aims to aid actionable decision-making by improving hydrological information for monitoring and forecasting hydrological extremes and their impacts at the local scales. To this end, I develop scalable computational approaches for high-resolution hydrological prediction by leveraging advances in satellite remote sensing, land surface modeling, machine learning, data fusion, and high-performance computing.

Currently, I am working on satellite land data assimilation for Earth System Models as a researcher in the Atmospheric and Ocean Science Program at Princeton University and visiting research scientist at the NOAA Geophysical Fluid Dynamics Laboratory. Prior, I worked on water resources and environmental engineering consulting. I hold a M.A. and Ph.D. in Civil and Environmental Engineering from Princeton University.

For my contribution to science, I was awarded the 2022 Paul F. Boulos Excellence in Computational Hydrology Award by the American Academy of Environmental Engineers and Scientists and the 2022 AGU Science for Solutions Award for “outstanding contributions to water and food security through advances in hyper-resolution land surface modeling and satellite remote sensing”.

Learn more about my interests in research and publications, and by following my updates on Twitter.

  • Hydrology
  • Agriculture
  • Floods and Droughts
  • Satellite Remote Sensing
  • Artificial Intelligence
  • High Performance Computing
  • Big Geospatial Data
  • PhD in Civil & Environmental Engineering

    Princeton University, 2021

  • Statistics & Machine Learning Certificate

    Princeton University, 2021

  • Computational Science & Engineering Certificate

    Princeton University, 2019

  • MA in Civil & Environmental Engineering

    Princeton University, 2017

  • BS Environmental Engineering

    Federal University of Paraná, 2014

Research & Portfolio

Integrating Earth Observations through AI and Physical Models
SMAP-HydroBlocks is the first 30-m resolution satellite-based surface soil moisture dataset over the continental United States, integrating multi-scale data with ML and physical modeling.
Integrating Earth Observations through AI and Physical Models
Hyper-Resolution Hydrologic and Land Surface Modeling
HydroBlocks is a field-scale resolving land surface model for computationally efficient hydrologic applications over continental extents. Learn about model development & applications here.
Hyper-Resolution Hydrologic and Land Surface Modeling
Field-scale Crop Yield Prediction
Satellite observations, physical models, and machine learning combined can enable crop yield prediction at high spatial resolution at data-scarse regions. Learn more about it here.
Field-scale Crop Yield Prediction
From Hydroclimate Data to Science-Informed Decisions
Integrating computational models and hydroclimate data for actionable agriculture decision-making. Towards resilience and adaptability in a changing climate.
From Hydroclimate Data to Science-Informed Decisions

Recent Publications

More on Publications and Google Scholar

Transformation of Brazil's biomes: The dynamics and fate of agriculture and pasture expansion into native vegetation
How Much Control do Smallholder Maize Farmers Have Over Yield?
Is Closing the Agricultural Yield Gap a “Risky” Endeavor?
Towards an Optimal Representation of Sub-Grid Heterogeneity in Land Surface Models
Drought Diagnosis: What the Medical Sciences Can Teach Us

News & Social