Diana Gergel
Data Scientist
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolDiana Gergel is a data and AI/ML scientist with 12 years of experience specializing in probabilistic weather forecasting and climate modeling, currently leading the AI Weather team at RWE AI Research Lab in Bellevue. She holds a PhD in computational hydrology focused on Arctic regional climate modeling and has translated that academic expertise into impactful industry work at Rhodium Group, Climate Impact Lab, BlackRock, and Gro Intelligence. Diana led a major CMIP6 downscaling and bias-correction project—publishing the dataset and a first-author paper on tail-risk methods—and helped productionize climate risk models including BlackRock’s first wildfire model. Her technical breadth spans applied econometrics, probabilistic forecasting, and robust test automation for hydrologic models (contributions to the widely used UW-Hydro/VIC testing infrastructure). Passionate about high-impact science and sustainability, she combines rigorous research with production delivery to advance climate resilience and decision-making. Colleagues describe her as someone who thrives on technically hard problems and turns scientific innovation into operational tools.
12 years of coding experience
University of Washington
English, Swahili, Hebrew, French, Spanish
Github Skills (6)
python10
testing10
xray8
xa8
hydrology7
clim7
Programming languages (4)
Github contributions (5)
UW-Hydro/VIC
May 2016 - Sep 2019
The Variable Infiltration Capacity (VIC) Macroscale Hydrologic Model
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:210 commits, 74 PRs, 2 pushes in 3 years 4 months
Contributions summary:Diana focused on improving the testing infrastructure and test coverage for the VIC model, particularly for the image driver. Their work involved expanding the system test infrastructure, adding tests to verify output files, and implementing checks for NaN values in the model's results. Furthermore, the user integrated these tests into the classic and image drivers' Travis testing workflows. The contributions demonstrate a focus on ensuring the reliability and correctness of the VIC model's output.
vicclimatestreamflowhydrologycapacity
dgergel/VIC
Mar 2016 - Sep 2019
The Variable Infiltration Capacity (VIC) Macroscale Hydrologic Model
Contributions:1 PR, 351 pushes, 85 branches in 3 years 6 months
vicvariablecapacity
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.