Helen Weierbach (she/her) is an Environmental Data Science Research Associate in the Energy Geosciences Division. Helen’s background is in applied mathematics including uncertainty quantification, model sensitivity analysis, and Bayesian statistical and machine learning. She is broadly interested in applying her mathematical and computational skills to understand how the earth system responds to changing climate conditions.
At the lab she works on two projects: Charuleka Varadharajan’s Early Career Research project, iNAIADS (iNtegration, Artificial Intelligence Analytical Data Services), and the Watershed SFA. For iNAIADS, she focuses on using Machine Learning (classical ML and Deep Learning) to model changes in stream temperature across spatio-temporal scales and during disturbance conditions. With the Watershed SFA, she works in Nicholas Bouskill’s lab group using field observations to constrain relevant nitrogen cycling processes in the East River Watershed into a watershed-scale model High Altitude Nitrogen Suite of Models or HAN SoMo. Using this model, she focuses on modeling the impact of future climate perturbations (such as atmospheric warming, drought, and wildfire) to understand the impact on mountainous hydro-biogeochemical cycling.