Projects
Systems I've built end-to-end — from distributed HPC simulation to production machine learning pipelines.
A distributed-memory rewrite of a snow-evolution model, scaled to 1,800 HPC cores to produce a 21-year, 100m-resolution snow record for the continental United States.
HPCFortranMPICoarray FortranDistributed SystemsGeospatial
An operational ML platform fusing in-situ observations, remote sensing, and physically based models into near-real-time snow forecasts for federal water managers.
Production MLData PipelinesRemote SensingFull-StackAWS
Multimodal Vision Transformer architectures fusing high-resolution terrain, lidar, and satellite data to optimize where environmental monitoring stations should go.
Vision TransformersMultimodal MLPyTorchDistributed TrainingGeospatial
An automated pipeline for Sentinel-1 SAR acquisition, quality control, and time-series analysis, built to characterize snowmelt progression across space and time.
Remote SensingSARData PipelinesPython