I am an Environmental and Geospatial Data Scientist passionate about using data-driven approaches to better understand how human activity impacts our planet's ecosystems. My work bridges environmental science, remote sensing, machine learning, and advanced statistical modeling to uncover patterns in how Earth's systems respond to change, and how we can use that insight to protect them.

I enjoy learning about new analysis and modeling techniques. Recently, I have been working on understanding how to harness Claude Code to operationalize some of my machine learning ideas. One example project I have been working on is using machine learning models to predict the phenological (i.e., seasonal) state along the Appalachian Trail in Massachusetts.

I earned my Ph.D. in Earth and Environment from Boston University, where I developed novel Bayesian models and automated workflows for analyzing 30 TB of satellite data to predict forest leaf phenology. As a NOAA Climate and Global Change Fellow at MIT, I expanded this work globally by integrating LiDAR, eddy covariance, and MODIS data to assess various impacts to the carbon cycle.

Currently, at Industrial Economics, Inc., I apply my expertise in spatial and temporal data analysis, ecological modeling, and machine learning to real-world environmental challenges, including assessing contaminant impacts at Superfund sites and guiding natural resource restoration decisions.

Across my career, I've combined technical rigor (R, Python, GIS, Bayesian and machine learning models) with environmental purpose, from forecasting ecosystem dynamics to helping clients interpret complex spatial data. I believe that actionable, transparent, and reproducible environmental data science is key to addressing the climate and ecological crises of our time.