I’m a data scientist at Bridger Photonics, where I turn aerial methane detection data into products, client insights, and strategy. My work spans statistical modeling, machine learning, client-facing analytics, and, most recently, orchestrating AI agents across a range of business contexts.
I work mainly in Python, SQL, and R, and I enjoy the full lifecycle: scoping an ambiguous problem, building the model or pipeline, and explaining the result to executives, regulators, or engineers. This site collects some of my technical work. Thanks for stopping by!
Data Scientist, Customer Success | Bridger Photonics (03/2026 - Present) | Remote
- Designing and orchestrating AI agent workflows across a range of business contexts
- Leading evaluation and scoping of the client analytics suite for the company data platform
- Owning end-to-end client data strategy: designing, presenting, and iterating on emissions analytics deliverables
Emissions Data Scientist II | Bridger Photonics (01/2025 - 03/2026) | Remote
- Co-developed a client analytics suite revealing an 18% YoY emissions reduction across the 20 largest clients
- Presented Bridger’s aerial methane detection technology and analytics methodology at PTAC 2025 in Calgary, Alberta
Policy Science Advisor | Data Scientist | Bridger Photonics (12/2023 - 01/2025) | Bozeman, MT
- Led R&D of super-emitter analytics using statistical modeling and techno-economic analysis; the work informed market strategy and public messaging on super-emitter prevalence
- Advocated for technology-neutral methane regulation through public comment letters and EO 12866 presentations to the Department of Transportation
Machine Learning Engineer | MEDS Capstone Project (12/2022 - 06/2023)
Measuring Agricultural Adaptation to Climate Change in Zambia Using Satellite Imagery and Machine Learning
- Predicting dissolved inorganic carbon from ocean chemistry: comparing linear regression, KNN, decision trees, random forests, gradient boosting, and SVMs in Python and R on CalCOFI data
- Predicting climbing incident outcomes from article text: NLP feature engineering and classification models in R
- Exploring extinction: statistical modeling of IUCN data across Animalia
See the full portfolio for more.
Donahue, C., Bartnik, A., Dillon, J., Hengst, V., Oberoi, K., Ottsen, P., & Thorpe, M. (2026). Making Real Progress: Operator Methane Emissions Reductions Driven by Aerial LiDAR LDAR Programs and Tracked by Measurement-Based Inventories. Rio Oil & Gas Expo and Conference (ROG.e 2026), IBP, Rio de Janeiro, Brazil. Technical paper IBP5873_2026.
Graduate
University of California, Santa Barbara | Bren School of the Environment & Management (June 2023)
Master of Environmental Data Science | 4.0 GPA
Undergraduate
University of Arkansas | Fayetteville, AR (2015 - 2020)
B.S. Environmental Science
B.A. Chemistry | Minor in Physics
B.A. Biology | Minor in Mathematics
Languages & tools: Python, SQL, R, MATLAB, PostgreSQL, Git, Docker, Tableau
Machine learning & statistics: gradient boosting, random forests, SVMs, regularized regression, NLP, hypothesis testing, spatial-temporal analysis, techno-economic analysis
AI & agentic systems: multi-agent orchestration, LLM APIs, tool integration (MCP), context engineering, AI-assisted analytics and automation