San Francisco Bay Area
Data analyst and environmental scientist. I work in GIS, remote sensing, and statistical analysis.
I have never felt so able to solve hard problems and build the ideas I have as I do now. My background is in the natural sciences, and I love physics and AI. What I enjoy most is thinking through a problem and doing the analysis that brings clarity and insight. I use AI tools throughout my work, and I believe they expand both the type and the scope of what we can accomplish. I still see them as tools. There is no replacement for human vision, intuition, and drive.
How I work
AI can let you move too fast, and too confidently, into territory you do not know well. That is a real risk, and it deserves to be faced directly rather than avoided out of fear. As people start to work alongside AI agents, I think the skills that matter most are the hardest ones to teach. They are also the most human. They are softer and more conceptual. They are not the old kind of skill that says I can do task X to get result Y, because that kind of work is being automated fast. What matters now is how clearly you think, and how well you can put that thinking into words.
An employee is no longer just one person in a role. Inside that person's computer is a small army of intelligence. So anyone, whatever their position, can act as the CEO of their own small company of agents, building the tools they need to do good work day to day. That, I think, is the real economics of agents. It is not that you rely on them to do everything for you. It is that you ask them to build the unique and reusable software that improves how you work.
Master's research · Remote sensing · Water resources
Testing whether Sentinel-2 vegetation time series can predict watershed-scale soil moisture in the Upper Gunnison / East River watershed near Crested Butte, Colorado.
10 m maps · 437 ground measurements, 17 sites · leave-one-site-out validation
Collaborative work · Lab method · Trace-gas flux
Turning a stock LI-COR LI-8250 flask multiplexer into a continuous-flow anoxic incubator for intact soil cores, and measuring methane and carbon dioxide flux under imposed anoxia.
4 intact cores · 8-port multiplexer · 92 h run · SLAC
Cartography · Interactive map · Community data
Where the Bay Area’s GIS community lives. A 24 by 36 inch poster and an interactive map built from 615 anonymized BayGeo membership records, by county, by ZIP code and year by year, for the BayGeo Open Map Challenge.
615 records · 25 California counties · 10 years · QGIS + deck.gl
Experiment · Work in progress · Agriculture
An interactive, serverless map that estimates winter cover-crop signals across California almond orchards using free satellite imagery. Counting that on the ground means a census, so this asks how much you can infer from space instead.
16,365 orchards · 9 counties · 6 winters (2018–19 … 2023–24)
Software project · Electron · React · TypeScript
A visibility-first desktop workspace for watching, directing, and collaborating with teams of AI agents across terminals, files, browsers, documents, and notebooks.
Harness-based, not SDK-based · cross-provider GroupThink · governed browser
Coursework
A few pieces from GIS coursework at the University of San Francisco. Graded class exercises, not research. Here are three that cover ground the projects above don't: routing a power line across a cost surface, building a bare-earth terrain model from airborne LiDAR, and scoring a floodplain against five environmental drivers at once.
View all coursework (seven pieces)
These are coursework, so the questions were mostly set by the assignment rather than by me.
About
I spent roughly five years in laboratory and field science before remote sensing became most of my work. That background means I've collected the field and lab data that GIS layers are made of, not only downloaded it: methane flux chambers, groundwater wells, porewater chemistry, soil cores. Soil health and regenerative agriculture remain interests of mine.
I'm now a graduate research assistant at the University of San Francisco, working on floodplain hydrology. I use Sentinel-2 imagery, harmonic regression, and interactive tools to map environmental conditions that are hard to measure on the ground.
Earlier, I was a Research Associate II at Pivot Bio (2020–2023), on the team whose product was named to TIME's Best Inventions of 2023.
M.S. candidate, Environmental Management, University of San Francisco (2024–2026; degree confers on thesis completion) · Advanced Certificate in Geospatial Information Science · Joseph Petulla Award, Outstanding MSEM Graduate Student (2026) · B.S. Ecology & Evolution, UC Santa Cruz.
Thesis presentation (PDF)
