Matt Duyst

Grassroots Carbon is the largest soil carbon removal company in the United States, issuing credits for regenerative grazing across two million acres of rangeland. I build and maintain the data infrastructure beneath that verification: a system that ingests sparse ground-truth field observations from multiple monitoring networks and harmonizes them with satellite imagery, spectral indices, terrain derivatives, and soil and climate context into training-ready datasets for the downstream models. Ranch-level stratification is designed around SEP v2, where clustering geophysically similar ground directly reduces the sampling uncertainty that drives credit deductions.

I engineered the team's shared covariate extraction tooling, a Python client that queries five authoritative geospatial sources through one interface and consolidates what were previously fragmented workflows into a single maintained codebase. I benchmark biomass and structural vegetation architectures spanning deep learning, ensemble methods, and process-based ecological models, with outputs supporting quantification under the Regenerative Standard, VM0042, and CAR-SEP, and extends them into counterfactual baselines that reconstruct expected productivity under business-as-usual management, a required step under each methodology. I also lead technology planning for the company's earth observation capabilities, evaluating sensing platforms and data sources for the geospatial roadmap. This work is under active development and unpublished; publications are forthcoming.

SeekOps is a NASA JPL spin-off that quantifies methane emissions with tunable diode laser absorption spectroscopy sensors flown on UAVs. As one of three scientists on the Science team, reporting to the co-founder and CTO, I led a quantitative assessment of flare destruction removal efficiency across the Bakken and Permian basins. The campaign deployed UAV-mounted TDLAS sensors, ultrasonic anemometers, and RTK ground stations, and calculated efficiency through mass balance, comparing uncombusted methane in each plume against measured inflow while examining the influence of flowrate, temperature, and pressure. The result covered 42 flare systems across 71 observations, including 27 revisits, and was published as first author and presented at SPE ATCE 2024 (SPE-221067-MS), contributing to enhanced leak detection and repair programs in two major shale basins.

I designed the QA/QC workflow for the company's UAV methane detection: LiDAR terrain corrections, surface roughness adjustments for airflow near oil and gas facilities, and wind vector validation through flight telemetry, with plume dynamics modeled from mass conservation to produce emission source maps aligned with OGMP and EPA reporting standards. I trained a fine-tuned YOLOv8 detector to classify wellheads, compressors, storage tanks, and flare stacks from aerial imagery for autonomous site characterization, managing the full cycle from annotation to held-out validation, and built the client-facing and internal visualization suites in Python and GIS platforms that communicated spatial emissions distributions across survey campaigns.

Fully funded as a Yale Merit Research Scholar and Hixon Center for Urban Sustainability Fellow, and a Graduate Teaching Fellow for Regression Modeling of Ecological and Environmental Data. In the Lee Lab I investigated the relationship between urbanization, rice cultivation, and methane across China's Yangtze River Delta, home to more than 150 million people: multi-decadal land cover classified from 30 m Landsat in Google Earth Engine, with urban extent from the GAIA dataset and paddy rice from the Phenology and Pixel-Based Paddy Mapping algorithm, set against Sentinel-5P TROPOMI column methane and tested for spatial clustering with Getis-Ord Gi* and Global Moran's I. The thesis proposed a DeepLabV3+ network to extend the emissions record before the satellite era. A 2026 reproduction of the analysis does not reach the thesis conclusion: no land-cover model outperforms a spatial null at 0.25 degrees, and both the original thesis and the reproduction are published together with an errata.

Alongside the thesis, I integrated thermal and RGB UAV imagery into a calibrated four-band orthomosaic to assess photovoltaic panel performance across Yale's West Campus array, and with a Yale collaborator earned an Honorable Mention at the 2022 Global Stocktake Climate Datathon ahead of COP 27, competing among more than 100 participants with a cross-sectoral analysis of allowance pathways under the EU Emissions Trading System.

Field and computational research at one of the world's longest-running peatland monitoring programs, working with eddy covariance towers, ultrasonic anemometers, and greenhouse gas analyzers under AmeriFlux protocols to capture methane concentration gradients at fine temporal resolution. The 2022 work applied feature importance and seasonal decomposition to isolate the environmental drivers of flux and built an ensemble of LightGBM, SARIMAX, Prophet, and XGBoost over OLS regression, reported at the time to explain 87 percent of variance with forecasts extended to 52 weeks.

The project was rebuilt from source in 2026 as a monthly study of the full 2009 to 2024 record, forecasting one to twelve months ahead against seasonal benchmarks and projecting the fitted relationships back two decades. The rebuilt finding is narrower and more useful: the seasonal cycle repeats reliably, the size of each season varies without trend, and none of the recorded covariates predict that variation once seasonality is accounted for. It is the first of my repositories brought to production standard, with its data, decisions, and limits documented.

UCLA Regents Scholar and Undergraduate Research Scholars Program recipient. The coursework covered the full geospatial stack: supervised and unsupervised image classification, spectral index analysis, SAR interpretation, DEM construction, spatial interpolation and autocorrelation, SQL spatial querying, cartographic design, and predictive environmental modeling. The undergraduate thesis measured surface vegetation change across the Mendocino Complex, at the time the largest wildfire in California history, from Landsat 8 pre- and post-fire scenes in Google Earth Engine using NDVI and NBR, and was presented at the 2019 Los Angeles Geospatial Summit, hosted by the USC Spatial Sciences Institute. Twenty-plus of the coursework maps form the archive on this site.