Attribution of individual methane and carbon dioxide emission sources using EMIT observations from space
Though built to map surface mineralogy, EMIT turned out to be a remarkably capable greenhouse gas instrument. Here we show that individual methane and CO2 point sources can be detected and attributed to their emitters from orbit.
Science Advances, 2023
SpecTf: Transformers enable data-driven imaging spectroscopy cloud detection
Cloud screening is a first, critical step for nearly every downstream imaging spectroscopy product. This work introduces a spectral transformer that learns cloud detection directly from the data, outperforming heritage approaches.
PNAS, 2025
Generalized radiative transfer emulation for imaging spectroscopy reflectance retrievals
Estimating reflectance from imaging spectroscopy at large scales requires radiative transfer models - which are slow and expensive. Here, we built one that uses surrogate models and neural networks that is fast and open source.
Remote Sensing of Environment, 2021
Simultaneous characterization of wildfire smoke and surface properties with imaging spectroscopy during the FIREX-AQ field campaign
Both surface and atmospheric properties are critical for Earth system science. In this work, we retrieve both dense smoke plume characteristics and the surfaces beneath them.
JGR: Atmospheres, 2022
Uncovering ecological patterns with convolutional neural networks
Despite their prevalence in image processing, CNNs have been relatively slow to be adopted in the context of ecology. This, however, is rapidly changing, and in this review we discuss emerging trends, good practices, and what lies ahead for CNNs in ecology.
Trends in Ecology & Evolution, 2019
Forest drought resistance at large geographic scales
As hot droughts become more frequent and more severe, it is important for long‐term forest management to understand which forests are at risk and which have the capacity to withstand these events. The findings in this California-based study are an important first step towards assessing spatially explicit forest stability in the face of a changing climate.
Geophysical Research Letters, 2019