activity
20242026
collaborators

6 papers

astro-ph.EP2026

MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres

M. L. Carroll, J. Li, S. D. Guzewich +3

We investigate the transferability of Earth weather foundation models to planetary atmospheres by adapting the GraphCast graph neural weather forecasting model to Mars. While Graph…

cs.CV2026

SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models

Xingyan Li, Jordan A. Caraballo-Vega, Jie Gong +2

Geospatial foundation models (GeoFMs), pretrained on large-scale geospatial data such as Earth observation (EO), climate, and weather data, have shown promising performance when fi…

astro-ph.EP2026

Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning

Brian P. Powell, Jorge Martinez-Palomera, Amy Tuson +3

We present a novel method for extracting moving objects from TESS data using machine learning. Our approach uses two stacked 3D U-Nets with skip connections, which we call a W-Net,…

cs.LG2025

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

Brian P. Powell, Jordan A. Caraballo-Vega, Mark L. Carroll +4

We report the discovery that binary encoding allows neural networks to extrapolate periodic functions beyond their training bounds. We introduce Normalized Base-2 Encoding (NB2E) a…

cs.CV2025

Mapping bathymetry of inland water bodies on the North Slope of Alaska with Landsat using Random Forest

Mark L. Carroll, Margaret R. Wooten, Claire E. Simpson +6

The North Slope of Alaska is dominated by small waterbodies that provide critical ecosystem services for local population and wildlife. Detailed information on the depth of the wat…

cs.CV2024

SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery

Caleb S. Spradlin, Jordan A. Caraballo-Vega, Jian Li +3

Foundation models have the potential to transform the landscape of remote sensing (RS) data analysis by enabling large computer vision models to be pre-trained on vast amounts of r…