Missions & Projects
Alphabetical
By Last Name:
Displaying records 1 to 12 of 12.
Show:
A shift in transitional forests of the North American boreal will persist through 2100
This research developed a machine learning model to predict current and future boreal forest canopy heights across northern regions using satellite data and climate projections. The study combines NASA's ICESat-2 satellite's vegetation height observations with climate and soil data to understand how forest canopy heights might change under different future climate scenarios. (Summarized with AI)
Key Staff
- Principal Investigator: Paul Montesano
- Project Manager: Mark Carroll
- Project Scientist: Melanie Frost
- Project Scientist: Jian Li
AI CoE support (AI CoE)
The Data Science Group co-leads the Goddard AI Center of Excellence by connecting partners, hosting events and training, and consulting on cutting-edge AI models for NASA.
Key Staff
- Project Lead: Mark Carroll
- Project Scientist: Melanie Frost
- Project Scientist: Jordan Caraballo-Vega
Cutting-edge models for Conservation: Ensemble machine learning advances ecological forecasting and reveals 40 years of changing climatic suitability for an aridland bird
Using ensemble machine learning and spatial analysis applied to tens of thousands of eBird records together with NASA’s MERRA-2 reanalysis, NASA researchers documented shifts in climatic suitability for Cassin’s Sparrow across the past four decades. These shifts appear to be altering the timing of the species’ breeding cycle, suggesting that seasonal climatic change may be driving both behavioral and evolutionary responses.
GenCast predictions using GEOS-FP data (GenCast-FP)
Generate GenCast Predictions with GEOS-FP data
Key Staff
- Software Developer: Alexander Kerr
- Software Developer: Glenn Tamkin
- Software Developer: Jian Li
- Software Developer: Jordan Caraballo-Vega
- Project Manager: Mark Carroll
- Project Scientist: William Putman
GraphCast predictions using ERA5 data (GraphCast - DSG)
Generate GraphCast predictions using ERA5 data.
Key Staff
- Software Developer: Jordan Caraballo-Vega
- Software Developer: Glenn Tamkin
- Software Developer: Jian Li
- Project Manager: Mark Carroll
MOD44 products (MOD44)
Science-ready product development from daily MODIS surface reflectance data (MOD09).
Key Staff
- Project Lead: Roger Gill
- Project Manager: Mark Carroll
- Project Scientist: Melanie Frost
Modeling surface reflectance from VHR imagery (SR VHR)
A model of top-of-atmosphere reflectance (TOAVHR) and Landsat-derived reference (SRreference) provides an high resolution estimate of surface reflectance in VHR imagery (SRVHR). Batch production of these SRVHR estimates help identify the most similar datasets useful for large area analysis.
Pangaea for application of Earth Observation Foundation Models (ILab Pangaea Bench)
ILab's fork of repository with Pangaea Bench and notebooks to apply a variety of Earth Observation Foundation Models (EO FMs) to various tasks.
Quantitative Evaluation of Foundation Models (QEFM)
Quantify the performance of Foundation Models (FMs) for weather and climate to guide GSFC scientists in effectively integrating AI into their research.
Key Staff
- Principal Investigator: Katherine Breen
- Project Manager: William Putman
- Project Scientist: Jian Li
Retrospective Ecological Niche Modeling
Automatic variable selection assists analysis of ecological niche changes enables the use of large variable collections and the discovery of viable predictors that may not be apparent using traditional variable selection methods. It employs a Monte Carlo optimization that enables out-of-core variable selection that is "infinitely scalable" in an extensive multicore compute environment. This work is especially valuable to the species conservaion research and management communities Current customers and potential partners include NASA, NMDGF, USFWS, TAMU/NRI.
SatVision-TOA Geospatial Foundation Model (SatVision-TOA)
SatVision-TOA demonstrates the untapped potential of leveraging moderate- to coarse-resolution data for deep learning in Earth observation. By training a 3-billion-parameter vision transformer on a 100-million-image MODIS TOA dataset, it establishes a scalable, open-source foundation for advancing atmospheric science, cloud analysis, and Earth system modeling. Its released weights and workflows aim to broaden participation and foster collaboration in remote sensing applications. SatVision-TOA captures diverse atmospheric and surface conditions. Additionally, the model improves performance in 3D cloud retrieval and environmental monitoring, surpassing baseline methods.
Weather Model for Mars (MarsCast)
Applying Earth Weather Foundation Models to Mars.
Key Staff
- Principal Investigator: Jian Li
- Project Manager: Mark Carroll
- Project Scientist: Scott Guzewich
- Project Scientist: Geronimo Villanueva
