Multi-Modal Foundation · allenai
OlmoEarth v1 FT — LFMC (Base)
Predicts live fuel moisture content in woody vegetation to support wildfire-risk monitoring from satellite imagery.
What OlmoEarth v1 FT — LFMC (Base) is
OlmoEarth v1 FT — LFMC (Base) is an Earth observation model developed by the Allen Institute for AI (allenai). It is fine-tuned from the foundational OlmoEarth-v1-Base model specifically to map live fuel moisture content (LFMC) in woody vegetation.
LFMC quantifies the water content of living plant foliage relative to its dry mass, serving as an important metric in assessing flammability. By estimating these values across landscapes, the model supports environmental researchers in monitoring wildfire hazard and assessing regional climate and ecological risk.
How it works
The model builds upon the pre-trained OlmoEarth-v1-Base architecture, adapting it for regression or mapping of fuel moisture levels from satellite data. It was trained using the continental United States subset of the Globe-LFMC-2.0 dataset compiled by Marta Yebra and colleagues.
Key facts
- Base model
- OlmoEarth-v1-Base
- Fine-tuning task
- Live Fuel Moisture Content (LFMC) prediction
- Training dataset
- Globe-LFMC-2.0 (continental US subset)
- Domain
- Earth observation, climate, and wildfire monitoring
What you can use it for
- Wildfire-risk monitoring
- Estimating live vegetation moisture levels across regions to determine areas with high flammability and potential wildfire ignition risk.
- Woody vegetation moisture assessment
- Mapping spatial patterns of water content specifically within woody plant canopies from Earth observation imagery.
- Ecological and climate analysis
- Assisting environmental researchers in tracking moisture dynamics in vegetation across the continental United States over time.
Run it here
We list this model but cannot run it yet: no pipeline_tag — needs a human.
Everything on this page still applies. Running it needs a loader for this repository, not a bigger machine.
Strengths and limits
Good at
- Specifically adapted for live fuel moisture content prediction from an Earth-observation foundation model.
- Trained on in situ continental United States measurements from the Globe-LFMC-2.0 database.
Watch out for
- Training is confined to the continental United States subset of Globe-LFMC-2.0, which may limit generalisation to other geographic regions.
- Designed specifically for woody vegetation, meaning it may not be suitable for estimating moisture in non-woody fuel types.
Inputs and outputs
You provide
Sequence or text
A protein or nucleotide sequence, or free text — whichever this model was trained on.
You get back
Mean-pooled representation, one vector per input.
Licence
Check the licence before commercial use · See model card
The See model card licence carries terms worth reading before you depend on it.
Questions
Can I use OlmoEarth v1 FT — LFMC (Base) commercially?
Check the licence before commercial use. The See model card licence carries terms worth reading before you depend on it.
What is Live Fuel Moisture Content (LFMC)?
LFMC is a metric measuring the moisture mass of living foliage relative to its dry weight, used in fire ecology to evaluate vegetation flammability.
What base architecture does this model use?
It is fine-tuned directly from allenai's OlmoEarth-v1-Base model.
What training data was used for fine-tuning?
The model was fine-tuned using the continental United States portion of the Globe-LFMC-2.0 dataset compiled by Marta Yebra et al.
Written from OlmoEarth v1 FT — LFMC (Base)'s own documentation (model card). Statements citing a figure that does not appear there are removed before publication. Licence and running details come from our registry.