100%
Skip to main content
Platform
GovTribe AI
AI-powered insights to accelerate your government contracting workflow.
MCP Server
Connect GovTribe to your AI tools.
Beacon
Find and connect with key government decision-makers.
Profiles
Federal Agencies
Federal Contract Vehicles
Federal Grant Programs
Major Defense Acquisition Programs
NAICS Categories
PSC Categories
States
Jurisdictions
NIGP Categories
UNSPSC Categories
Vendors
Enrichment By Clearbit
Reports
New Entrants
Funding Analysis
Vehicle Analysis
Groups
Capture
Pipelines
Pursuits
Alerts
Teaming
Data
Awards
Forecasts
Federal Opportunities
State & Local Opportunities
Files
Prime and Subcontractors
Activity
Search
Exports
Solutions
Use Case
Opportunity Identification
Capture Management
Competitive Intelligence
Teaming & Partner Identification
Proposal Management
Strategic Leadership
Go-to-Market Strategy
Industry
Federal Contractors
State & Local Contractors
Grant Seekers
Government Agencies
Research & Consulting
Pricing
More
About Us
Features
Get A Demo
Sign Up
Blog
User Guide
Data Model
GovTribe for Agents
Login
Contact sales
Try for free
Login
Contact sales
Try for free
All Federal Grant Awards
Project Grant 80NSSC26K0095
Award Date
7/8/25
Completion Date
7/7/28
Dollars Obligated
$174K
Overview
Activity
1
Transactions
1
Subawards
2
Similar Awards
Federal Agency
Shared Services Center
Awardee
Michigan Technological University (GKMSN3DA6P91)
Federal Grant Program
43.001
Assistance Type
Project Grant
Place of Performance
Houghton, MI, USA
Description
DYNAMIC FUEL AND SOIL MOISTURE FOR NEXT GENERATION LANDFIRE FUELS.
Posted 1/15/26
5
1
Mod #
Description
ReasonForModification
Federal Obligation
Date
Not listed
DYNAMIC FUEL AND SOIL MOISTURE FOR NEXT GENERATION LANDFIRE FUELS.
$173.7k
1/15/26
5
1
GrantNumber
Description
Subgrantee
Prime Award
Dollars Obligated
Updated At
250880Z2S
Task 6 focuses on assessing the capabilities of existing datasets and analytical tools to enhance the accuracy and reliability of dead and live fuel moisture estimates. This evaluation will support the development of improved fuel moisture products critical for fire management applications. The specific scope includes: Review and Assessment of Existing Datasets and Tools: Evaluate the performance and applicability of current datasets and tools such as NCAR's Fuel Moisture Content (FMC) retrievals, Normalized Difference Vegetation Index (NDVI), Keetch-Byram Drought Index (KBDI), and Topofire model outputs. This involves analyzing their strengths, limitations, spatial and temporal resolutions, and relevance to different fuel types and fire management needs. Validation and Calibration Using Field Data: Use available field datasets of live and dead fuel moisture to validate and calibrate the outputs from these tools. This will ensure that the evaluated datasets meet the accuracy requirements for operational fire behavior modeling and prescribed fire planning. Identification of Gaps and Recommendations: Identify gaps in current datasets and tools that limit fuel moisture estimation accuracy. Provide recommendations for improvements or additional data needs to enhance fuel moisture modeling capabilities. Collaboration with LANDFIRE and Fire Practitioners: Engage with LANDFIRE partners and fire management practitioners to ensure that the evaluation aligns with end-user needs and operational requirements.
University Of New Mexico
Project Grant 80NSSC26K0095
$54.4k
10/13/26
250880DZ3S
This proposal will contribute to operationalization and stakeholder engagement for FireSense project objectives, and contribute towards Dynamic fuel and soil moisture for Next Generation LANDFIRE fuels. USRA will contribute AI/ML expertise to the project and contribute to the task of ensemble modeling. The ensemble modeling task will use data curated by the proposal team into an analysis-ready co-located geospatial format as inputs to train the ensemble machine learning models. The models will consist of Random Forests, Gradient Boosting, Generalized Additive Models, and explore deep spectrospatial features extracted from the datasets by sparse convolutional neural networks and use weighted average to derive ensemble predictions of fuel moisture. Once the model is successfully trained, we will evaluate test performance and robustness and different locations with ground truth data. The workflow will use open source libraries and packages in Python such as scikit, TensorFlow, PyTorch, rasterio and share all model configurations such as code, train, test data, weights, hyperparameters and other configurations as a deliverable with the LANDFIRE stakeholders. USRA will contribute to developing, training and testing the machine learning models with other proposal team members and incorporate any feedback from the LANDFIRE stakeholders for operational use.
Universities Space Research Association
Project Grant 80NSSC26K0095
$27.5k
5/27/26