SATPC0035876 Tab 04 4 SOW.pdf
PDF 189 KB Posted
- Solicitation number
- 80NSSC24877445Q
About this file
This document is a Statement of Work (SOW) for the development of a Harmonized Landsat Sentinel-2 (HLS) AI Geospatial Foundation Model (GeoFM) to support various geospatial science applications, including Aquaculture and Wetlands Mapping, Forest Biomass Estimation, and Deforestation Driver Classification.
The SOW requires the contractor to provide research and science expertise to support the development of the GeoFM, including designing and evaluating novel downstream use cases, assessing the model's generalizability and performance, and creating labeled training data and documentation for new benchmarks. The contractor is also expected to provide outreach and communication support, such as organizing workshops and training sessions to educate the science community on the GeoFM's capabilities. The period of performance is from August 1, 2024 to January 31, 2026, and the place of performance is at facilities located at Clark University. This SOW is associated with a federal contract opportunity with the Solicitation Number 80NSSC24877445Q, issued by the National Aeronautics and Space Administration (NASA) Shared Services Center.
View the file
Other files
| File | Type | Posted |
|---|---|---|
| SATPC0035876 Tab 07 Capability Statement FBO Posting.pdf |
On GovTribe
Work with this file
- Download the original file
- Contacts named in this file
- Similar government files
- Ask GovTribe AI about this file
Text version
Statement of Work for
Harmonized Landsat Sentinel-2 (HLS) AI Geospatial Foundation Model (GeoFM) for Aquaculture and Wetlands Mapping, Forest Biomass Estimation, and Deforestation Driver Classification
Background and Objective:
Artificial intelligence (AI) model development is playing an important role in advancing our understanding of science. Foundation models (FM), in particular, provide flexibility for developers to pretrain a single model and then customize it for specific downstream tasks.
The NASA Inter-agency Implementation and Advanced Concepts Team (IMPACT) at the Marshall Space Flight Center (MSFC) is developing a foundation model for geospatial science applications and is seeking support in designing, building and evaluating the model to advance and explore a wide range of tasks within the field of geospatial science (i.e., Aquaculture and Wetlands Mapping, Forest Biomass Estimation, and Deforestation Driver Classification).
Requirements: The contractor shall:
Provide research and science expertise to support the development of a GeoFM in Aquaculture and Wetlands Mapping, Forest Biomass Estimation, and Deforestation Driver Classification applications.
a. Develop approach and design for novel downstream science use cases relevant to
Aquaculture and Wetlands Mapping, Forest Biomass Estimation, and Deforestation Driver Classification, etc.
b. Evaluate generalizability of the model in fine-tuning tasks across different regions.
c. Evaluate the performance of the GeoFM in classifying drivers of deforestation.
d. Utilize above-ground carbon estimates from Lidar and ground-based observations.
e. Assist the AI team within IMPACT to develop enhancements to the model’s architecture.
f. Create and provide access to labeled, science training data for each downstream use case.
g. Create or provide documentation for new or existing benchmarks to evaluate the performance of the FM.
h. Support the development of fine-tuning approaches for the downstream use cases.
i. Assist the AI team within IMPACT to validate and evaluate the performance of the FM on downstream use cases.
Provide outreach and communication support aimed at educating and training the science community on the capabilities of the AI FM.
a. Organize and host workshops, tutorials, and/or hackathons with the science community.
b. Train scientists and developers on the capabilities of the AI FM related to the developed downstream use cases.
c. Assist the IMPACT team with disseminating research findings through technical reports, conference presentations, and journal publications.
d. Assist with publicizing the AI FM results to the scientific community as an open-source science collaboration.
Development Cycle: The contractor shall:
Follow the FM development iteration cycles shown below.
Deliverables: The contractor shall deliver:
a. Access to labeled, science training data for each downstream use case.
b. Documentation for new or existing benchmarks to evaluate the performance of the FM.
c. Training & tutorial materials to be used during workshops and/or hackathons with the science community.
d. Research findings as technical reports, conference presentations, and journal publications.
Place of Performance:
Facilities at the Clark University
Period of Performance:
August 1, 2024 through January 31, 2026.
File details come from the government source that posted it. Updated .