Discovery · side-by-side comparison
NASA and DOI
Similarity 0.42 (moderate). Moderate: overlapping task language; often related functions in different settings. Classified as Similar use case: The descriptions overlap. The inventory alone cannot show whether either system could be shared.
Why they matched
| Component | Contribution to score |
|---|---|
| System outputs | +0.130 |
| Problem description | +0.111 |
| Same topic area | +0.060 |
| Shared operational function | +0.052 |
| Same AI classification | +0.037 |
| Expected benefits | +0.025 |
| Total | 0.416 |
Most distinctive shared terms: land cover, cover, land, imagery, satellite, training
| Field | Sub-Saharan West Africa Land Cover Change | Machine learning-based landscape feature classification using satellite and airborne imagery [2024 INV#WO0000000108791; 2024 INV#WO0000000108794] |
|---|---|---|
| Agency |  NASANational Aeronautics and Space Administration |  DOIDepartment of the Interior |
| Bureau | GSFC: Goddard Space Flight Center | USGS |
| Stage | Pre-deployment | Pilot |
| Topic | Science | Science |
| AI classification | Classical / predictive ML | Classical / predictive ML |
| Sourcing | Not reported | Purchased from vendor |
| Vendor (reported) | Not reported | ESRIEsri |
| System name | Not reported | Not reported |
| Problem | In recent decades, Sub-Saharan West Africa has seen rapid and ongoing land cover change fueled by population growth and subsequent agricultural expansion and intensification. These changes have led to negative impacts including a decrease in land productivity, loss of local biodiversity, and a general degradation of ecosystem services, resulting in debate over whether policies to discourage this type of transformation should be introduced. However, moderate resolution satellite data and traditional remote sensing methods are insufficient at resolving land cover land use change in this region, which is dominated by small, dispersed patches of savanna-woodlands and smallholder agriculture systems (< 3 ha.) that consist of highly dynamic and often ill-defined field boundaries. In Senegal, extreme latitudinal gradients in phenology, limited availability of cloud-free wet season imagery, and widespread burnt area during the dry season add further complexity in identifying sub-hectare land cover and change. | need to increase the accuracy of habitat and land cover classifications |
| Outputs | Presented here, our quantitative results evaluating the impact of spatial resolution on the accuracy of mapping agricultural expansion and tree/shrub cover in Senegal provide insight into the optimal input parameters for mapping land cover with deep learning applications. | habitat and land cover classifications |
| Benefits | Thanks to the growing availability of very high resolution (VHR) imagery (< 3 m GSD) through commercial vendors and the increased accessibility of high-performance computing resources such as GPUs, we are now able to perform computationally-expensive, deep learning-based predictions on thousands of VHR observations for mapping fine-scale land cover over large areas. We have leveraged these enhanced capabilities by developing a series of deep learning models for land cover classification with WorldView 8-band imagery (2 m GSD), and have performed inference on all data available over the study domain. To assess the cost-benefit of this effort, we implemented a simple spatial resolution experiment at select locations in Senegal by pansharpening and resampling 2 m WorldView multispectral imagery and training data to alternate spatial resolutions (0.5 m, 5 m, 10 m, and 30 m) for training and inference using our deep learning models. | enhanced accuracy of habitat and land cover classifications |
| Data description | Not reported | Airborne and Satellite imagery - often with required field-based training data |
| PII | Not reported | No |
| ATO | Not reported | No |
| Public code | Not reported | Not reported |
Exploratory reuse assessment
What the inventory can and cannot show| Functional similarity | moderate (0.42) | Some support |
| Inputs and outputs | Both describe outputs; compare below | Some support |
| Mission or administrative function | Image and video analysis | Some support |
| Documentation available | Code: none linked · System names: Not in inventory | Weak or missing |
| Technical uncertainties | AI classification: same; sourcing: unknown / vendor | Verify outside inventory |
| Data-access constraints | Data descriptions: Not in inventory / Reported | Verify outside inventory |
| Privacy and security | PII: blank / no · ATO: blank / no | Verify outside inventory |
| Legal or policy constraints | Not in inventory. Requires independent verification. | Verify outside inventory |
No pair is marked as a validated reuse opportunity. That needs technical, legal and operational evidence beyond this inventory.
Questions for a human reviewer
- Do NASA and DOI solve the same problem for the same kind of user, or only use similar words?
- Are the inputs (data types, formats, volumes) compatible?
- A vendor product is involved. Do licence terms allow use by another agency, and is it available on a government-wide vehicle?
- Does either system's Authorization to Operate cover use by another agency?