USDA · USDA-137 · record R1435

Automated Road Mapping

Department of Agriculture · Natural Resources and Environment

Overview

Development stage: PilotSource: b) Pilot – The use case has been deployed in a limited test or pilot capacity.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2025-05-05 (day precision)Source: 5/5/2025
Withheld from public reporting: Not reported

Mission

Topic area: Science
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

Road and trail maps are essential for effective fire response, forest management, and public safety in wildland areas. Unfortunately, many existing maps are outdated or incomplete. Forest Service employees currently rely on time-consuming and labor-intensive methods like GPS mapping.

Expected benefits

Effective implementation may enable the Forest Service to more comprehensively manage road network data at lower cost. Improved data can increase safety on federal lands.

System outputs

The AI system produces high resolution images of mapped roads within areas managed by the Forest Service.

Technology

AI classification: Computer visionSource: Computer Vision: AI that processes and interprets visual data (e.g., images and videos).
System name(s): Not reported
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): RedCastle Resources
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: No
Demographic features: k) None of the above
Training and evaluation data: Training data was collected using LiDAR digital terrain models and National Agriculture Imagery Program imagery. Approximately 2000 image patches were generated for initial model training.
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported