USDA · USDA-089 · record R1388

AI for regional forest mapping and monitoring

Department of Agriculture · Natural Resources and Environment

Overview

Development stage: DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2002-10-01 (day precision)Source: 10/1/2002
Withheld from public reporting: Not reported

Mission

Topic area: Energy and the Environment
Operational functions: Image and video analysis Derived by keyword rules; see methodology

Problem the AI is intended to solve

The purpose of this model is to use existing satellite images and forest survey data from the USDA Forest Service to create detailed maps of forest structures. Continuing research to understand and communicate errors and uncertainties in mapping and to improve algorithms over time.

Expected benefits

In addition to basic and applied research innovations, the application provides maps of forest structure (e.g., tree density and size, timber volume) and composition (tree species) which supports National Environmental Policy Act (NEPA) and other planning operations. These data may provide cost savings by either reducing the need to generate independent data through geographic information systems or field work. This research will help land managers be more effective and efficient with their planning.

System outputs

The model outputs Geographic Information System (GIS) data that are predictions of forest attributes, such as tree density and tree species data in a study area.

Technology

AI classification: Classical / predictive MLSource: Classical/Predictive Machine Learning: Models trained on data to make predictions or classifications based on identified patterns or relatio…
System name(s): Not reported
Custom-developed code: Yes
Public source code: github.com ↗

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): Oregon State University
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: Forest Inventory and Analysis data collected by the USDA Forest Service (Research & Development). It contains 200,000 individual plot measurements, and hundreds of Geospatial Information System (GIS) features (climate data, satellite images, topography, etc.) stored as GIS data (30-meter raster maps; GeoTiffs).
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