USDA · USDA-120 · record R1418

Digital Soil Mapping

Department of Agriculture · Farm Production and Conservation

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: 2012-10-01 (day precision)Source: 10/1/2012
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

The purpose of this project is to implement new soil map products at local, regional, and national scales to provide more explicit soil information than traditional soil mapping products.

Expected benefits

The expected benefits are that AI streamlines the data development process, creates more consistent and detailed maps, and provides objective estimates of uncertainty to support conservation activities, decision makers, and environmental modelers.

System outputs

Outputs include maps of soil type for selected local and regional project areas, including areas without any soil map products. Outputs also include continuous soil property maps representing individual soil properties predicted at seven depths for the continental United States.

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): The R Project for Statistical Computing; Arc Soil Inference Engine; System for Automatic Geoscientific Analyses; Google Earth Engine; Google Compute Platform
Custom-developed code: Yes
Public source code: github.com ↗

Sourcing

How it was built: Developed in-houseSource: b) Developed in-house
Vendor (as reported): Not reported
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: Yes
Demographic features: k) None of the above
Training and evaluation data: The AI models are trained and evaluated using a combination of soil field observations and previous aggregated soil spatial data. The training data include information such as soil particle size distribution, organic matter content, bulk density, depth to restrictive features, and water states.
Federal Data Catalog: catalog.data.gov ↗

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