AI use-case explorer
AI use cases
Search and filter every reported use case. Open a record for the agency's full description, governance answers and source provenance.
Columns (7)
| Use case | Agency | Stage | High-impact | Topic area | AI classification | Sourcing |
|---|---|---|---|---|---|---|
| Adaptive Risk Model for Inspected Small Passenger Vessels DHS-178 · USCG | DHS | Deployed | Not high-impact | Administrative Functions | Classical / predictive ML | Developed in-house |
| ELIS Evidence Classifier Service DHS-16 · USCIS | DHS | Deployed | Not high-impact | Service Delivery | Classical / predictive ML | Contract and in-house |
| Streamflow Duration Assessment Modeling 25 · OW | EPA | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Microsoft Power Automate (custom document processing model) 35 · OFA | EPA | Deployed | Not high-impact | Administrative Functions | Classical / predictive ML | Developed in-house |
| Helpdesk chat assistant for common data system tasks 39 · OFA | EPA | Deployed | Not high-impact | Information Technology | Classical / predictive ML | Contract and in-house |
| Agency Records Management System 73 · OFA | EPA | Deployed | Not high-impact | Service Delivery | Classical / predictive ML | Contract and in-house |
| Living Literature Review: Semi-automated Literature Screening 76 · OAR | EPA | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Using machine learning methods to analyze drivers of water quality 77 · AO | EPA | Deployed | Not high-impact | Energy and the Environment | Classical / predictive ML | Developed in-house |
| Machine Learning Data Validation NCUA_E&I-01 · NCUA|E&I | NCUA | Deployed | Not high-impact | Procurement and Financial Management | Classical / predictive ML | Developed in-house |
| Automated Walrus Haulout Monitoring [2024 INV#WO0000000110052] DOI-0247 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| PAWSC Ecotoxicology PFAS Machine Learning [2024 INV#WO0000000112908] DOI-0238 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Delineating sub-surface drainage using satellite imagery [2024 INV#WO0000000109525] DOI-0230 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Oil Spill Response for Ice-Covered Rivers [2024 INV#WO0000000109142] DOI-0208 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Pacific Northwest Stream Flow Permanence [2024 INV#WO0000000109137] DOI-0207 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Climate Futures for Lizards and Snakes in Western North America [2024 INV#WO0000000109092] DOI-0201 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Using Machine Learning in USGS StreamStats to make suspended sediment and bedload predictions [2024 INV#WO0000000107977] DOI-0176 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Rangeland Condition Monitoring Assessment and Projection (RCMAP) [2024 INV#WO0000000107126] DOI-0171 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| use of random forest for species distribution modeling DOI-0161 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| PRObability of Streamflow PERmanence (PROSPER models) [2024 INV#WO0000000109074] DOI-0156 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Machine Learning for automatic fracture mapping and rock identification [2024 INV#WO0000000109499] DOI-0155 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Machine Learning for Avalanche Frequency Modeling DOI-0148 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Classifying CWD-Infected Elk Using Recurrent Neural Networks on GPS Movement Data DOI-0135 · USGS | DOI | Deployed | Not high-impact | Energy and the Environment | Classical / predictive ML | Developed in-house |
| Deep?learning Integrations into NEIC Operations [2024 INV#WO0000000109496] DOI-0119 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| USGS Flow Photo Explorer [2024 INV#WO0000000109196] DOI-0117 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Contract and in-house |
| Coastal Change Likelihood: Synthesizing change factors using supervised learning DOI-0115 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Purchased from vendor |
| Predicting post-fire tree mortality DOI-0100 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Global food-and-water security-support analysis data (GFSAD) project [2024 INV#WO0000000107073] DOI-0095 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Frog vocalization recognition from digital recordings DOI-0092 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Patterns in the Landscape – Analyses of Cause and Effect DOI-0090 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Estimates of Habitat Suitability of Reed Canarygrass (Phalaris arundinacea) in Upper Mississippi River Floodplain Forest Understories DOI-0084 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Submersed Aquatic Vegetation Vulnerability Evaluation Application (SAVVEA) DOI-0081 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Machine learning in remote sensing-based wildfire and natural resource risk assessments DOI-0072 · USGS | DOI | Deployed | Not high-impact | Emergency Management | Classical / predictive ML | Developed in-house |
| Telemetry Analysis Learning Algorithm (TALA) DOI-0070 · USGS | DOI | Deployed | Not high-impact | Other | Classical / predictive ML | Developed in-house |
| LANDFIRE DOI-0069 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Invasive Grass Mapping DOI-0068 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Evapotranspiration mapping and monitoring DOI-0067 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| National Land Cover Database (NLCD) [2024 INV#WO0000000107887] DOI-0066 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Microsoft eDiscovery Attorney-Client Privilege Detection DOI-0021 · SOL | DOI | Deployed | Not high-impact | Other | Classical / predictive ML | Purchased from vendor |
| Performance Modeling / Performance Forecasting DOI-0016 · SOL | DOI | Deployed | Not high-impact | Administrative Functions | Classical / predictive ML | Developed in-house |
| Effects of vehicle traffic on space use and road crossings of caribou in the Arctic [2024 INV#WO0000000110111] DOI-0007 · USGS | DOI | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Sub-Asset Maintenance Model BEP-25 · Bureau of Engraving and Printing (BEP) | TREAS | Deployed | Not high-impact | Procurement and Financial Management | Classical / predictive ML | Contract and in-house |
| Inventory Replenishment Forecast BEP-42 · Bureau of Engraving and Printing (BEP) | TREAS | Deployed | Not high-impact | Procurement and Financial Management | Classical / predictive ML | Contract and in-house |
| IDV Model BEP-67 · Bureau of Engraving and Printing (BEP) | TREAS | Deployed | Not high-impact | Procurement and Financial Management | Classical / predictive ML | Contract and in-house |
| Form 990N Machine Learning Model TREAS-125 · Internal Revenue Service (IRS) | TREAS | Deployed | Not high-impact | Information Technology | Classical / predictive ML | Developed in-house |
| Machine Translation TREAS-28 · Internal Revenue Service (IRS) | TREAS | Deployed | Not high-impact | Service Delivery | Classical / predictive ML | Contract and in-house |
| Synthetic Data Engine TREAS-85 · Internal Revenue Service (IRS) | TREAS | Deployed | Not high-impact | Information Technology | Classical / predictive ML | Purchased from vendor |
| Identity Verification TREAS-IRS-59 · Internal Revenue Service (IRS) | TREAS | Deployed | Not high-impact | Service Delivery | Classical / predictive ML | Purchased from vendor |
| Integrate Word Processor AI for Digitalization TREAS-IRS-64 · Internal Revenue Service (IRS) | TREAS | Deployed | Not high-impact | Service Delivery | Classical / predictive ML | Contract and in-house |
| Programmatic Access to LLMs via API TREASURY-OFR-002 · Office of Financial Research (OFR) | TREAS | Deployed | Not high-impact | Science | Classical / predictive ML | Developed in-house |
| Insight R3095 · Chief Information Officer, Disability Information Systems | SSA | Deployed | Not high-impact | Government Benefits Processing | Classical / predictive ML | Developed in-house |