Streamflow Duration Assessment Modeling

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

The output of this AI use case does not serve as a principal basis for decisions or actions that have a legal, material, binding, or significant effect on rights or safety.

Start date

2011-11-15 (day precision)Source: 11/15/2011 00:00:00

Withheld from public reporting

NoSource: a) No

Mission

Topic area

Science

Operational functions

No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

Improved streamflow classification

Expected benefits

Because streamflow duration classes is unknown for most streams across the nation, the classifications from Streamflow Duration Assessment Methods (SDAMs) can inform ecological assessments and resource management decisions, such as setting restoration goals or applying appropriate water quality standards. SDAMs also support identifying waters that may be subject to regulatory jurisdiction under the Clean Water Act or other authorities.

System outputs

Prediction of whether a streamflow is “perennial,” “intermittent,” or “ephemeral”

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)

Posit Connect (DMAP)

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

Most of the data used to train and evaluate performance of the model was collected by EPA or contractors specifically for the development of SDAMs. The data can be found here: - PNW https://www.hydroshare.org/resource/fb4e7b8758d0478cbfe0d6c786f0f968/ - NE and SE https://catalog.data.gov/dataset/nese-betasdam-final-data-and-code - AW https://catalog.data.gov/dataset/aw-betasdam-final-data-and-code - WM https://catalog.data.gov/dataset/wm-betasdam-final-data-and-code - GP https://catalog.data.gov/dataset/gp-betasdam-final-data-and-code

Federal Data Catalog

www.hydroshare.org ↗

Governance

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

Potential impacts and how they were identified

Not reported