DOI · DOI-0132 · record R2630

Four AI systems using different strategies to identify, classify and locate both volcano-tectonic and non-traditional volcanic earthquakes

Department of the Interior · USGS

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: 2011-01-01 (day precision)Source: 1/1/2011
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

Identifying and classifying volcanic earthquakes, which can be very different from traditional tectonic earthquakes. These are addressed with CNN's, hidden Markov models, and pre-trained neural networks for picking P- and S-waves in seismograms, hierarchial clustering, identifying non-traditional volcanic earthquakes (e.g., long-period, degassing events, bubble collapse, and assigning magnitudes).

Expected benefits

These methods will automatically detect and classify earthquakes in large data sets without human review. In the case of identifying small earthquakes, the method has detected 4.5x more earthquakes than human review.

System outputs

Catalogs of earthquakes

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: No
Public source code: doi.org ↗

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: Seismic waveforms and spectrograms
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