Data to Test and Evaluate the Performance of Neural Network Architectures for Seismic Signal Discrimination. Volume 1

Abstract

This report describes a data set that was developed to test and evaluate the performance of neural networks for automated processing and interprepation of seismic data. This data set may also be valuable for many other studies related to seismic monitoring of nuclear explosion testing at regional distance. It includes waveform and parametric data from 241 regional events recorded by the short-period elements of the NORESS and ARCESS arrays in Norway (33 channels/array). The waveform data are stored in SAC binary format, and the parametric data are stored in ASCII files. The event epicentral distances are 200-1800 km, and the event Lg magnitudes are approximately 1.5-3. 2. Most of the events are mining explosions in western USSR, Sweden, and Finland. However, 18 of the events are earthquakes, and 22 are presumed underwater explosions. Detailed documentation has been developed for each event, and is included in eight separate database reports.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 27, 1991
Accession Number
ADA254413

Entities

People

  • Gagan B. Patnaik
  • Thomas J. Sereno Jr.

Organizations

  • Leidos

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Computing System Architectures
  • Data Sets
  • Databases
  • Earth Sciences
  • Earthquakes
  • Expert Systems
  • Explosions
  • Geography
  • Geology
  • Geophysics
  • Network Architecture
  • Neural Networks
  • Nuclear Explosion Testing
  • Nuclear Explosions
  • Planetary Sciences
  • Underwater Explosions
  • Waveforms

Readers

  • Computer Science.
  • Seismology

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference