QuakeCast: Earthquake Forecasting Using Machine Learning to Identify and Classify Preseismic Ionospheric Anomalies as Earthquake Signals: FY21 Homeland Protection and Air Traffic Control Technical Investment Program

Abstract

Earthquakes are deadly, expensive, and unpredictable. To date, the study of earthquakes has been predominantly through seismology, which has enabled researchers to describe the long-term progression of earthquakes, but is unable to provide early forecasting necessary for short-term disaster preparation. Global Navigation Satellite Systems (GNSS) satellites offer a new opportunity to study earthquakes and begin to unravel the complex interactions between preseismic processes and the global electric circuit that may be the key to earthquake early forecasting. The QuakeCast project is developing a novel machine learning method to identify ionosphere anomalies as preseismic earthquake signals and uses them to predict impending magnitude, geographical region, and timing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 20, 2022
Accession Number
AD1183107

Entities

People

  • Bhavani Ananthabhotla
  • Dieter W. Schuldt
  • Jeffrey Liu
  • Jessica D. Reid
  • Matthew L. Weiss
  • Samuel Scheele

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence Software
  • Artificial Satellites
  • Computer Vision
  • Detection
  • Detectors
  • Dimensionality Reduction
  • Earthquakes
  • Global Navigation Satellite Systems
  • Image Recognition
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Navigation
  • Navigation Satellites
  • Neural Networks
  • Warning Systems

Fields of Study

  • Environmental science

Readers

  • Atmospheric Science/Meteorology
  • Seismology
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • Space