Skip to main content
  • English
  • Español
  • Français

United
Nations

 

Office for Outer Space Affairs
UN-SPIDER Knowledge Portal

  • Accueil
  • À propos
    • Qu'est-ce que l'ONU-SPIDER?
    • À propos d’UNOOSA
    • Publications
    • Offres d'emploi
    • Rencontrez l'équipe
    • Contact
  • Applications spatiales
    • Technologie satellitaire
    • Mécanismes d’urgence
    • Recovery Mechanisms
    • Réseau international d'alerte aux astéroïdes
    • Space Mission Planning Advisory Group
    • Initiative internationale sur la météorologie spatiale
    • Les technologies spatiales à l'ONU
    • Comptes-rendus d'utilisateurs
  • Liens & ressources
    • Application de données du mois
      • Disaster Recovery
    • Sources de données
    • SIG et logiciels de télédétection
    • Online Learning Resources
    • Institutions
  • Risques & catastrophes
    • Prévention des risques de catastrophe
    • Systèmes d'alerte précoce
    • Gestion des catastrophes et des interventions d'urgence
    • Aléas naturels
    • Cadre d'action de Sendai
    • L'ONU et la prévention des risques de catastrophe
    • L'ONU et les alertes précoces
    • L'ONU et la gestion des catastrophes
  • Appui technique
    • Missions Conseil
    • Appui d’urgence
    • Appui à distance
    • Pratiques recommandées
    • Activités de formation
    • Utilisations pratiques
  • Réseaux
    • Bureaux régionaux d’appui
    • GP-STAR
    • MHEWS
    • IWG-SEM
  • Projets
    • SPEAR
    • SEWS-D
    • EvIDENz
    • Flood GUIDE
  • Actualités
    • Actualités
    • Événements
    • Événements passés
  • Admin
    • SAM Items

Breadcrumb

  • Home
  • New Studies Use Machine Learning Models To Predict Earthquakes
  • New studies use machine learning models to predict earthquakes

New studies use machine learning models to predict earthquakes

Synthetic aperature radar patterns of seismic deformations associated with a model earthquake on the San Francisco section of the San Andreas Fault. Synthetic aperature radar patterns of seismic deformations associated with a model earthquake on the San Francisco section of the San Andreas Fault. Image: NASA/JPL/UCDavis

Earthquakes are a major concern in increasingly populated regions, however their prediction is a difficult task. Researchers have recently made progress in the use of complex simulation and modeling techniques to better forecast the occurrences of earthquakes.

In a recent study, researchers used Gradient Boosted Regression Trees, a machine learning technique for regression and classification problems that incorporates training data, to better determine spatiotemporally complex loading histories within subduction zones. The researchers simulated tens of earthquakes using a small‐scale experimental replica of a subduction zone and show that machine learning predicts well the timing and size of laboratory earthquakes by reconstructing and properly interpreting the spatiotemporally complex loading history of the system. These results promise substantial progress in real earthquake forecasting as they suggest that the complex motion recorded by geodesists at subduction zones might be diagnostic of earthquake imminence.

Random Forest (RF) approach for predicting time remaining before failure.
Random Forest (RF) approach for predicting time remaining before failure. Image: Bertrand Rouet‐Leduc / Geophysical Research Letters, Volume 44, Issue 18, September 2017 / CC BY-NC-ND 4.0

 

Other improvements have been also applied to early warning systems. Signals along the ocean can sometimes be deceptive as to the occurrence of earthquakes, sending false alarms regarding tsunamis and tectonic events. To mitigate this problem, a team of researchers recently used machine learning tools to determine if the waveforms are generated by earthquakes or local noise sources. They trained the algorithms with about 700,000 P-waves emitted by past earthquakes in southern California and Japan to better recognize the energy wave and differentiate it from other waves that may trigger a false alarm. Effectively, this better distinguishes what an earthquake-related wave is: in the study the accuracy was over 99% as to what waves constituted those related to earthquakes.

Using Machine Learning and Surface Deformation Data to Predict Earthquakes
Wed, 13 Mar 2019 - 09:22
Japan
United States of America
Earthquake

Footer menu

  • Contact
  • Terms of Use

User account menu

  • Log in