Research press release



Geoscience: Monitoring earthquakes at the speed of light

光速で伝播する重力変化信号を評価するよう訓練された機械学習モデルを使用することで、大地震の発生と進行をリアルタイムで正確に推定できることが明らかになった。この知見を報告する論文が、Nature に掲載される。


今回、Andrea Licciardiたちは、日本国内の地震発生可能性のある1400地点で発生する地震のモデル化シナリオ(35万点)を用いて、PEGSに関する深層学習モデル(PEGSNetと命名)を訓練した。そして、過去の地震記録の中で最大級で、被害が最も大きかった2011年の東北地方太平洋沖地震の実際のデータを使って、PEGSNetを検証した。Licciardiたちは、PEGSNetが、地震の発生位置だけでなく、地震のサイズと時間の経過による変化可能性を正確に推定できるという見解を示している。重要なのは、PEGSNetが、これらのことを地震波が到達する前に迅速に推定できることである。


The evolution of large earthquakes can be accurately estimated in real-time using a machine-learning model trained to assess signals of gravity changes, which travel at the speed of light, according to a paper published in Nature.

Earthquakes are usually monitored by assessing seismic waves — pulses of energy that radiate through the Earth’s crust. However, warning systems based on seismic waves can be too slow to accurately assess the size of large earthquakes (ranked as 8 or above on the moment magnitude scale) as they develop. Tracking prompt elastogravity signals (PEGS), which travel at the speed of light and are the result of sudden displacements of rock causing changes in gravity, is one proposed solution. However, whether PEGS could permit the rapid and reliable estimation of the location and progression of large earthquakes as they arise in real-time is, as of yet, untested.

Andrea Licciardi and colleagues trained a deep-learning model (named PEGSNet) on PEGS using 350,000 modelling scenarios of earthquakes initiating at 1,400 potential earthquake locations in Japan. Real data from one of the largest and most destructive earthquakes ever recorded — the Tohoku-Oki earthquake in 2011 — were then used to test the model. The authors suggest that PEGSNet is capable of accurately estimating the location of earthquakes, as well as their size and how this might change over time. Importantly, PEGSNet can do this rapidly, before the arrival of seismic waves.

The authors conclude that PEGSNet could be important for the early monitoring of large earthquakes and how they evolve — from surface rupture to possible associated tsunamis. Although the model is specific to Japan, the authors highlight that it could be easily adapted to other regions, with only small changes needed to implement this strategy in real time.

doi: 10.1038/s41586-022-04672-7

「Nature 関連誌注目のハイライト」は、ネイチャー広報部門が報道関係者向けに作成したリリースを翻訳したものです。より正確かつ詳細な情報が必要な場合には、必ず原著論文をご覧ください。

メールマガジンリストの「Nature 関連誌今週のハイライト」にチェックをいれていただきますと、毎週最新のNature 関連誌のハイライトを皆様にお届けいたします。