@article{fdi:010085139,
  title = {{I}nstantaneous tracking of earthquake growth with elastogravity signals},
  author = {{L}icciardi, {A}ndr{\'e}a and {B}letery, {Q}uentin and {R}ouet-{L}educ, {B}. and {A}mpuero, {J}ean-{P}aul and {J}uhel, {K}{\'e}vin},
  editor = {},
  language = {{ENG}},
  abstract = {{R}apid and reliable estimation of large earthquake magnitude (above 8) is key to mitigating the risks associated with strong shaking and tsunamis'. {S}tandard early warning systems based on seismic waves fail to rapidly estimate the size of such large earthquakes(2-5). {G}eodesy-based approaches provide better estimations, but are also subject to large uncertainties and latency associated with the slowness of seismic waves. {R}ecently discovered speed-of-light prompt elastogravity signals ({PEGS}) have raised hopesthat these limitations may be overcome(6,7), but have not been tested for operational early warning. {H}ere we show that {PEGS} can be used in real time to track earthquake growth instantaneously after the event reaches a certain magnitude. {W}e develop a deep learning model that leverages the information carried by {PEGS} recorded by regional broadband seismometers in {J}apan before the arrival of seismic waves. {A}fter training on a database of synthetic waveforms augmented with empirical noise, we showthat the algorithm can instantaneously track an earthquake source time function on real data. {O}ur model unlocks 'true real-time' accessto the rupture evolution oflarge earthquakes using a portion of seismograms that is routinely treated as noise, and can be immediately transformative fortsunami early warning.},
  keywords = {},
  booktitle = {},
  journal = {{N}ature},
  volume = {606},
  numero = {},
  pages = {319--324},
  ISSN = {0028-0836},
  year = {2022},
  DOI = {10.1038/s41586-022-04672-7},
  URL = {https://www.documentation.ird.fr/hor/fdi:010085139},
}