loading page

RockNet: Rockfall and earthquake detection and association via multitask learning and transfer learning
  • +6
  • Wu-Yu Liao,
  • En-Jui Lee,
  • Chung-Ching Wang,
  • Po Chen,
  • Floriane Provost,
  • Clément Hibert,
  • Jean-Philippe Malet,
  • Chung-Ray Chu,
  • Guan-Wei Lin
Wu-Yu Liao
National Cheng Kung University
Author Profile
En-Jui Lee
National Cheng Kung University

Corresponding Author:[email protected]

Author Profile
Chung-Ching Wang
National Cheng Kung University
Author Profile
Po Chen
University of Wyoming
Author Profile
Floriane Provost
Institut De Physique Du Globe De Strasbourg
Author Profile
Clément Hibert
Institut Terre et Environnement de Strasbourg / ITES, CNRS, University of Strasbourg
Author Profile
Jean-Philippe Malet
French National Centre for Scientific Research (CNRS)
Author Profile
Chung-Ray Chu
Guan-Wei Lin
National Cheng Kung University


Seismological data can provide timely information for slope failure hazard assessments, among which rockfall waveform identification is challenging for its high waveform variations across different events and stations. A rockfall waveform does not have typical body waves as earthquakes do, so researchers have made enormous efforts to explore characteristic function parameters for automatic rockfall waveform detection. With recent advances in deep learning, algorithms can learn to automatically map the input data to target functions. We develop RockNet via multitask and transfer learning; the network consists of a single-station detection model and an association model. The former discriminates rockfall and earthquake waveforms. The latter determines the local occurrences of rockfall and earthquake events by assembling the single-station detection model representations with multiple station recordings. RockNet achieves macro F1 scores of 0.990 and 0.981 in terms of discriminating earthquakes and rockfalls from other events with the single-station detection and association models, respectively.
2023Published in IEEE Transactions on Geoscience and Remote Sensing on pages 1-1. 10.1109/TGRS.2023.3284008