A Distributed Multi-Sensor Machine Learning Approach to Earthquake Early Warning

@inproceedings{Fauvel2020ADM,
  title={A Distributed Multi-Sensor Machine Learning Approach to Earthquake Early Warning},
  author={Kevin Fauvel and Daniel Balouek-Thomert and Diego Melgar and Pedro Silva and Anthony Simonet and Gabriel Antoniu and Alexandru Costan and V{\'e}ronique Masson and Manish Parashar and Ivan Rodero and Alexandre Termier},
  booktitle={AAAI},
  year={2020}
}
Our research aims to improve the accuracy of Earthquake Early Warning (EEW) systems by means of machine learning. EEW systems are designed to detect and characterize medium and large earthquakes before their damaging effects reach a certain location. Traditional EEW methods based on seismometers fail to accurately identify large earthquakes due to their sensitivity to the ground motion velocity. The recently introduced high-precision GPS stations, on the other hand, are ineffective to identify… Expand
View via Publisher
ojs.aaai.org
15 Citations
Background Citations
5
Methods Citations
1

15 Citations

Citation Type

Citation Type

EARTHQUAKE ALERT SYSTEM BASED ON IOT TECHNOLOGY
Many countries have implemented EEW(early earthquake warning) system to save human lives. The earthquake early warning and rapid response system in Istanbul represents one of the few examples of… Expand
EARTHQUAKE ALERT SYSTEM BASED ON IOT TECHNOLOGY Under the Guidance of P.RAJA
Many countries have implemented EEW(early earthquake warning) system to save human lives. The earthquake early warning and rapid response system in Istanbul represents one of the few examples of… Expand
Towards a semantic model for IoT-based seismic event detection and classification
TLDR
An ontology model for describing the seismic domain is introduced, through the data collection from sensors, to gather seismic signals aimed at the seismic event recognition, and a machine learning-based classification has been accomplished to identify seismic events. Expand
Harnessing the Computing Continuum for Urgent Science
TLDR
An Early Earthquake Warning workflow, which combines data streams from geo-distributed seismometers and high-precision GPS stations to detect large ground motions, is proposed as a system stack that can enable the fluid integration of distributed analytics across a dynamic infrastructure spanning the computing continuum. Expand
Facilitating Data Discovery for Large-scale Science Facilities using Knowledge Networks
  • Yubo Qin, I. Rodero, M. Parashar
  • Computer Science
  • 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
  • 2021
TLDR
This paper develops the collaborative knowledge-aware graph attention network (CKAT) recommendation model, which leverages graph neural networks to explicitly encode the collaborative signals through propagation and combine them with knowledge associations, and integrates aknowledge-aware neural attention mechanism to enable the CKAT to pay more attention to key information while reducing irrelevant noise. Expand
Local Cascade Ensemble for Multivariate Data Classification
TLDR
Evaluation of LCE and LCEM shows that the hybrid ensemble method LCE outperforms the state-of-the-art classifiers on the UCI and UEA datasets and that LCEM provides explainability by design and manifests robust performance when faced with challenges arising from continuous data collection. Expand
Leveraging User Access Patterns and Advanced Cyberinfrastructure to Accelerate Data Delivery from Shared-use Scientific Observatories
TLDR
A push-based data delivery framework that leverages emerging in-network capabilities, along with data pre-fetching techniques based on a hybrid data management model is presented and the ability of the framework to significantly improve data delivery performance and reduce network traffic at the observatories’ facilities is demonstrated. Expand
A Novel Conformal Design for Multi-Sensor System Synthesis
TLDR
Considering the thermal desorption performance of pre-concentration unit and the response delay of multi-sensor in conformal chamber, the optimal airflow speed for the novel e-nose system is solved via Newton method and the conformal design achieves the satisfactory performance compared with conventional design. Expand
International Journal of Social Science and Economic Research
The paper investigates the effect of stock market development on sector-wide GDP using a sample from Sub-Saharan Africa consisting of Botswana, Kenya, Nigeria and South Africa for the period… Expand
Harnessing the Computing Continuum for Urgent Science
Urgent science describes time-critical, data-driven scientific work-flows that can leverage distributed data sources in a timely way to facilitate important decision making. While our capacity for ...
...
1
2
...

References

SHOWING 1-10 OF 28 REFERENCES
Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning
TLDR
This study trains a generative adversarial network to learn the characteristics of first‐arrival earthquake P waves, using 300,000 waveforms recorded in southern California and Japan, and demonstrates that GANs can discover a compact and effective representation of seismic waves, which has the potential for wide applications in seismology. Expand
Convolutional neural network for earthquake detection and location
TLDR
This work leverages the recent advances in artificial intelligence and presents ConvNetQuake, a highly scalable convolutional neural network for earthquake detection and location from a single waveform, and applies it to study the induced seismicity in Oklahoma, USA. Expand
A wireless mesh sensing network for early warning
TLDR
The paper gives a short overview of the approach for developing decentralized early warning systems and an evaluation based on experiences gained from model investigations, testbeds in Berlin, and prototype installations in Istanbul. Expand
Quantifying the Value of Real‐Time Geodetic Constraints for Earthquake Early Warning Using a Global Seismic and Geodetic Data Set
Geodetic earthquake early warning (EEW) algorithms complement point-source seismic systems by estimating fault-finiteness and unsaturated moment magnitude for the largest, most damaging earthquakes.… Expand
On robust and reliable automated baseline corrections for strong motion seismology
TLDR
A proposed automated baseline correction algorithm using only accelerometer data is analyzed and it is found that the error incurred from automated baseline corrections that rely on seismic data alone is complex and can be large in both the time and frequency domains of interest in seismological and engineering applications. Expand
Earthquake detection through computationally efficient similarity search
TLDR
FAST detected most (21 of 24) cataloged earthquakes and 68 uncataloged earthquakes in 1 week of continuous data from a station located near the Calaveras Fault in central California, achieving detection performance comparable to that of autocorrelation, with some additional false detections. Expand
Earthquake Early Warning and Tsunami Warning of JMA for the 2011 off the Pacific Coast of Tohoku Earthquake
The 2011 off the Pacific coast of Tohoku Earthquake (Mw9.0) occurred on March 11, 2011, caused strong ground motion around northeastern Japan, and generated devastating tsunami, which killed more… Expand
Earthquake magnitude calculation without saturation from the scaling of peak ground displacement
GPS instruments are noninertial and directly measure displacements with respect to a global reference frame, while inertial sensors are affected by systematic offsets—primarily tilting—that adversely… Expand
Geospatial Cyberinfrastructure: Past, present and future
TLDR
This paper reviews the research, development, education, and other efforts that have contributed to building GCI in terms of its history, objectives, architecture, supporting technologies, functions, application communities, and future research directions. Expand
Autoregressive forests for multivariate time series modeling
TLDR
Multivariate autoregressive forest, namely mv-ARF, is a nonparametric vector autoregression approach which provides an easy and efficient representation that scales well with large datasets that is very similar to time series kernels used for multivariate time series classification problems. Expand
...
1
2
3
...