Identification and spatio-temporal analysis of earthquake clusters using SOM–DBSCAN model

Sharma, Ashish; Vijay, Rahul Kumar; Nanda, Satyasai Jagannath

doi:10.1007/s00521-022-08085-5

Cited by 4 publications

(1 citation statement)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, Bountzis et al [20] present a two step clustering algorithm called the Markovian Arrival Process-(MAP-DBSCAN) to detect change-points in the seismicity rate and subsequently, clustering seismic events in selected areas of Greece. Recently, Sharma [21] proposed two-stage method, based on Self-Organized Map and Density-based Temporal Clustering techniques, for implementing an effective spatiotemporal clustering by identifying the aftershock clusters and background events. The experimental study was carried out on some earthquake catalogues of different part of the world, and compared with benchmark declustering algorithms.…”

Section: Introductionmentioning

confidence: 99%

Space-time clustering of seismic events in Chile using ST-DBSCAN-EV algorithm

Nicolis,

Delgado,

Peralta

et al. 2024

Environ Ecol Stat

View full text Add to dashboard Cite

Chile is one of the most seismic countries in the world especially due to the subduction of the Nazca plate under the South America plate along the Chilean cost. Normally, the spatial distribution of seismic events tends to form spatial and temporal clusters around the main event including both precursor and aftershock events. However, it is very difficult to identify whether an event is a precursor, a main event or an aftershock. In the literature, only some large earthquakes are well described but it does not exist an automatic method to classify them. In this work, we propose a new density based clustering method, called ST-DBSCAN-EV (Space-time DBSCAN with Epsilon Variable), which allows the Epsilon parameter (the radius) to vary depending on the density of the points. The results of the ST-DBSCAN-EV are validated on three important earthquakes with magnitude greater than 8.0 Mw occurred in Chile in the last 20 years, by carrying out a series of experiments considering different combinations of parameters. A comparison with some traditional clustering techniques such as the DBSCAN, ST-DBSCAN, and the K-Means has been implemented for assessing the performance of the proposed method. Almost in all cases ST-DBSCAN-EV outperformed traditional ones by providing an F1-Score metric higher than 0.8. Finally, the results of classification are compared with a declustering method.

show abstract

Section: Introductionmentioning

confidence: 99%