A Detailed Earthquake Catalog for Banda Arc–Australian Plate Collision Zone Using Machine-Learning Phase Picker and an Automated Workflow

Jiang, Chengxin; Zhang, Ping; White, Malcolm C. A.; Pickle, R. C.; Miller, Meghan

doi:10.1785/0320210041

Cited by 27 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present-day seismic structure may be further complicated by exotic terranes or microplates formed during the Jurassic breakup of eastern Gondwana (e.g., Supendi et al, 2020;. Most recently, Jiang et al (2022) offers a most complete catalog with data of the YS network, which describes a complex pattern of crustal events across the collisional zone and into the backarc, as well as abundant deep slab seismicity. Anisotropy is also investigated by Harris and Miller (in press) using shear wave splitting, which suggests potential along-strike variations in mantle dynamics.…”

mentioning

confidence: 99%

Tectonic Fabric in the Banda Arc‐Australian Continent Collisional Zone Imaged by Teleseismic Receiver Functions

Zhang

Miller

Schulte-Pelkum

2022

Geochem Geophys Geosyst

Self Cite

View full text Add to dashboard Cite

The Banda Arc-Australian continent collision in eastern Indonesia and Timor-Leste is exemplary of an incipient oblique arc-continent collision. From west to east, the incoming Indo-Australian plate structure transitions from Cretaceous to Jurassic age oceanic lithosphere (Müller et al., 2008) to continental margin lithosphere that is inherently heterogeneous (Harris, 2011;Keep & Haig, 2010;Spakman & Hall, 2010). To the north of the plate boundary, the transition in the incoming plate structure is evident in the linear single volcanic Sunda Arc bifurcating into a double chain of islands (Figure 1a). The northern chain of islands is referred to as the inner arc, composed of volcanic rocks of Neogene age. The southern chain of islands is the non-volcanic outer arc, formed by orogenic structures. The outer arc includes the NNE-SSW oriented islands of Timor, Savu, and Rote and the NNW-SSW striking Sumba Island between the Java Trench-Timor Trough system and the volcanic arc (Figure 1).

show abstract

mentioning

confidence: 99%

Tectonic Fabric in the Banda Arc‐Australian Continent Collisional Zone Imaged by Teleseismic Receiver Functions

Zhang

Miller

Schulte-Pelkum

2022

Geochem Geophys Geosyst

Self Cite

View full text Add to dashboard Cite

show abstract

“…The CRED model does not identify phase arrivals. We choose these two DL models for comparison because EQTransformer is popularly used 8 , 9 and represents the state-of-the-art in general practice, CRED is designed for the sole task of detecting earthquakes (i.e., does not simultaneously identify phases), and the pre-trained models are readily available through the SeisBench 10 package.…”

Section: Resultsmentioning

confidence: 99%

Classifying seismograms using the FastMap algorithm and support-vector machines

White

Sharma

et al. 2023

Commun Eng

Self Cite

View full text Add to dashboard Cite

Neural networks and related deep learning methods are currently at the leading edge of technologies used for classifying complex objects such as seismograms. However they generally demand large amounts of time and data for model training and their learned models can sometimes be difficult to interpret. FastMapSVM is an interpretable machine learning framework for classifying complex objects, combining the complementary strengths of FastMap with support vector machines (SVMs) and extending the applicability of SVMs to domains with complex objects. FastMap is an efficient linear-time algorithm that maps complex objects to points in a Euclidean space while preserving pairwise domain-specific distances between them. Here we invoke FastMapSVM as a lightweight alternative to neural networks for classifying seismograms. We demonstrate that FastMapSVM outperforms other state-of-the-art methods for classifying seismograms when train data or time is limited. We also show that FastMapSVM can provide an insightful visualization of seismogram clustering behaviour and thus earthquake classification boundaries. We expect FastMapSVM to be viable for classification tasks in many other real-world domains.

show abstract

“…Similar to template matching, the recent ML-based method often increases the number of events in catalogs by tenfold compared with conventional approaches (Tan et al 2021;Ma and Chen 2022) with a much lower computation cost (Perol et al 2018). By benefiting from the developments in this field, many studies exploring seismicity with high resolution have been published (Liu et al 2020;Park et al 2020;Ross et al 2020;Wang et al 2020a;Baker et al 2021;Li et al 2021;Jiang et al 2022;Gong et al 2022a;Chen et al 2022a). This improvement in catalog quality is expected to improve earthquake forecasts based on seismicity models (Mancini et al 2022).…”

Section: Importance Of Improving Earthquake Cataloging Methods and Co...mentioning

confidence: 99%

Recent advances in earthquake seismology using machine learning

Kubo,

Naoi,

Kano

2024

Earth Planets Space

View full text Add to dashboard Cite

Given the recent developments in machine-learning technology, its application has rapidly progressed in various fields of earthquake seismology, achieving great success. Here, we review the recent advances, focusing on catalog development, seismicity analysis, ground-motion prediction, and crustal deformation analysis. First, we explore studies on the development of earthquake catalogs, including their elemental processes such as event detection/classification, arrival time picking, similar waveform searching, focal mechanism analysis, and paleoseismic record analysis. We then introduce studies related to earthquake risk evaluation and seismicity analysis. Additionally, we review studies on ground-motion prediction, which are categorized into four groups depending on whether the output is ground-motion intensity or ground-motion time series and the input is features (individual measurable properties) or time series. We discuss the effect of imbalanced ground-motion data on machine-learning models and the approaches taken to address the problem. Finally, we summarize the analysis of geodetic data related to crustal deformation, focusing on clustering analysis and detection of geodetic signals caused by seismic/aseismic phenomena. Graphical Abstract

show abstract

A Detailed Earthquake Catalog for Banda Arc–Australian Plate Collision Zone Using Machine-Learning Phase Picker and an Automated Workflow

Cited by 27 publications

References 37 publications

Tectonic Fabric in the Banda Arc‐Australian Continent Collisional Zone Imaged by Teleseismic Receiver Functions

Tectonic Fabric in the Banda Arc‐Australian Continent Collisional Zone Imaged by Teleseismic Receiver Functions

Classifying seismograms using the FastMap algorithm and support-vector machines

Recent advances in earthquake seismology using machine learning

Contact Info

Product

Resources

About