Mosaicking Andean morphostructure and seismic cycle crustal deformation patterns using GNSS velocities and machine learning

Aug 5, 2026

Upload by Jiven

Unsupervised machine learning is used to characterize continental-scale crustal motions in Chilean subduction zones affected by the seismic cycle. Agglomerative clustering analyzes spatial patterns in GNSS regional velocities without requiring a physical source model, using a continental velocity field from two time windows (pre-2014 and 2018–2021) and comparing two GNSS-derived feature-preprocessing strategies. Results map first-order deformation patterns linked to interplate coupling variations and postseismic relaxation, while a second approach estimates strain and rotation rates under network heterogeneity via least-squares inversions and Bayesian model selection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Machine learning approach for GNSS velocity mosaics

Feature preprocessing strategies

Strain and rotation estimation with Bayesian model selection

Spatial correlation with seismic segmentation and geology

TYPE Original Research PUBLISHED 27 March 2023 DOI 10.3389/feart.2023.1096238 OPEN ACCESS EDITED BY Angelo De Santis, Istituto Nazionale di Geofisica e Vulcanologia (INGV), Italy REVIEWED BY Mohammad Radad, Shahrood University of Technology, Iran Keyvan Khayer, Shahrood University of Technology, Iran Amin Roshandel Kahoo, Shahrood University of Technology, Iran *CORRESPONDENCE Vicente Yáñez-Cuadra, [vicenteyanez@proton. me](vicenteyanez@proton. me)[ ](vicenteyanez@proton. me)† PRESENT ADDRESS Marcos Moreno, Departamento de Ingeniería Estructural y Geotécnica, Pontificia Universidad Católica, Santiago, Chile SPECIALTY SECTION This article was submitted to Solid Earth Geophysics, a section of the journal Frontiers in Earth Science RECEIVED 11 November 2022 ACCEPTED 11 January 2023 PUBLISHED 27 March 2023 CITATION Yáñez-Cuadra V, Moreno M, Ortega-Culaciati F, Donoso F, Báez JC and Tassara A (2023), Mosaicking Andean morphostructure and seismic cycle crustal deformation patterns using GNSS velocities and machine learning. Front. Earth Sci. 11:1096238 . doi: 10.3389/feart.2023.1096238 COPYRIGHT © 2023 Yáñez-Cuadra, Moreno, Ortega-Culaciati, Donoso, Báez and Tassara. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Mosaicking Andean morphostructure and seismic cycle crustal deformation patterns using GNSS velocities and machine learning Vicente Yáñez-Cuadra 1*, Marcos Moreno 1†, Francisco Ortega-Culaciati 2, Felipe Donoso 1, Juan Carlos Báez 3 and Andrés Tassara 4 1 Departamento de Geofísica, Facultad de Ciencias Físicas y Matemáticas, Universidad de Concepción, Concepción, Chile, 2 Departamento de Geofísica, Facultad de Ciencias Físicas y Matemáticas, Universidad de Chile, Santiago, Chile, 3Centro Sismológico Nacional, Santiago, Chile, 4 Departamento de Ciencias de la Tierra, Facultad de Ciencias Químicas, Universidad de Concepción, Concepción, Chile We use unsupervised machine learning techniques to analyze continental-scale crustal motions in areas affected by the seismic cycle of large subduction earthquakes along the Chilean Trench. Specifically, we use the agglomerative clustering algorithm as an exploratory tool to investigate spatial patterns in GNSS regional velocities without the complexity of modeling a physical source. We present a continental-scale velocity field including all available GNSS data for two-time windows (pre-2014, 2018–2021) that represents two periods with different deformation patterns of the seismic cycle. We test two different preprocessing methodologies for the design of machine learning features from the GNSS-derived velocities. The first method uses the direction and magnitude of the secular rates as input features to the clustering algorithm. These results show a clustering spatially related to seismic cycle deformation, separating latitudinal segments with different velocities in the fore-arc and back-arc, as well as regions affected by postseismic relaxation. Thus, highlighting the effectiveness of this method for mapping first-order patterns of active deformation in a subduction zone, that are particularly related to variations on interplate coupling and postseismic transient deformation. In a more sophisticated approach, we use surface strain and rotational rates from GNSS velocities as features in the second methodology. Here, we develop a novel methodology to estimate strain and rotation rates accounting for the spatial heterogeneity of the GNSS-network. We determine the spatial scale at which these features are estimated by least sq

FAQs

How do the findings relate to tectonics and geology?

The results show spatial correlations between fore-arc seismic segmentation and geological/structural domains across the arc and back-arc, supporting the influence of Andean structures on the observed deformation field.

Aug 5, 2026

Upload by Jiven