Centre de documentation
scientifique

Wavelet-like denoising of GNSS data through machine learning. Application to the time series of the Campi Flegrei volcanic area (Southern Italy) / Rolando Carbonari in Geomatics, Natural Hazards and Risk, vol 14 n° 1 (2023)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 14 n° 1 (2023) . - n° 2187271 Titre : Wavelet-like denoising of GNSS data through machine learning. Application to the time series of the Campi Flegrei volcanic area (Southern Italy) Type de document : Article/Communication Auteurs : Rolando Carbonari, Auteur ; Umberto Riccardi, Auteur ; Prospero De Martino, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 2187271 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes IGN] caldeira [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] déformation de la croute terrestre [Termes IGN] données GNSS [Termes IGN] filtrage du bruit [Termes IGN] Naples [Termes IGN] relief volcanique [Termes IGN] risque naturel [Termes IGN] série temporelle [Termes IGN] surveillance géologique [Termes IGN] transformation en ondelettes Résumé : (auteur) The great potential of the Global Navigation Satellite System (GNSS) in monitoring ground deformation is widely recognized. As with other geophysical data, GNSS time series can be significantly noisy, hiding elusive ground deformation signals. Several denoising techniques have been proposed to improve the signal-to-noise ratio over the years. One of the most effective denoising techniques has been proved to be multi-resolution decomposition through the discrete wavelet transform. However, wavelet analysis requires long data sets to be effective, as well as long computation times, that hinder its use as a real or near real-time monitoring tool. We propose training by a Convolutional Neural Network (CNN) to perform the equivalent of wavelet analysis to overcome these limitations. Once trained, the CNN model provides answers within seconds, making it feasible as a real-time data analysis tool. Our Machine Learning algorithm is tested on daily GNSS time series collected in the Campi Flegrei caldera (Southern Italy), which is a highly volcanic risk area. Without significant gaps, the retrieved RMSE and R2 values vary in the ranges 0.65–0.98 and 0.06–0.52 cm, respectively. These results are encouraging, as they hint at the possibility of applying this methodology in more effective real-time monitoring solutions for active volcanoes. Numéro de notice : A2023-180 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1080/19475705.2023.2187271 Date de publication en ligne : 10/03/2023 En ligne : https://doi.org/10.1080/19475705.2023.2187271 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102949 [article]

Radial interpolation of GPS and leveling data of ground deformation in a resurgent caldera: application to Campi Flegrei (Italy) / Andrea Bevilacqua in Journal of geodesy, vol 94 n°2 (February 2020)  

Public [article]  inJournal of geodesy > vol 94 n°2 (February 2020) Titre : Radial interpolation of GPS and leveling data of ground deformation in a resurgent caldera: application to Campi Flegrei (Italy) Type de document : Article/Communication Auteurs : Andrea Bevilacqua, Auteur ; Augusto Neri, Auteur ; Prospero De Martino, Auteur ; et al., Auteur Année de publication : 2020 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] analyse diachronique [Termes IGN] caldeira [Termes IGN] Campanie (Italie) [Termes IGN] déformation horizontale de la croute terrestre [Termes IGN] déformation verticale de la croute terrestre [Termes IGN] données géodésiques [Termes IGN] données GPS [Termes IGN] fonction de base radiale [Termes IGN] image radar moirée [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] interpolation [Termes IGN] modèle de déformation tectonique [Termes IGN] régression linéaire [Termes IGN] réseau de nivellement [Termes IGN] surveillance géologique [Termes IGN] volcan Résumé : (auteur) This study presents a new method, called the Radial Interpolation Method, to interpolate data characterized by an approximately radial pattern around a relatively constrained central zone, such as the ground deformation patterns shown in many active volcanic areas. The method enables the fast production of short-term deformation maps on the base of spatially sparse ground deformation measurements and can provide uncertainty quantification on the interpolated values, fundamental for hazard assessment purposes and deformation source reconstruction. The presented approach is not dependent on a priori assumptions about the geometry, location and physical properties of the source, except for the requirement of a locally radial pattern, i.e., allowing multiple centers of symmetry. We test the new method on a synthetic point source example, and then, we apply the method to selected time intervals of real geodetic data collected at the Campi Flegrei caldera during the last 39 years, including examples of leveling, Geodetic Precise Traversing measurements and Global Positioning System. The maps of horizontal displacement, calculated inland, show maximum values lying along a semicircular annular region with a radius of about 2–3 km in size. This semi-annular area is marked by mesoscale structures such as faults, sand dikes and fractures. The maps of vertical displacement describe a linear relation between the maximum vertical uplift measured and the volume variation. The multiplicative factor in the linear relation is about 0.3 × 106 m3/cm if we estimate the proportion of the ΔV that is captured by the GPS network onland and we use this to estimate the full ΔV. In this case, the 95% confidence interval on K because of linear regression is ± 5%. Finally, we briefly discuss how the new method could be used for the production of short-term vent opening maps on the base of real-time geodetic measurements of the horizontal and vertical displacements. Numéro de notice : A2020-152 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-020-01355-x Date de publication en ligne : 05/02/2020 En ligne : https://doi.org/10.1007/s00190-020-01355-x Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94785 [article]