Denoising of Geodetic Time Series Using Spatiotemporal Graph Neural Networks: Application to Slow Slip Event Extraction

• URL: http://arxiv.org/abs/2405.03320v1
• Date: Mon, 6 May 2024 09:55:11 GMT
• Title: Denoising of Geodetic Time Series Using Spatiotemporal Graph Neural Networks: Application to Slow Slip Event Extraction
• Authors: Giuseppe Costantino, Sophie Giffard-Roisin, Mauro Dalla Mura, Anne Socquet,
• Abstract summary: We design SSE SSEdenois, a graph-based attentive denoiser that learns latent characteristics of noise to reveal SSE-related displacement with sub-millimeter precision. The proposed method is applied to the Cascadia subduction zone, where SSEs occur along with rumbling of tectonic tremors.
• Score: 2.659901499016884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geospatial data has been transformative for the monitoring of the Earth, yet, as in the case of (geo)physical monitoring, the measurements can have variable spatial and temporal sampling and may be associated with a significant level of perturbations degrading the signal quality. Denoising geospatial data is, therefore, essential, yet often challenging because the observations may comprise noise coming from different origins, including both environmental signals and instrumental artifacts, which are spatially and temporally correlated, thus hard to disentangle. This study addresses the denoising of multivariate time series acquired by irregularly distributed networks of sensors, requiring specific methods to handle the spatiotemporal correlation of the noise and the signal of interest. Specifically, our method focuses on the denoising of geodetic position time series, used to monitor ground displacement worldwide with centimeter- to-millimeter precision. Among the signals affecting GNSS data, slow slip events (SSEs) are of interest to seismologists. These are transients of deformation that are weakly emerging compared to other signals. Here, we design SSEdenoiser, a multi-station spatiotemporal graph-based attentive denoiser that learns latent characteristics of GNSS noise to reveal SSE-related displacement with sub-millimeter precision. It is based on the key combination of graph recurrent networks and spatiotemporal Transformers. The proposed method is applied to the Cascadia subduction zone, where SSEs occur along with bursts of tectonic tremors, a seismic rumbling identified from independent seismic recordings. The extracted events match the spatiotemporal evolution of tremors. This good space-time correlation of the denoised GNSS signals with the tremors validates the proposed denoising procedure.

Related papers

• Evaluating ML Robustness in GNSS Interference Classification, Characterization \& Localization [42.14439854721613]
  Jamming devices present a significant threat by disrupting signals from the global navigation satellite system (GNSS) The detection of anomalies within frequency snapshots is crucial to counteract these interferences effectively. This paper introduces an extensive dataset capturing interferences within a large-scale environment including controlled multipath effects.
  arXiv  Detail & Related papers  (2024-09-23T15:20:33Z)
• A Differential Smoothness-based Compact-Dynamic Graph Convolutional Network for Spatiotemporal Signal Recovery [9.369246678101048]
  This paper proposes a Compact-fold Con Graphal Network (CDCN) fortemporal signal recovery. Experiments on real-world datasets show that CDCN significantly outperforms the state-of-the-art models fortemporal signal recovery.
  arXiv  Detail & Related papers  (2024-08-06T06:42:53Z)
• Acceleration Noise Induced Decoherence in Stern-Gerlach Interferometers for Gravity Experiments [0.0]
  Acceleration noises can cause decoherence problems of Stern-Gerlach interferometer. I will theoretically study these mechanisms of decoherence based on the analytical time-evolution operator of an SGI.
  arXiv  Detail & Related papers  (2024-06-16T07:54:34Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection [67.60791405198063]
  We propose a correlation-aware spatial-temporal graph learning (termed CST-GL) for time series anomaly detection. CST-GL explicitly captures the pairwise correlations via a multivariate time series correlation learning module. A novel anomaly scoring component is further integrated into CST-GL to estimate the degree of an anomaly in a purely unsupervised manner.
  arXiv  Detail & Related papers  (2023-07-17T11:04:27Z)
• Characterizing low-frequency qubit noise [55.41644538483948]
  Fluctuations of the qubit frequencies are one of the major problems to overcome on the way to scalable quantum computers. The statistics of the fluctuations can be characterized by measuring the correlators of the outcomes of periodically repeated Ramsey measurements. This work suggests a method that allows describing qubit dynamics during repeated measurements in the presence of evolving noise.
  arXiv  Detail & Related papers  (2022-07-04T22:48:43Z)
• High-Order Qubit Dephasing at Sweet Spots by Non-Gaussian Fluctuators: Symmetry Breaking and Floquet Protection [55.41644538483948]
  We study the qubit dephasing caused by the non-Gaussian fluctuators. We predict a symmetry-breaking effect that is unique to the non-Gaussian noise.
  arXiv  Detail & Related papers  (2022-06-06T18:02:38Z)
• A hybrid approach to seismic deblending: when physics meets self-supervision [0.0]
  We introduce a new concept that consists of embedding a self-supervised denoising network into the Plug-and-Play framework. A novel network is introduced whose design extends the blind-spot network architecture of [28 ] for partially correlated noise. The network is then trained directly on the noisy input data at each step of the supervised time algorithm.
  arXiv  Detail & Related papers  (2022-05-30T19:24:21Z)
• Space-Time Graph Neural Networks [104.55175325870195]
  We introduce space-time graph neural network (ST-GNN) to jointly process the underlying space-time topology of time-varying network data. Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs.
  arXiv  Detail & Related papers  (2021-10-06T16:08:44Z)
• FastHyMix: Fast and Parameter-free Hyperspectral Image Mixed Noise Removal [20.043152870504738]
  This paper introduces a fast and parameter-free hyperspectral image mixed noise removal method (termed FastHyMix) It exploits two main characteristics of hyperspectral data, namely low-rankness in the spectral domain and high correlation in the spatial domain. The proposed method takes advantage of the low-rankness using subspace representation and the correlation of HSIs by adding a powerful deep image prior.
  arXiv  Detail & Related papers  (2021-09-18T08:35:45Z)
• Frequency fluctuations of ferromagnetic resonances at milliKelvin temperatures [50.591267188664666]
  Noise is detrimental to device performance, especially for quantum coherent circuits. Recent efforts have demonstrated routes to utilizing magnon systems for quantum technologies, which are based on single magnons to superconducting qubits. Researching the temporal behavior can help to identify the underlying noise sources.
  arXiv  Detail & Related papers  (2021-07-14T08:00:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.