{ "id": 190942, "title": "Papers on seismicity, volcanology and predicting eruptions", "url": "/competitions/predict-volcanic-eruptions-ingv-oe/discussion/190942", "author_name": "", "post_date": "2020-10-13T23:01:28.521815400Z", "votes": 14, "comment_count": 1, "views": 0, "content": "

Hey everyone!

\n

I wanted to start a research paper thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!

\n

Research Papers:

\n\n

Tangential interest:

\n", "messages": [ { "id": "1048893", "postDate": "10/13/2020 23:01:28", "content": "

Hey everyone!

\n

I wanted to start a research paper thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!

\n

Research Papers:

\n\n

Tangential interest:

\n", "rawMarkdown": "Hey everyone!\n\nI wanted to start a research paper thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\n**Research Papers:**\n* [The transformer earthquake alerting model: A new versatile approach to earthquake early warning](https://arxiv.org/abs/2009.06316) - Here we propose a novel early warning method, the deep-learning based transformer earthquake alerting model (TEAM). TEAM analyzes raw, strong motion waveforms of an arbitrary number of stations at arbitrary locations in real-time, making it easily adaptable to changing seismic networks.\n\n* [Statistical characterization and time-series modeling of seismic noise](https://arxiv.org/abs/2009.01549) - The objectives of this work are (i) to critically study these long-held assumptions and (ii) to propose a systematic procedure for developing appropriate time-series models.\n\n* [Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale](https://arxiv.org/abs/2008.02903) - In this study we present a large dataset of seismograms recorded along the vertical, north, and east components of 1487 broad-band or very broad-band receivers distributed worldwide; this includes 629,095 3-component seismograms generated by 304,878 local earthquakes and labeled as EQ, and 615,847 ones labeled as noise (AN). Application of machine learning to this dataset shows that a simple Convolutional Neural Network of 67,939 parameters allows discriminating between earthquakes and noise single-station recordings, even if applied in regions not represented in the training set. Achieving an accuracy of 96.7, 95.3, and 93.2% on training, validation, and test set\n\n* [Screening of seismic records for performing time-history dynamic analyses of tailings dams: a power-spectral based approach](https://arxiv.org/abs/2009.06426) - \nIn this study, a new semi-analytical procedure for evaluating the seismic demand imposed by a given seismic record on a tailings dam is proposed. The procedure employs the spectral properties of the record filtered by those of the dam.\n\n* [A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets](https://arxiv.org/abs/1905.07286) - The ability of machine learning to automatically identify signals of interest in these large InSAR datasets has already been demonstrated, but data-driven techniques, such as convolutional neutral networks (CNN) require balanced training datasets of positive and negative signals to effectively differentiate between real deformation and noise.\n\n* [Seismic Inversion by Hybrid Machine Learning](https://arxiv.org/abs/2009.06846) - We present a new seismic inversion met hod that uses deep learning (DL) features for the subsurface velocity model estimation. The DL feature is a low-dimensional representation of the high-dimensional seismic data, which is automatically generated by a convolutional autoencoder (CAE) and preserved in the latent space.\n\n* [Kernel Ridge Regression Using Importance Sampling with Application to Seismic Response Prediction](https://arxiv.org/abs/2009.09136) - In this paper, our contribution is twofold. The first contribution is to propose a novel landmark selection method that promotes diversity using an efficient two-step approach. Our landmark selection technique follows a coarse to fine strategy, where the first step computes importance scores with a single pass over the whole data. The second step performs K-means clustering on the constructed coreset to use the obtained centroids as landmarks.\n\n* [Unsupervised seismic facies classification using deep convolutional autoencoder](https://arxiv.org/abs/2008.01995) - We apply a deep convolutional autoencoder for unsupervised seismic facies classification, which does not require manually labeled examples. The facies maps are generated by clustering the deep-feature vectors obtained from the input data. Our method yields accurate results on real data and provides them instantaneously. The proposed approach opens up possibilities to analyze geological patterns in real time without human intervention.\n\n* [Improving the Robustness of the Advanced LIGO Detectors to Earthquakes](https://arxiv.org/abs/2007.12847) - Our method greatly improved the interferometers' capability to remain operational during earthquakes, with ground velocities up to 3.9\\,μm/s rms in the beam direction, setting a new record for both detectors.\n\n* [SeismoFlow -- Data augmentation for the class imbalance problem](https://arxiv.org/abs/2007.12229) - In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance.\n\n* [Point process models for quasi-periodic volcanic earthquakes](https://arxiv.org/abs/1803.07688) - We evaluate the performance of candidate formulations for LP data, based on inhomogeneous point process models with four different inter-event time distributions: exponential (IP), Gamma (IG), inverse Gaussian (IIG), and Weibull (IW). We examine how well these models explain the observed data, and the quality of retrospective forecasts of eruption time. We use a Bayesian MCMC approach to fit the models.\n\n**Tangential interest:**\n* [Deep reconstruction of strange attractors from time series](https://arxiv.org/abs/2002.05909) \n[Associated Code](https://github.com/williamgilpin/fnn)\nInspired by classical techniques for studying the strange attractors of chaotic systems, we introduce a general embedding technique for time series, consisting of an autoencoder trained with a novel latent-space loss function. We show that our technique reconstructs the strange attractors of synthetic and real-world systems better than existing techniques, and that it creates consistent, predictive representations of even stochastic systems.\n\n* [Asymmetric prior in wavelet shrinkage](https://arxiv.org/abs/2010.04666) - Statistical properties such as bias, variance, classical and bayesian risks of the associated asymmetric rule are provided and performances of the proposed rule are obtained in simulation studies involving artificial asymmetric distributed coefficients and the Donoho-Johnstone test functions. Application in a seismic real dataset is also analyzed.", "votes": null }, { "id": "1132998", "postDate": "12/30/2020 21:04:00", "content": "

Thanks, it's really helpful!

", "rawMarkdown": "Thanks, it's really helpful!", "votes": null } ], "comments": [ { "id": 1132998, "author_name": "hobowang", "author_url": "", "post_date": "12/30/2020 21:04:00", "content": "

Thanks, it's really helpful!

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1048893": "Hey everyone!\n\nI wanted to start a research paper thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\n**Research Papers:**\n* [The transformer earthquake alerting model: A new versatile approach to earthquake early warning](https://arxiv.org/abs/2009.06316) - Here we propose a novel early warning method, the deep-learning based transformer earthquake alerting model (TEAM). TEAM analyzes raw, strong motion waveforms of an arbitrary number of stations at arbitrary locations in real-time, making it easily adaptable to changing seismic networks.\n\n* [Statistical characterization and time-series modeling of seismic noise](https://arxiv.org/abs/2009.01549) - The objectives of this work are (i) to critically study these long-held assumptions and (ii) to propose a systematic procedure for developing appropriate time-series models.\n\n* [Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale](https://arxiv.org/abs/2008.02903) - In this study we present a large dataset of seismograms recorded along the vertical, north, and east components of 1487 broad-band or very broad-band receivers distributed worldwide; this includes 629,095 3-component seismograms generated by 304,878 local earthquakes and labeled as EQ, and 615,847 ones labeled as noise (AN). Application of machine learning to this dataset shows that a simple Convolutional Neural Network of 67,939 parameters allows discriminating between earthquakes and noise single-station recordings, even if applied in regions not represented in the training set. Achieving an accuracy of 96.7, 95.3, and 93.2% on training, validation, and test set\n\n* [Screening of seismic records for performing time-history dynamic analyses of tailings dams: a power-spectral based approach](https://arxiv.org/abs/2009.06426) - \nIn this study, a new semi-analytical procedure for evaluating the seismic demand imposed by a given seismic record on a tailings dam is proposed. The procedure employs the spectral properties of the record filtered by those of the dam.\n\n* [A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets](https://arxiv.org/abs/1905.07286) - The ability of machine learning to automatically identify signals of interest in these large InSAR datasets has already been demonstrated, but data-driven techniques, such as convolutional neutral networks (CNN) require balanced training datasets of positive and negative signals to effectively differentiate between real deformation and noise.\n\n* [Seismic Inversion by Hybrid Machine Learning](https://arxiv.org/abs/2009.06846) - We present a new seismic inversion met hod that uses deep learning (DL) features for the subsurface velocity model estimation. The DL feature is a low-dimensional representation of the high-dimensional seismic data, which is automatically generated by a convolutional autoencoder (CAE) and preserved in the latent space.\n\n* [Kernel Ridge Regression Using Importance Sampling with Application to Seismic Response Prediction](https://arxiv.org/abs/2009.09136) - In this paper, our contribution is twofold. The first contribution is to propose a novel landmark selection method that promotes diversity using an efficient two-step approach. Our landmark selection technique follows a coarse to fine strategy, where the first step computes importance scores with a single pass over the whole data. The second step performs K-means clustering on the constructed coreset to use the obtained centroids as landmarks.\n\n* [Unsupervised seismic facies classification using deep convolutional autoencoder](https://arxiv.org/abs/2008.01995) - We apply a deep convolutional autoencoder for unsupervised seismic facies classification, which does not require manually labeled examples. The facies maps are generated by clustering the deep-feature vectors obtained from the input data. Our method yields accurate results on real data and provides them instantaneously. The proposed approach opens up possibilities to analyze geological patterns in real time without human intervention.\n\n* [Improving the Robustness of the Advanced LIGO Detectors to Earthquakes](https://arxiv.org/abs/2007.12847) - Our method greatly improved the interferometers' capability to remain operational during earthquakes, with ground velocities up to 3.9\\,μm/s rms in the beam direction, setting a new record for both detectors.\n\n* [SeismoFlow -- Data augmentation for the class imbalance problem](https://arxiv.org/abs/2007.12229) - In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance.\n\n* [Point process models for quasi-periodic volcanic earthquakes](https://arxiv.org/abs/1803.07688) - We evaluate the performance of candidate formulations for LP data, based on inhomogeneous point process models with four different inter-event time distributions: exponential (IP), Gamma (IG), inverse Gaussian (IIG), and Weibull (IW). We examine how well these models explain the observed data, and the quality of retrospective forecasts of eruption time. We use a Bayesian MCMC approach to fit the models.\n\n**Tangential interest:**\n* [Deep reconstruction of strange attractors from time series](https://arxiv.org/abs/2002.05909) \n[Associated Code](https://github.com/williamgilpin/fnn)\nInspired by classical techniques for studying the strange attractors of chaotic systems, we introduce a general embedding technique for time series, consisting of an autoencoder trained with a novel latent-space loss function. We show that our technique reconstructs the strange attractors of synthetic and real-world systems better than existing techniques, and that it creates consistent, predictive representations of even stochastic systems.\n\n* [Asymmetric prior in wavelet shrinkage](https://arxiv.org/abs/2010.04666) - Statistical properties such as bias, variance, classical and bayesian risks of the associated asymmetric rule are provided and performances of the proposed rule are obtained in simulation studies involving artificial asymmetric distributed coefficients and the Donoho-Johnstone test functions. Application in a seismic real dataset is also analyzed.", "1132998": "Thanks, it's really helpful!" }, "source": "meta" }