Filters








573 Hits in 4.5 sec

Recurrent Convolutional Neural Networks help to predict location of Earthquakes [article]

Roman Kail, Alexey Zaytsev, Evgeny Burnaev
2020 arXiv   pre-print
We examine the applicability of modern neural network architectures to the midterm prediction of earthquakes.  ...  Our deep neural network model has a recurrent part (LSTM) that accounts for time dependencies between earthquakes and a convolutional part that accounts for spatial dependencies.  ...  Our architecture is a recurrent neural network with convolutional layers at each time step.  ... 
arXiv:2004.09140v3 fatcat:grgkzpuyavcabaci37gavh5erq

Spatiotemporal Pattern Mining for Nowcasting Extreme Earthquakes in Southern California [article]

Bo Feng, Geoffrey C. Fox
2021 arXiv   pre-print
In this modeling approach, we use synthetic deep learning neural networks with domain knowledge in geoscience and seismology to exploit earthquake patterns for prediction using convolutional long short-term  ...  Most studies of them have many successful applications of using deep neural networks.  ...  We are grateful to Cisco University Research Program Fund grant 2020-220491 for supporting this research. We thank the Futuresystems team for their support.  ... 
arXiv:2012.14336v3 fatcat:3c5qs6dob5hsbcchzbb7d2w6ga

3D Convolution Recurrent Neural Networks for Multi-Label Earthquake Magnitude Classification

Muhammad Shakeel, Kenji Nishida, Katsutoshi Itoyama, Kazuhiro Nakadai
2022 Applied Sciences  
We present an integrated 3-dimensional convolutional recurrent neural network (3D-CNN-RNN) trained to classify the seismic waveforms into multiple categories based on the problem formulation.  ...  We leverage the use of a benchmark dataset comprising of earthquake waveforms having different magnitude and present 3D-CNN-RNN, a highly scalable neural network for multi-label classification problems  ...  With the recent success of recurrent neural networks (RNN) [26] [27] [28] in modeling the dependencies, we propose to employ separate RNNs on each kernel of the last convolutional layer to model the  ... 
doi:10.3390/app12042195 fatcat:5xd36hq43rhr7aqhrdh6zigani

Deep Learning Models Augment Analyst Decisions for Event Discrimination

Lisa Linville, Kristine Pankow, Timothy Draelos
2019 Geophysical Research Letters  
Our approach includes two neural network variations (recurrent and convolutional) to identify events as either quarry blasts or earthquakes.  ...  We explore the use of convolutional and recurrent neural networks to accomplish discrimination of explosive and tectonic sources for local distances.  ...  Any subjective views or opinions that might be expressed in the paper do not necessarily represent the views of the U.S. Department of Energy or the U.S. Government.  ... 
doi:10.1029/2018gl081119 fatcat:tky2ni4er5agzixkh627ahcd7u

Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking

S. Mostafa Mousavi, William L. Ellsworth, Weiqiang Zhu, Lindsay Y. Chuang, Gregory C. Beroza
2020 Nature Communications  
Applying our model to 5 weeks of continuous data recorded during 2000 Tottori earthquakes in Japan, we were able to detect and locate two times more earthquakes using only a portion (less than 1/3) of  ...  Earthquake signal detection and seismic phase picking are challenging tasks in the processing of noisy data and the monitoring of microearthquakes.  ...  Eiichi Fukuyama, Kaz Imanishi, Shin Aoi, Takanori Matsuzawa helped us to acquire HiNet data for the Tottori sequence.  ... 
doi:10.1038/s41467-020-17591-w pmid:32770023 fatcat:7v7fb2fkufckjalvwrelh7fcxa

CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detection [article]

S. Mostafa Mousavi, Weiqiang Zhu, Yixiao Sheng, Gregory C. Beroza
2018 arXiv   pre-print
Here, we introduce the Cnn-Rnn Earthquake Detector (CRED), a detector based on deep neural networks.  ...  The network uses a combination of convolutional layers and bi-directional long-short-term memory units in a residual structure.  ...  Acknowledgments We would like to thank Stephane Zuzlewski for this help in accessing the waveform data and meta data archived in NCEDC.  ... 
arXiv:1810.01965v1 fatcat:tm33346ewrgyppgtmrco4e6ppi

Object Detection Using Convolutional Neural Networks for Natural Disaster Recovery

Deva Salluri, Kalpana Bade, Gargi Madala
2020 International Journal of Safety and Security Engineering  
To make this simple and easy Convolutional Neural Networks (CNN) models are used for object detection of disaster's aftermath.  ...  As there are various types of natural disasters such as hurricanes, tsunamis, floods, earthquakes etc., this study focuses on floods and earthquake images for object detection by using neural networks  ...  Among all these Convolutional Neural Network (CNN) is the best algorithm used for implementing deep learning techniques. CNN is also a kind of ANN.  ... 
doi:10.18280/ijsse.100217 fatcat:gfhwbe5egrdybpa4af6u3wg4ta

A CNN-BiLSTM Model with Attention Mechanism for Earthquake Prediction [article]

Parisa Kavianpour, Mohammadreza Kavianpour, Ehsan Jahani, Amin Ramezani
2021 arXiv   pre-print
Aware of these issues, this paper proposes a novel prediction method based on attention mechanism (AM), convolution neural network (CNN), and bi-directional long short-term memory (BiLSTM) models, which  ...  Nevertheless, due to the stochastic character of earthquakes and the challenge of achieving an efficient and dependable model for earthquake prediction, efforts have been insufficient thus far, and new  ...  Zaytsev, “Recurrent convolutional neural passed into BiLSTM.  ... 
arXiv:2112.13444v1 fatcat:hlmge5ezpzec3d6q6xc5xcdcbm

Editorial

Mirjana Ivanovic, Milos Radovanovic
2020 Computer Science and Information Systems  
"Study of Cardiac Arrhythmia Classification Based on Convolutional Neural Network," authored by Yonghui Dai et al. presents another application of CNNs, in this case studying feature classification of  ...  In "Land-Use Classification via Ensemble Dropout Information Discriminative Extreme Learning Machine Based on Deep Convolution Feature," Tianle Zhang et al. consider combining convolutional neural networks  ...  transformation structure of recurrent neural networks (RNNs).  ... 
doi:10.2298/csis200200ii fatcat:ar5cex7uqnc7phtvgwpfsn47wi

Novel Intelligent Spatiotemporal Grid Earthquake Early-Warning Model

Daoye Zhu, Yi Yang, Fuhu Ren, Shunji Murai, Chengqi Cheng, Min Huang
2021 Remote Sensing  
This model includes a seismic grid sample model (SGSM) and a spatiotemporal grid model based on a three-dimensional group convolution neural network (3DGCNN-SGM).  ...  Five groups of control experiments were designed, namely with the use of atmospheric temperature anomaly data only, use of historical earthquake data only, a non-group convolution control group, a support  ...  Acknowledgments: The author is sincerely grateful for the comments of the anonymous reviewers and members of the editorial team. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs13173426 fatcat:gxdjg7743rhlldezaamus6t5ia

Multivariate Time Series Regression with Graph Neural Networks [article]

Stefan Bloemheuvel and Jurgen van den Hoogen and Dario Jozinović and Alberto Michelini and Martin Atzmueller
2022 arXiv   pre-print
Therefore, in this work, we propose an architecture capable of processing these long sequences in a multivariate time series regression task, using the benefits of Graph Neural Networks to improve predictions  ...  Our model is tested on two seismic datasets that contain earthquake waveforms, where the goal is to predict intensity measurements of ground shaking at a set of stations.  ...  These approaches adapt existing neural network architectures to use operators from the graph domain. Examples are Gated Recurrent GNNs that utilise the spectral convolutions from [28] .  ... 
arXiv:2201.00818v2 fatcat:iwipt5eyuvdx3d3oibxnultjvm

Deep Learning for Geophysics: Current and Future Trends

Siwei Yu, Jianwei Ma
2021 Reviews of Geophysics  
The authors thank Society of Exploration Geophysicists, Nature Research, and American Association for the Advancement of Science for allowing us to reuse the original figures from their journals.  ...  Acknowledgments The work was supported in part by the NSFC under grant nos. 41625017 and 41804102, National Key Research and Development Program of China under grant nos. 2017YFB0202902 and 2018YFC1503705  ...  To detect small and weak earthquake signals robust to strong noise and non-earthquake signals, a residual network with convolutional and recurrent units is developed (Mousavi, Zhu, Sheng, et al., 2019  ... 
doi:10.1029/2021rg000742 fatcat:6ifbu5izhzbxvhjfgmuh3vcznq

Location reference identification from tweets during emergencies: A deep learning approach [article]

Abhinav Kumar, Jyoti Prakash Singh
2019 arXiv   pre-print
This research aims to extract location words used in the tweet using a Convolutional Neural Network (CNN) based model.  ...  We achieved the exact matching score of 0.929, Hamming loss of 0.002, and F_1-score of 0.96 for the tweets related to the earthquake.  ...  Lourentzou et al. (2017) utilized neural network architecture to predict the geo-location of users.  ... 
arXiv:1901.08241v1 fatcat:peujlnaa7bahlpu5gljhbvm42e

İnşaat Mühendisliğinde Derin Öğrenme Algoritmalarının Değerlendirilmesi ve Uygulanması

Melda ALKAN ÇAKIROĞLU, Ahmet Ali SÜZEN
2020 El-Cezeri: Journal of Science and Engineering  
Deep Learning Algorithm has been used which has Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) & Long short-term memory (LSTM) in these applications.  ...  Recurrent Neural Network (RNN) Recurrent Neural Networks (RNN), originally designed by Jeff Elman, are a class of artificial neural networks where connections between nodes form a directed loop [28] .  ... 
doi:10.31202/ecjse.679113 fatcat:5buojg4dsfadtjy4xzvlwogmhi

Fast approximate simulation of seismic waves with deep learning [article]

Benjamin Moseley, Andrew Markham, Tarje Nissen-Meyer
2018 arXiv   pre-print
We simulate the response of acoustic seismic waves in horizontally layered media using a deep neural network.  ...  In contrast to traditional finite-difference modelling techniques our network is able to directly approximate the recorded seismic response at multiple receiver locations in a single inference step, without  ...  We would also like to thank Tom Le Paine for his fast WaveNet implementation on GitHub from which our code was based on (github.com/tomlepaine/fastwavenet).  ... 
arXiv:1807.06873v1 fatcat:63dqxogkxraqjicuh5ubme4m6m
« Previous Showing results 1 — 15 out of 573 results