Effect of solid-earth-tide on GPS time series

The solid-earth-tide models IERS1992 and IERS2003 are used to analyze some GPS-baseline,vertical-component and zenith-tropospheric-delay data from the Crustal Movement GPS Continuous Observation Net-work of Shandong and IGS stations. The results show that the differences between the baselines computed with the different models are at sub-millimeter level, and the differences in vertical component is direct proportional to station latitude. Also the amplitude of ZTD differences is about 0. 6-1.0 mm, which is 6% -8% of the amplitude of solid-earth-tide differences. Although these effects are quite small, to analyze non-tidal deformation correctly, we should still use a single standard for processing GPS data.

Extraction of transient signal from GPS position time series by employing ICA

Transient deformation,such as post-seismic slip,slow slip and pre-seismic slip events,is a limited lowfrequency deformation that can last for hours to months,in contrast to a sudden slip on a fault caused by earthquakes.Continuous Global Positioning System(CGPS),one of the most common geodetic techniques for continuously monitoring crustal deformation,is capable of capturing transient deformation signals.A critical point in characterizing transient deformation signals is the development of extracting and deciphering transient deformation signals from a huge and messy data set of position time series.Principal Component Analysis(PCA),one of the data-driven methods,has been employed to derive transient deformation signals from position time series combing with Kalman filtering.Independent Component Analysis(ICA)performs well in recovering and separating the sources of observed data,however,it is rarely used in extracting transient deformation signals.We aim to decompose the transient deformation signals from the daily GPS observation deployed in Akutan Island from 2007 to 2015 with the ICA method and obtain the spatiotemporal responses to the source signals of transient deformation.Our results indicate that ICA method can also characterize effectively transient deformation signals spatially and temporally.Additionally,the independent relationship between sources obtained by ICA allows for flexibility in linearly combining different sources.

A new method for coseismic offset detection from GPS coordinate time series

Currently,the extraction of coseismic offset signals primarily relies on earthquake catalog data to determine the occurrence time of earthquakes.This is followed by the process of differencing the average GPS coordinate time series data,with a time interval of 3 to 5 days before and after the earthquake.In the face of the huge amount of GPS coordinate time series data today,the conventional approach of relying on earthquake catalog data to assist in obtaining coseismic offset signals has become increasingly burdensome.To address this problem,we propose a new method for automatically detecting coseismic offset signals in GPS coordinate time series without an extra earthquake catalog for reference.Firstly,we pre-process the GPS coordinate time series data for filtering out stations with significant observations missing and detecting and removing outliers.Secondly,we eliminate other signals and errors in the GPS coordinate time series,such as trend and seasonal signals,leaving the coseismic offset signals as the primary signal.The resulting coordinate time series is then modeled using the first-order difference and data stacking method.The modeling method enables automatic detection of the coseismic offset signals in the GPS coordinate time series.The aforementioned method is applied to automatically detect coseismic offset signals using simulated data and the Searles Valley GPS data in California,USA.The results demonstrate the efficacy of our proposed method,successfully detecting coseismic offsets from vast amounts of GPS coordinate time series data.

Study of the effects on GPS coordinate time series caused by higher-order ionospheric corrections calculated using the DIPOLE model

As one of the main error sources in high-precision Global Positioning System （GPS） data processing, higher-order ionospheric （HOI） delays cause significant effects on coordinate time series that cannot be ignored in analyses of long time series. Typically two geomagnetic models, DIPOLE model and Inter- national Geomagnetic Reference Field （IGRF） model, are used for calculating HOI corrections. This paper investigates the effects of HOI correction caused by the DIPOLE model on coordinate time series. GPS data from 104 globally distributed International GNSS Service （IGS） stations spanning from January, 1999 to December, 2003 were reprocessed following up-to-date processing strategies utilizing GAMIT and GLOBK software. Two coordinate time series solutions before and after applying HOI corrections using the DIPOLE model were derived for studying the effects in terms of seasonal variations and noise amplitudes. The results show that after applying the HOI corrections calculated with DIPOLE, the noise amplitudes of the coordinate time series increased, especially in the north and east directions, and the increased amplitudes of the flicker noise were larger than those of the white noise. Furthermore, spurious periodic signals that were probably introduced by the HOI corrections from the DIPOLE model were also found. Moreover, an apparent increase was confirmed for the power spectra of most of the stations, especially in the north direction, and the amplitudes of both the annual and semi-annual signals also increased in the north and east directions. It can be inferred that the quality of the external data sources such as the geomagnetic model might be the key factors that lead to the above results. The results also suggest that we should be very careful when the DIPOLE model is used for HOI corrections.

The Application of the Bursa Model to the Integration of GPS Time Series

In this paper the method of combining the Bursa model to integrate several regional time series to derive a unified global time series is introduced in detail. Then,an example taken from CMONOC( Crustal Movement Observation Network of China) is used to test if the combination method is feasible. The precision of the integrated time series with the combination method is below 2mm( North),3mm( East),that is same as the results from the direct integration of the time series and the precision of the baseline is below 6mm,which proves that the combination method can be used to integrate several regional time series to derive a unified global time series.

GPS time-series and its response to M_S=8.1 Kunlunshan earthquake

In this paper, observation data in 25 GPS reference stations of China have been analyzed by calculating GPS position coordinate time-series with GIPSY. Result shows there is an obvious trend variation in such time-series. The trend variations of time series along the longitude and latitude coordinate reflect the motion of each position in the global-plate, in which the trend variation in the vertical direction reveals some large-scale construction information or reflects the local movement around the positions. The analysis also shows that such time-series have a variation cycle of nearly 1.02 a, but the reason still remains to be further studied. At the end of this paper, response of the time-series to MS=8.1 Kunlunshan earthquake was analyzed, and the seismogenic process of MS=8.1 Kunlunshan earthquake, according to the time proceeding and the feature of anomaly, was divided into 3 phases-changes in blocks with forces, strain accumulation, quick accumulation and slow release of energy. At the initial stage of seismogenic process of MS=8.1 earthquake and at the imminent earthquake, coseismic process as well as during the post earthquake recovery, anomaly in vertical direction is always in a majority. The anomalous movement in vertical direction at the initial stage resulted in a blocking between faults, while at the middle stage of seismogenic process, the differential movement between blocks are in a majority, which is the major reason causing energy accumulating at the blocking stage of faults.

Time series prediction of reservoir bank landslide failure probability considering the spatial variability of soil properties

Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stability of reservoir banks changes with the long-term dynamics of external disastercausing factors.Thus,assessing the time-varying reliability of reservoir landslides remains a challenge.In this paper,a machine learning(ML)based approach is proposed to analyze the long-term reliability of reservoir bank landslides in spatially variable soils through time series prediction.This study systematically investigated the prediction performances of three ML algorithms,i.e.multilayer perceptron(MLP),convolutional neural network(CNN),and long short-term memory(LSTM).Additionally,the effects of the data quantity and data ratio on the predictive power of deep learning models are considered.The results show that all three ML models can accurately depict the changes in the time-varying failure probability of reservoir landslides.The CNN model outperforms both the MLP and LSTM models in predicting the failure probability.Furthermore,selecting the right data ratio can improve the prediction accuracy of the failure probability obtained by ML models.

Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

Unsupervised Time Series Segmentation: A Survey on Recent Advances

Time series segmentation has attracted more interests in recent years,which aims to segment time series into different segments,each reflects a state of the monitored objects.Although there have been many surveys on time series segmentation,most of them focus more on change point detection(CPD)methods and overlook the advances in boundary detection(BD)and state detection(SD)methods.In this paper,we categorize time series segmentation methods into CPD,BD,and SD methods,with a specific focus on recent advances in BD and SD methods.Within the scope of BD and SD,we subdivide the methods based on their underlying models/techniques and focus on the milestones that have shaped the development trajectory of each category.As a conclusion,we found that:(1)Existing methods failed to provide sufficient support for online working,with only a few methods supporting online deployment;(2)Most existing methods require the specification of parameters,which hinders their ability to work adaptively;(3)Existing SD methods do not attach importance to accurate detection of boundary points in evaluation,which may lead to limitations in boundary point detection.We highlight the ability to working online and adaptively as important attributes of segmentation methods,the boundary detection accuracy as a neglected metrics for SD methods.

Improved Responses with Multitaper Spectral Analysis for Magnetotelluric Time Series Data Processing:Examples from Field Data

In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without a multitaper approach for spectral estimation.There are several common ways to increase the reliability of the Fourier spectral estimation from experimental(noisy)data;for example to subdivide the experimental time series into segments,taper these segments(using single taper),perform the Fourier transform of the individual segments,and average the resulting spectra.

An Innovative Deep Architecture for Flight Safety Risk Assessment Based on Time Series Data

With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.

Periodic signal extraction of GNSS height time series based on adaptive singular spectrum analysis

Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.

Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.

A novel framework for predicting non-stationary production time series of shale gas based on BiLSTM-RF-MPA deep fusion model

Shale gas, as an environmentally friendly fossil energy resource, has gained significant commercial development and shows immense potential. However, accurately predicting shale gas production faces substantial challenges due to the complex law of decline, nonlinear and non-stationary features in production data, which greatly repair the robustness of current models in predicting shale gas production time series. To address these challenges and improve accuracy in production forecasting, this paper introduces a novel and innovative approach: a hybrid proxy model that combines the bidirectional long short-term memory(BiLSTM) neural network and random forest(RF) through deep learning. The BiLSTM neural network is adept at capturing long-term dependencies, making it suitable for understanding the intricate relationships between input and output variables in shale gas production.On the other hand, RF serves a dual purpose: reducing model variance and addressing the concept drift problem that arises in non-stationary time series predictions made by BiLSTM. By integrating these two models, the hybrid approach effectively captures the inherent dependencies present in long and nonstationary production time series, thereby reducing model uncertainty. Furthermore, the combination of BiLSTM and RF is optimized using the recently-proposed marine predators algorithm(MPA) to fine-tune hyperparameters and enhance the overall performance of the proxy model. The results demonstrate that the proposed BiLSTM-RF-MPA model achieves higher prediction accuracy and demonstrates stronger generalization capabilities by effectively handling the complex nonlinear and non-stationary characteristics of shale gas production time series. Compared to other models such as LSTM, BiLSTM, and RF, the proposed model exhibits superior fitting and prediction performance, with an average improvement in performance indicators exceeding 20%. This innovative framework provides valuable insights for forecasting the complex production performance of unconventional oil and gas reservoirs, which sheds light on the development of data-driven proxy models in the field of subsurface energy utilization.

TSCND:Temporal Subsequence-Based Convolutional Network with Difference for Time Series Forecasting

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

Advancing Autoencoder Architectures for Enhanced Anomaly Detection in Multivariate Industrial Time Series

In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.

CNN-LSTM based incremental attention mechanism enabled phase-space reconstruction for chaotic time series prediction

To improve the prediction accuracy of chaotic time series and reconstruct a more reasonable phase space structure of the prediction network,we propose a convolutional neural network-long short-term memory(CNN-LSTM)prediction model based on the incremental attention mechanism.Firstly,a traversal search is conducted through the traversal layer for finite parameters in the phase space.Then,an incremental attention layer is utilized for parameter judgment based on the dimension weight criteria(DWC).The phase space parameters that best meet DWC are selected and fed into the input layer.Finally,the constructed CNN-LSTM network extracts spatio-temporal features and provides the final prediction results.The model is verified using Logistic,Lorenz,and sunspot chaotic time series,and the performance is compared from the two dimensions of prediction accuracy and network phase space structure.Additionally,the CNN-LSTM network based on incremental attention is compared with long short-term memory(LSTM),convolutional neural network(CNN),recurrent neural network(RNN),and support vector regression(SVR)for prediction accuracy.The experiment results indicate that the proposed composite network model possesses enhanced capability in extracting temporal features and achieves higher prediction accuracy.Also,the algorithm to estimate the phase space parameter is compared with the traditional CAO,false nearest neighbor,and C-C,three typical methods for determining the chaotic phase space parameters.The experiments reveal that the phase space parameter estimation algorithm based on the incremental attention mechanism is superior in prediction accuracy compared with the traditional phase space reconstruction method in five networks,including CNN-LSTM,LSTM,CNN,RNN,and SVR.