Anomaly detection of earthquake precursor data using long short-term memory networks

Cai, Yin; Shyu, Mei Ling; Tu, Yue; Teng, Yun; Hu, Xing

doi:10.1007/s11770-019-0774-1

Cited by 29 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Task-based research is also affected by task types. Internal linguistic factors refer to a language phenomenon or feature that may have an impact on the performance and development of CAF due to its special attributes (such as attributive clauses), and external factors include individual learner differences (such as anxiety, devotion, and academic ability) [9].…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Synthetic Network and Search Filter Algorithm in English Oral Duplicate Correction Map

Chen

2021

Complexity

View full text Add to dashboard Cite

Combining the communicative language competence model and the perspective of multimodal research, this research proposes a research framework for oral communicative competence under the multimodal perspective. This not only truly reflects the language communicative competence but also fully embodies the various contents required for assessment in the basic attributes of spoken language. Aiming at the feature sparseness of the user evaluation matrix, this paper proposes a feature weight assignment algorithm based on the English spoken category keyword dictionary and user search records. The algorithm is mainly based on the self-built English oral category classification dictionary and converts the user’s query vector into a user-English-speaking type vector. Through the calculation rules proposed in this paper, the target user’s preference score for a specific type of spoken English is obtained, and this score is assigned to the unrated item of the original user’s feature matrix as the initial starting score. At the same time, in order to solve the problem of insufficient user similarity calculation accuracy, a user similarity calculation algorithm based on “Synonyms Cilin Extended Edition” and search records is proposed. The algorithm introduces “Synonyms Cilin” to calculate the correlation between the semantic items, vocabulary, and query vector in the user query record to obtain the similarity between users and finally gives a user similarity calculation that integrates user ratings and query vectors method. For the task of Chinese grammar error correction, this article uses two methods of predicting the relationship between words in the corpus, Word2Vec and GloVe, to train the word vectors of different dimensions and use the word vectors to represent the text features of the experimental samples, avoiding sentences brought by word segmentation. On the basis of word vectors, the advantages and disadvantages of CNN, LSTM, and SVM models in this shared task are analyzed through experimental data. The comparative experiment shows that the method in this paper has achieved relatively good results.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Synthetic Network and Search Filter Algorithm in English Oral Duplicate Correction Map

Chen

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…Applications of RNN and LSTM to solve geophysical problems are recent and date back to the very last years. These examples refer to earthquake classification (Kuyuk & Susumu, 2018), detection of earthquake precursors (Cai et al ., 2019), earthquake magnitude prediction (Gonzales et al ., 2019), facies classification from post‐stack seismic data (Grana et al., 2020), seismic velocity analysis (Fabien‐Ouellet & Sarkar, 2020), well log generation (Zhang et al ., 2018), well production prediction (Jie et al ., 2020), seismic data interpolation (Yoon et al ., 2020) and porosity estimation from well log data (Chen et al ., 2020).…”

Section: Introductionmentioning

confidence: 99%

Elastic properties and litho‐fluid facies estimation from pre‐stack seismic data through bidirectional long short‐term memory networks

Aleardi

2022

Geophysical Prospecting

View full text Add to dashboard Cite

One of the main goals of pre‐stack seismic inversion is the estimation of elastic properties (i.e. P‐, S‐ wave velocities and density) and litho‐fluid classes in the investigated area. To this end, many inversion strategies have been proposed, but the most popular is based on a two‐step inversion approach: First, elastic properties are inferred from pre‐stack data, and then a classification algorithm is used to convert the outcomes of the first stage into litho‐fluid facies. In this work, we propose an alternative approach based on recurrent neural networks. We train two bidirectional long short‐term memory networks to predict the inverse mappings from pre‐stack seismic data to elastic properties, and litho‐fluid classes. In the elastic inversion, we also use a Monte Carlo simulation approach to properly propagate onto the model space both the uncertainties related to noise contamination in the data and to the modelling error introduced by the network approximation. One crucial aspect of any machine‐learning inversion strategy is the definition of an appropriate training set. In this case, the models forming the training and validation examples are drawn according to a previously defined elastic and facies prior models derived from actual well log recordings. In particular, we assume a Gaussian‐mixture elastic prior, and we also take into account the uncertainties affecting the estimation of the transition probabilities of facies. We invert each seismic gather independently, and in this context, the generation of the training set, and the learning process can be accomplished with a very limited computational effort on a common notebook. Once trained, the networks estimate the elastic properties, the litho‐fluid facies and the related uncertainties from the pre‐stack data in near real‐time. Synthetic and field data inversions are used to validate the proposed method. The network predictions are also benchmarked against the outcomes of a more standard two‐step approach that combines a linear elastic inversion and a subsequent point‐wise Bayesian classification. Our results demonstrate that the implemented algorithm guarantees more accurate elastic property estimations and facies predictions than the standard inversion strategy. In particular, the predictions provided by the long short‐term memory network are less affected by erroneous assumptions on the noise statistics and prior model and by errors in the estimated source wavelet.

show abstract

“…Zhang et al [24] successfully used the LSTM neural network to predict groundwater levels within the Hetao Plain. Cai et al [25] also used the LSTM neural network to predict groundwater levels, geomagnetism, and gravity precursor data; thus, effectively identifying precursor anomalies. Although the LSTM neural network effectively predicts time series data, this method is still challenging when obtaining ideal results for the strongly nonlinear data.…”

Section: Introductionmentioning

confidence: 99%

Groundwater Radon Precursor Anomalies Identification by EMD-LSTM Model

Feng

Zhong

Yan

et al. 2022

Water

View full text Add to dashboard Cite

Groundwater radon concentrations can reflect the changes of crustal stress and strain. Scholars and scientific institutions have also recorded groundwater radon precursor anomalies before earthquakes. Therefore, groundwater radon monitoring is an effective means of predicting seismic activities. However, the variation of radon concentrations within groundwater is not only affected by structural factors, but also by environmental factors, such as air pressure, temperature, and rainfall. This causes difficulty in identifying the possible precursor anomalies. Therefore, the EMD-LSTM model is proposed to identify the radon anomalies. This study investigated the time series data of groundwater radon from well #32 located in Sichuan province. Three models (including the LSTM (Long Short-Term Memory) model with auxiliary data, the EMD-LSTM (Empirical Mode Decomposition Long Short-Term Memory) model with auxiliary data, and the EMD-LSTM model without auxiliary data) were developed in order to predict groundwater radon variations. The results indicated that the prediction accuracy of the EMD-LSTM model was much higher than that of the LSTM model, and the EMD-LSTM model without auxiliary data also can obtain an ideal prediction result. Furthermore, the different durations of seismic activities T (T = ±10, ±30, ±50, and ±100) were also investigated by comparing the identification results. The identification rate of the precursor anomalies was the highest when T = ±30. The EMD-LSTM model identified five possible radon anomalies among the seven selected earthquakes. Taking well #32 as an example, we provided a promising method, that was the EMD-LSTM model, to detect the groundwater radon anomalies. It also suggested that the EMD-LSTM model can be used to identify the possible precursor anomalies within future studies.

show abstract

Anomaly detection of earthquake precursor data using long short-term memory networks

Cited by 29 publications

References 24 publications

[Retracted] Synthetic Network and Search Filter Algorithm in English Oral Duplicate Correction Map

[Retracted] Synthetic Network and Search Filter Algorithm in English Oral Duplicate Correction Map

Elastic properties and litho‐fluid facies estimation from pre‐stack seismic data through bidirectional long short‐term memory networks

Groundwater Radon Precursor Anomalies Identification by EMD-LSTM Model

Contact Info

Product

Resources

About