arXiv subjects

Nishtha Srivastava

Publications and source records attributed to Nishtha Srivastava.

18 recordsLinked to original sources

arXiv2026

Probabilistic and Alarm-Based Evaluation of a b-Value-Driven Deep Learning Earthquake Forecast

We evaluate the forecasting performance of a deep learning model, originally introduced as a pattern-extraction framework, that operates on the spatiotemporal evolution of seismic b-values in a short-term forecasting context. Model output is rescaled to account for training on balanced datasets and evaluated relative to a spatial base-rate model using the Brier Skill Score (BSS). Absolute skill values are small, but mean BSS values are consistently positive, including at locations where Mw geq 5 earthquakes occurred during the test period, indicating information content beyond historical seismicity alone. Alarm-based evaluation using Molchan diagrams shows elevated event capture rates at low alarm fractions (5.88 percent of events captured at 1 percent area under alarm), indicating discrimination exceeding random and purely spatial reference models under constrained alarm conditions. Comparison with ETAS-derived triggered probabilities further reveals a weak positive correlation, suggesting partial sensitivity of the model output to seismic regimes characterized by enhanced clustering and recent activity, while remaining distinct from classical aftershock-based descriptions. Together, these results indicate that spatiotemporal variations in b-values contain a persistent, though limited, signal relevant to probabilistic earthquake forecasting, yielding marginal but consistent improvements over baseline models across complementary evaluation frameworks.

physics.geo-ph↗

arXiv2026

An Interpretable Physics Informed Multi-Stream Deep Learning Architecture for the Discrimination between Earthquake, Quarry Blast and Noise

The reliable discrimination of tectonic earthquakes from anthropogenic quarry blasts and transient noise remains a critical challenge in single station seismic monitoring. In this study, we introduce a novel Physics Informed Convolutional Recurrent Neural Network (PI CRNN) that embeds seismological domain knowledge directly into the feature extraction and learning process. We adapt a multistream architecture with three parallel encoders: (i) Time Domain: SincNet Encoder, (ii) MultiResolution Spectrogram branch, and, (iii) Physics Branch, followed by a fusion and a bidirectionalLSTM module. Evaluated on the Curated Pacific Northwest AI ready Seismic Dataset, the PI CRNN achieves an overall classification accuracy of 97.56 percent on an independent test set. It outperforms a standard CRNN baseline, a classical P to S amplitude ratio method, and a Physics Informed Neural Network (PINN) that enforces physical constraints via the loss function. Furthermore, the model demonstrates perfect precision in noise rejection (100 percent Recall). Interpretability analysis using saliency maps confirms that the architecture successfully learns distinct physical signatures, identifying bimodal P- and S-wave arrivals for earthquakes versus singular impulsive onsets for blasts. This work establishes a scalable, transparent framework for AI-driven seismology, proving that architectural inductive bias provides an alternative reliable approach compared to purely data-driven approaches.

physics.geo-ph↗

arXiv2026

Detecting Spatiotemporal b-Value Anomalies with a Progressive Deep Learning Architecture

Identifying systematic patterns in seismicity that precede large earthquakes remains a central challenge in statistical seismology. In this work, we present a methodological framework for detecting spatiotemporal anomalies in seismicity using the evolution of gridded b-values. Focusing on the Japanese subduction zone, we construct daily b-value fields on a fine spatial grid by aggregating local seismicity over moving time windows, yielding a continuous 2+1D representation of seismic-state evolution. We formulate the problem as a binary classification task in which spatiotemporal blocks extracted from these $b$-value fields are labeled according to the occurrence of a target earthquake with \Mw $\geq 5$ in the central region within the next day. To model this data, we introduce a hybrid deep-learning architecture that combines a spatial convolutional encoder with a temporal convolutional network, enabling joint learning of spatial structure and temporal dynamics. A progressive meta-epoch training scheme is employed, in which the model is iteratively updated using a time-forward strategy that mirrors operational deployment and mitigates issues related to nonstationarity. This paper is strictly methodological in scope. It describes the construction of b-value fields, the spatiotemporal sampling strategy, the network architecture, and the progressive training and internal validation framework used for model development and parameter selection.

physics.geo-ph↗

arXiv2026

Evaluating the SAIPy Performance using a Local Seismic Network for Volcano-Tectonic Earthquakes Monitoring

In this study, we evaluated the performance of SAIPy, an open-source Python package for deep learning-based seismic data analysis, by applying its single-station monitoring tools and extending its use to a seismic network based approach, using data from a local seismic network deployed in a Caldera. Although the integrated models into SAIPy for earthquake detection,magnitude estimation, seismic phase picking, and P-wave polarity classification, were originally trained on tectonic signals, we assess their performance in a more complex seismic environment that includes volcano-tectonic events, along with signal interference from distant earthquakes.We also demonstrate the advantages of integrating outputs using multiple stations to improve event detection. SAIPy was able to identify a significantly larger number of local events than those included in previously published catalogs. SAIPy demonstrated reliable phase picking and P-wave polarity estimation, particularly for local volcano-tectonic events, with some limitations observed in the magnitude estimation for complex volcanic signals. These results support the utility of SAIPy for processing continuous seismic data and suggest that future retraining using data with physically standardized units, removing instrumental response, and including data from more diverse seismic sources, could improve its generalization for magnitude estimation to complex scenarios and different seismic networks and sensor types.

physics.geo-ph↗

arXiv2025

Neural Earthquake Forecasting with Minimal Information: Limits, Interpretability, and the Role of Markov Structure

Forecasting earthquake sequences remains a central challenge in seismology, particularly under non-stationary conditions. While deep learning models have shown promise, their ability to generalize across time remains poorly understood. We evaluate neural and hybrid (NN plus Markov) models for short-term earthquake forecasting on a regional catalog using temporally stratified cross-validation. Models are trained on earlier portions of the catalog and evaluated on future unseen events, enabling realistic assessment of temporal generalization. We find that while these models outperform a purely Markovian model on validation data, their test performance degrades substantially in the most recent quintile. A detailed attribution analysis reveals a shift in feature relevance over time, with later data exhibiting simpler, more Markov-consistent behavior. To support interpretability, we apply Integrated Gradients, a type of explainable AI (XAI) to analyze how models rely on different input features. These results highlight the risks of overfitting to early patterns in seismicity and underscore the importance of temporally realistic benchmarks. We conclude that forecasting skill is inherently time-dependent and benefits from combining physical priors with data-driven methods.

physics.geo-ph↗

arXiv2025

A Deep Learning Pipeline for Large Earthquake Analysis using High-Rate Global Navigation Satellite System Data

Deep learning techniques for processing large and complex datasets have unlocked new opportunities for fast and reliable earthquake analysis using Global Navigation Satellite System (GNSS) data. This work presents a deep learning model, MagEs, to estimate earthquake magnitudes using data from high-rate GNSS stations. Furthermore, MagEs is integrated with the DetEQ model for earthquake detection within the SAIPy package, creating a comprehensive pipeline for earthquake detection and magnitude estimation using HR-GNSS data. The MagEs model provides magnitude estimates within seconds of detection when using stations within 3 degrees of the epicenter, which are the most relevant for real-time applications. However, since it has been trained on data from stations up to 7.5 degrees away, it can also analyze data from larger distances. The model can process data from a single station at a time or combine data from up to three stations. The model was trained using synthetic data reflecting rupture scenarios in the Chile subduction zone, and the results confirm strong performance for Chilean earthquakes. Although tests from other tectonic regions also yielded good results, incorporating regional data through transfer learning could further improve its performance in diverse seismic settings. The model has not yet been deployed in an operational real-time monitoring system, but simulation tests that update data in a second-by-second manner demonstrate its potential for future real-time adaptation.

physics.geo-ph↗

arXiv2024

High Magnitude Earthquake Identification Using an Anomaly Detection Approach on HR GNSS Data

Earthquake early warning systems are crucial for protecting areas that are subject to these natural disasters. An essential part of these systems is the detection procedure. Traditionally these systems work with seismograph data, but high rate GNSS data has become a promising alternative for the usage in large earthquake early warning systems. Besides traditional methods, deep learning approaches have gained recent popularity in this field, as they are able to leverage the large amounts of real and synthetic seismic data. Nevertheless, the usage of deep learning on GNSS data remains a comparatively new topic. This work contributes to the field of early warning systems by proposing an autoencoder based deep learning pipeline that aims to be lightweight and customizable for the detection of anomalies viz. high magnitude earthquakes in GNSS data. This model, DetEQ, is trained using the noise data recordings from nine stations located in Chile. The detection pipeline encompasses: (i) the generation of an anomaly score using the ground truth and reconstructed output from the autoencoder, (ii) the detection of relevant seismic events through an appropriate threshold, and (iii) the filtering of local events, that would lead to false positives. Robustness of the model was tested on the HR GNSS real data of 2011 Mw 6.8 Concepcion earthquake recorded at six stations. The results highlight the potential of GNSS based deep learning models for effective earthquake detection.

physics.geo-ph↗

arXiv2023

When linear inversion fails: neural-network optimization for sparse-ray travel-time tomography of a volcanic edifice

In this study, we present an artificial neural network (ANN)-based approach for travel-time tomography of a volcanic edifice. We employ ray tracing to simulate the propagation of seismic waves through the heterogeneous medium of a volcanic edifice, and an inverse modeling algorithm that uses an ANN to estimate the velocity structure from the observed travel-time data. The performance of the approach is evaluated through a 2-dimensional numerical study that simulates i) an active source seismic experiment with few (explosive) sources placed on one side of the edifice and a dense line of receivers placed on the other side, and ii) earthquakes located inside the edifice and receivers placed on both sides of the edifice. The results are compared with those obtained from conventional damped linear inversion, demonstrating that the ANN-based approach outperforms the classical approach, particularly in situations with sparse ray coverage. Our study emphasizes the advantages of employing a relatively simple ANN architecture in conjunction with second-order optimizers to minimize the loss function. The ANN-based approach is computationally efficient and capable of providing high-resolution velocity images of anomalous structures within the edifice, making it a potentially valuable tool for the detection of low velocity anomalies related to magmatic intrusions or mush.

physics.geo-ph↗

arXiv2023

SAIPy: A Python Package for single station Earthquake Monitoring using Deep Learning

Seismology has witnessed significant advancements in recent years with the application of deep learning methods to address a broad range of problems. These techniques have demonstrated their remarkable ability to effectively extract statistical properties from extensive datasets, surpassing the capabilities of traditional approaches to an extent. In this study, we present SAIPy, an open source Python package specifically developed for fast data processing by implementing deep learning. SAIPy offers solutions for multiple seismological tasks, including earthquake detection, magnitude estimation, seismic phase picking, and polarity identification. We introduce upgraded versions of previously published models such as CREIMERT capable of identifying earthquakes with an accuracy above 99.8 percent and a root mean squared error of 0.38 unit in magnitude estimation. These upgraded models outperform state of the art approaches like the Vision Transformer network. SAIPy provides an API that simplifies the integration of these advanced models, including CREIMERT, DynaPickerv2, and PolarCAP, along with benchmark datasets. The package has the potential to be used for real time earthquake monitoring to enable timely actions to mitigate the impact of seismic events. Ongoing development efforts aim to enhance the performance of SAIPy and incorporate additional features that enhance exploration efforts, and it also would be interesting to approach the retraining of the whole package as a multi-task learning problem.

physics.geo-ph↗

arXiv2023

Testing the Potential of Deep Learning in Earthquake Forecasting

Reliable earthquake forecasting methods have long been sought after, and so the rise of modern data science techniques raises a new question: does deep learning have the potential to learn this pattern? In this study, we leverage the large amount of earthquakes reported via good seismic station coverage in the subduction zone of Japan. We pose earthquake forecasting as a classification problem and train a Deep Learning Network to decide, whether a timeseries of length greater than 2 years will end in an earthquake on the following day with magnitude greater than 5 or not. Our method is based on spatiotemporal b value data, on which we train an autoencoder to learn the normal seismic behaviour. We then take the pixel by pixel reconstruction error as input for a Convolutional Dilated Network classifier, whose model output could serve for earthquake forecasting. We develop a special progressive training method for this model to mimic real life use. The trained network is then evaluated over the actual dataseries of Japan from 2002 to 2020 to simulate a real life application scenario. The overall accuracy of the model is 72.3 percent. The accuracy of this classification is significantly above the baseline and can likely be improved with more data in the future

physics.geo-ph↗

arXiv2023

Real-time Earthquake Monitoring using Deep Learning: a case study on Turkey Earthquake Aftershock Sequence

Seismic phase picking and magnitude estimation are essential components of real time earthquake monitoring and earthquake early warning systems. Reliable phase picking enables the timely detection of seismic wave arrivals, facilitating rapid earthquake characterization and early warning alerts. Accurate magnitude estimation provides crucial information about the size of an earthquake and potential impact. Together, these steps contribute to effective earthquake monitoring, enhancing our ability to implement appropriate response measures in seismically active regions and mitigate risks. In this study, we explore the potential of deep learning in real time earthquake monitoring. To that aim, we begin by introducing DynaPicker which leverages dynamic convolutional neural networks to detect seismic body wave phases. Subsequently, DynaPicker is employed for seismic phase picking on continuous seismic recordings. To showcase the efficacy of Dynapicker, several open source seismic datasets including window format data and continuous seismic data are used for seismic phase identification, and arrival time picking. Additionally,the robustness of DynaPicker in classifying seismic phases was tested on the low magnitude seismic data polluted by noise. Finally, the phase arrival time information is integrated into a previously published deep learning model for magnitude estimation. This workflow is then applied and tested on the continuous recording of the aftershock sequences following the Turkey earthquake to detect the earthquakes, seismic phase picking and estimate the magnitude of the corresponding event. The results obtained in this case study exhibit a high level of reliability in detecting the earthquakes and estimating the magnitude of aftershocks following the Turkey earthquake.

physics.geo-ph↗

arXiv2023

Exploring a CNN Model for Earthquake Magnitude Estimation using HR-GNSS data

High rate Global Navigation Satellite System (HR GNSS) data can be highly useful for earthquake analysis as it provides continuous high-rate measurements of ground motion. This data can be used to estimate the magnitude, to assess the potential of an earthquake for generating tsunamis, and to analyze diverse parameters related to the seismic source. Particularly, in this work, we present the first results of a deep learning model based on a convolutional neural network for earthquake magnitude estimation, using HR GNSS displacement time series. The influence of different dataset configurations, such as station numbers, epicentral distances, signal duration, and earthquake size, were analyzed to figure out how the model can be adapted to various scenarios. We explored the potential of the model for global application and compared its performance using both synthetic and real data from different seismogenic regions. The performance of our model at this stage was satisfactory in estimating earthquake magnitude from synthetic data. Comparable results were observed in tests using synthetic data from a different tectonic region than the training data. Furthermore, the model was tested using real data from different regions and magnitudes, resulting in a good accuracy, provided that the data from a particular group of stations had similar epicentral distance constraints to those used during the model training. The robustness of the DL model can be improved to work independently from the window size of the time series and the number of stations, enabling faster estimation by the model using only near field data. Overall, this study provides insights for the development of future DL approaches for earthquake magnitude estimation with HR-GNSS data, emphasizing the importance of proper handling and careful data selection for further model improvements.

physics.geo-ph↗

arXiv2022

Sunda-arc seismicity: continuing increase of high-magnitude earthquakes since 2004

Spatial and temporal data for earthquakes with magnitude M greater than or equal to 6.5 can provide crucial information about the seismic history and potential for large earthquakes in a region. We analyzed approximately 313,500 events that occurred in the Sunda-arc region during the last 56 years, from 1964 to 2020, reported by the International Seismological Center. We report a persistent increase in the annual number of the events with mb greater than or equal to 6.5. We tested this increase against the null hypothesis and discarded the possibility of the increase being due to random groupings. The trend given by Auto-Regressive Integrated Moving Average suggests continuing increase of such large-magnitude events in the region during the next decade. At the same time, the computed Gutenberg Richter b value shows anomalies that can be related to the occurrence of the mega 2004 Sumatra earthquake, and to possible state of high tectonic stress in the eastern parts of the region.

physics.geo-ph↗

arXiv2022

Deep Learning-based Small Magnitude Earthquake Detection and Seismic Phase Classification

Reliable earthquake detection and seismic phase classification is often challenging especially in the circumstances of low magnitude events or poor signal-to-noise ratio. With improved seismometers and better global coverage, a sharp increase in the volume of recorded seismic data is witnessed. This makes the handling of the seismic data rather daunting based on traditional approaches and therefore fuels the need for a more robust and reliable method. In this study, we investigate two deep learningbased models, termed 1D ResidualNeuralNetwork (ResNet) and multi-branch ResNet, for tackling the problem of seismic signal detection and phase identification, especially the later can be used in the case where multiple classes is organized in the hierarchical format. These methods are trained and tested on the dataset of the Southern California Seismic Network. Results demonstrate that the proposed methods can achieve robust performance for the detection of seismic signals, and the identification of seismic phases, even when the seismic events are of small magnitude and are masked by noise. Compared with previously proposed deep learning methods, the introduced frameworks achieve 4% improvement in earthquake monitoring, and a slight enhancement in seismic phase classification.

physics.geo-ph↗

arXiv2022

CREIME: A Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation

The detection and rapid characterisation of earthquake parameters such as magnitude are of prime importance in seismology, particularly in applications such as Earthquake Early Warning (EEW). Traditionally, algorithms such as STA/LTA are used for event detection, while frequency or amplitude domain parameters calculated from 1-3 seconds of first P-arrival data are sometimes used to provide a first estimate of (body wave) magnitude. Owing to extensive involvement of human experts in parameter determination, these approaches are often found to be insufficient. Moreover, these methods are sensitive to the signal to noise ratio and may often lead to false or missed alarms depending on the choice of parameters. We, therefore, propose a multitasking deep learning model the Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation (CREIME) that: (i) detects the first earthquake signal, from background seismic noise, (ii) determines first P arrival time as well as (iii) estimates the magnitude using the raw 3-component waveform data from a single station as model input. Considering, speed is of essence in EEW, we use up to two seconds of P-wave information which, to the best of our knowledge, is a significantly smaller data window (5 second window with up to of P wave data) compared to the previous studies. To examine the robustness of CREIME we test it on two independent datasets and find that it achieves an average accuracy of 98 percent for event vs noise discrimination and is able to estimate first P arrival time and local magnitude with average root mean squared errors of 0.13 seconds and 0.65 units, respectively. We also compare CREIME architecture with architectures of other baseline models, by training them on the same data, and also with traditional algorithms such as STA/LTA, and show that our architecture outperforms these methods.

physics.geo-ph↗

arXiv2021

A study on the effect of input data length on deep learning based magnitude classifier

The rapid characterisation of earthquake parameters such as its magnitude is at the heart of Earthquake Early Warning (EEW). In traditional EEW methods the robustness in the estimation of earthquake parameters have been observed to increase with the length of input data. Since time is a crucial factor in EEW applications, in this paper we propose a deep learning based magnitude classifier and, further we investigate the effect of using five different durations of seismic waveform data after first P wave arrival of length 1s, 3s, 10s, 20s and 30s. This is accomplished by testing the performance of the proposed model that combines Convolution and Bidirectional Long-Short Term Memory units to classify waveforms based on their magnitude into three classes "noise", "low magnitude events" and "high magnitude events". Herein, any earthquake signal with magnitude equal to or above 5.0 is labelled as high magnitude. We show that the variation in the results produced by changing the length of the data, is no more than the inherent randomness in the trained models, due to their initialisation.

physics.geo-ph↗

arXiv2021

AWESAM: A Python Module for Automated Volcanic Event Detection Applied to Stromboli

Many active volcanoes in the world exhibit Strombolian activity, which is typically characterized by relatively frequent mild events and also by rare and much more destructive major explosions and paroxysms. Detailed analyses of past major and minor events can help to understand the eruptive behavior of the volcano and the underlying physical and chemical processes. Catalogs of volcanic eruptions may be established using continuous seismic recordings at stations in the proximity of volcanoes. However, in many cases, the analysis of the recordings relies heavily on the manual picking of events by human experts. Recently developed Machine Learning-based approaches require large training data sets which may not be available a priori. Here, we propose an alternative automated approach: the Adaptive-Window Volcanic Event Selection Analysis Module (AWESAM). This process of creating event catalogs consists of three main steps: (i) identification of potential volcanic events based on squared ground-velocity amplitudes, an adaptive MaxFilter, and a prominence threshold. (ii) catalog consolidation by comparing and verification of the initial detections based on recordings from two different seismic stations. (iii) identification and exclusion of signals from regional tectonic earthquakes. The software package is applied to publicly accessible continuous seismic recordings from two almost equidistant stations at Stromboli volcano in Italy. We tested AWESAM by comparison with a hand-picked catalog and found that around 95 percent of the eruptions with a signal-to-noise ratio above three are detected. In a first application, we derive a new amplitude-frequency relationship from over 290.000 volcanic events at Stromboli during 2019-2020. The module allows for a straightforward generalization and application to other volcanoes worldwide.

physics.geo-ph↗

arXiv2021

EPick: Multi-Class Attention-based U-shaped Neural Network for Earthquake Detection and Seismic Phase Picking

Earthquake detection and seismic phase picking not only play a crucial role in travel time estimation of body waves(P and S waves) but also in the localisation of the epicenter of the corresponding event. Generally, manual phase picking is a trustworthy and the optimum method to determine the phase arrival time, however, its capacity is restricted by available resources and time. Moreover, noisy seismic data renders an additional critical challenge for fast and accurate phase picking. In this study, a deep learning based model, EPick, is proposed which benefits both from U shaped neural network (also called UNet)and attention mechanism, as a strong alternative for seismic event detection and phase picking. On one hand, the utilization of UNet structure enables addressing different levels of deep features. On the other hand, attention mechanism promotes the decoder in the UNet structure to focus on the efficient exploitation of the low-resolution features learned from the encoder part to achieve precise phase picking. Extensive experimental results demonstrate that EPick achieves better performance over the benchmark method, and show the models robustness when tested on a different seismic dataset.

physics.geo-ph↗