Search Results (161)

Effective earthquake early warning (EEW) is essential for disaster prevention in the built environment, enabling a rapid structural response, system shutdown, and occupant evacuation to mitigate damage and casualties. However, most current EEW systems lack rigorous reliability analyses of their predictive outcomes, limiting their effectiveness in real-world scenarios—especially for on-site warnings, where data are limited and time is critical. To address these challenges, we propose a Bayesian neural network (BNN) framework based on Stein variational gradient descent (SVGD). By performing Bayesian inference, we estimate the posterior distribution of the parameters, thus outputting a reliability analysis of the prediction results. In addition, we incorporate a continual learning mechanism based on elastic weight consolidation, allowing the system to adapt quickly without full retraining. Our experiments demonstrate that our SVGD-BNN model significantly outperforms traditional peak displacement (Pd)-based approaches. In a 3 s time window, the Pearson correlation coefficient R increases by 9.2% and the residual standard deviation $SD$ decreases by 24.4% compared to a variational inference (VI)-based BNN. Furthermore, the prediction variance generated by the model can effectively reflect the uncertainty of the prediction results. The continual learning strategy reduces the training time by 133–194 s, enhancing the system’s responsiveness. These features make the proposed framework a promising tool for real-time, reliable, and adaptive EEW—supporting disaster-resilient building design and operation. Full article

China is one of the countries severely affected by earthquakes, making precise and timely identification of earthquake precursors essential for reducing casualties and property damage. A novel method is proposed that combines a rock acoustic emission (AE) detection technique with deep learning methods to facilitate real-time monitoring and advance earthquake precursor detection. The AE equipment and seismometers were installed in a granite tunnel 150 m deep in the mountains of eastern Guangdong, China, allowing for the collection of experimental data on the correlation between rock AE and seismic activity. The deep learning model uses features from rock AE time series, including AE events, rate, frequency, and amplitude, as inputs, and estimates the likelihood of seismic events as the output. Precursor features are extracted to create the AE and seismic dataset, and three deep learning models are trained using neural networks, with validation and testing. The results show that after 1000 training cycles, the deep learning model achieves an accuracy of 98.7% on the validation set. On the test set, it reaches a recognition accuracy of 97.6%, with a recall rate of 99.6% and an F₁ score of 0.975. Additionally, it successfully identified the two biggest seismic events during the monitoring period, confirming its effectiveness in practical applications. Compared to traditional analysis methods, the deep learning model can automatically process and analyse recorded massive AE data, enabling real-time monitoring of seismic events and timely earthquake warning in the future. This study serves as a valuable reference for earthquake disaster prevention and intelligent early warning. Full article

In this study, we analyzed the lithospheric seismic background of the Tianshan and adjacent areas by combining various geophysical methods (effective elastic thickness, time-varying gravity, apparent density, and InSAR), and explored the genesis mechanism of the Wushi Ms7.1 earthquake as an example, which led to the following conclusions: (1) The effective elastic thickness (Te) of the Tianshan lithosphere is low (13–28 km) and weak, while the Tarim and Junggar basins have Te > 30 km with high intensity, and the loads are all mainly from the surface (F < 0.5). Earthquakes occur mostly in areas with low values of Te. (2) Medium and strong earthquakes are prone to occur in regions with alternating positive and negative changes in the gravity field during the stage of large-scale reverse adjustment. It is expected that the risk of a moderate-to-strong earthquake occurring again in the vicinity of the survey area between 2025 and 2026 is relatively high. (3) Before the Wushi earthquake, the positive and negative boundaries of the apparent density of the crust at 12 km shifted to be approximately parallel to the seismic fault, and the earthquake was triggered after undergoing a “solidification” process. (4) The Wushi earthquake is a leptokurtic strike-slip backwash type of earthquake; coseismic deformation shows that subsidence occurs in the high-visual-density zone, and vice versa for uplift. The results of this study reveal the lithosphere-conceiving environment of the Tianshan and adjacent areas and provide a basis for regional earthquake monitoring, early warning, and post-disaster disposal. Full article

The Mw 7.8 Gorkha Earthquake of 25 April 2015 triggered over 25,000 landslides across central Nepal, with 4775 events concentrated in Gorkha District alone. Despite substantial advances in landslide susceptibility mapping, existing studies often overlook the compound role of post-seismic rainfall and lack robust spatial validation. To address this gap, we validated an ensemble machine learning framework for co-seismic landslide susceptibility modeling by integrating seismic, geomorphological, hydrological, and anthropogenic variables, including cumulative post-seismic rainfall. Using a balanced dataset of 4775 landslide and non-landslide instances, we evaluated the performance of Logistic Regression (LR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) models through spatial cross-validation, SHapley Additive exPlanations (SHAP) explainability, and ablation analysis. The RF model outperformed all others, achieving an accuracy of 87.9% and a Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) value of 0.94, while XGBoost closely followed (AUC = 0.93). Ensemble models collectively classified over 95% of observed landslides into High and Very High susceptibility zones, demonstrating strong spatial reliability. SHAP analysis identified elevation, proximity to fault, peak ground acceleration (PGA), slope, and rainfall as dominant predictors. Notably, the inclusion of post-seismic rainfall substantially improved recall and F1 scores in ablation experiments. Spatial cross-validation revealed the superior generalizability of ensemble models under heterogeneous terrain conditions. The findings underscore the value of integrating post-seismic hydrometeorological factors and spatial validation into susceptibility assessments. We recommend adopting ensemble models, particularly RF, for operational hazard mapping in earthquake-prone mountainous regions. Future research should explore the integration of dynamic rainfall thresholds and physics-informed frameworks to enhance early warning systems and climate resilience. Full article

On 22 May 2012, a magnitude Mw 5.6 earthquake struck the Pernik region of western Bulgaria, causing structural damage in nearby cities, including Sofia. This study assesses the seismic response of a six-story reinforced concrete building in central Sofia, utilizing real accelerogram data recorded at the basement (SGL1) and sixth floor (SGL2) levels during the earthquake. Using the Kanai–Yoshizawa (KY) model, the study estimates inter-story motion and assesses amplification effects across the structure. Analysis of peak ground acceleration (PGA), velocity (PGV), displacement (PGD), and spectral ratios reveals significant dynamic amplification of peak ground acceleration and displacement on the sixth floor, indicating flexible and dynamic behavior, as well as potential resonance effects. The analysis combines three spectral techniques—Horizontal-to-Vertical Spectral Ratio (H/V), Floor Spectral Ratio (FSR), and the Random Decrement Method (RDM)—to determine the building’s dynamic characteristics, including natural frequency and damping ratio. The results indicate a dominant vibration frequency of approximately 2.2 Hz and damping ratios ranging from 3.6% to 6.5%, which is consistent with the typical damping ratios of mid-rise concrete buildings. The findings underscore the significance of soil–structure interaction (SSI), particularly in sedimentary basins like the Sofia Graben, where localized geological effects influence seismic amplification. By integrating accelerometric data with advanced spectral techniques, this research can enhance ongoing site-specific monitoring and seismic design practices, contributing to the refinement of earthquake engineering methodologies for mitigating seismic risk in earthquake-prone urban areas. Full article

The application of deep learning to seismic electric signal (SES) anomaly detection remains underexplored in geophysics. This study introduces the integration of a 1D convolutional neural network (1DCNN) with a self-attention mechanism to automate SES analysis in a station in a certain place in China. Utilizing physics-informed data augmentation, our framework adapts to real-world interference scenarios, including subway operations and tidal fluctuations. The model achieves an F1-score of 0.9797 on a 7-year dataset, demonstrating superior robustness and precision compared to traditional manual interpretation. This work establishes a practical deep learning solution for real-time geoelectric anomaly monitoring, offering a transformative tool for earthquake early warning systems. Full article

The accurate and timely estimation of earthquake magnitude is essential for effective tsunami early warning, particularly in seismically active regions such as Indonesia. Conventional seismic approaches are often hindered by magnitude saturation in significant events (Mw > 7.5), resulting in systematically underestimated magnitudes. To address this limitation, we develop a regional peak ground displacement (PGD) scaling law using high-rate GNSS (HR-GNSS) data from 21 moderate to large earthquakes in Indonesia. Based on 87 PGD observations, we construct a regression model that relates PGD, hypocentral distance, and moment magnitude (Mw). The PGD-derived magnitudes (MPGD) exhibit strong concordance with catalog moment magnitudes, achieving a mean absolute deviation (MAD) of 0.21 and surpassing the accuracy of previously published global models. Retrospective analyses reveal that MPGD estimates converge within 2–3 min for well-recorded events and remain robust, even for great and tsunamigenic earthquakes. These results underscore the potential of HR-GNSS data to complement conventional seismic networks, providing rapid and reliable magnitude estimates for operational tsunami early warning in Indonesia. Full article

The National Institute of Earth Physics (NIEP) in Romania has upgraded its seismic monitoring stations into multifunctional platforms equipped with advanced devices for measuring gas emissions, magnetic fields, telluric fields, solar radiation, and more. This enhancement enabled the integration of a seismic forecasting system designed to extend the alert time of the existing warning system, which previously relied solely on seismic data. The implementation of an Operational Earthquake Forecast (OEF) aims to expand NIEP’s existing Rapid Earthquake Early Warning System (REWS) which currently provides a warning time of 25–30 s before an earthquake originating in the Vrancea region reaches Bucharest. The AFROS project (PCE119/4.01.2021) introduced fundamental research essential to the development of the OEF system. As a result, real-time analyses of radon and CO₂ emissions are now publicly available at afros.infp.ro, dategeofizice. The primary monitored area is Vrancea, known for producing the most destructive earthquakes in Romania, with impacts extending to neighboring countries such as Bulgaria, Ukraine, and Moldova. The structure and methodology of the monitoring network are adaptable to other seismic regions, depending on their specific characteristics. All collected data are stored in an open-access database available in real time, geobs.infp.ro. The monitoring methods include threshold-based event detection and seismic data analysis. Each method involves specific technical nuances that distinguish this monitoring network as a novel approach in the field. In conclusion, experimental results indicate that the Gutenberg-Richter law, combined with gas emission measurements (radon and CO₂), can be used for real-time earthquake forecasting. This approach provides warning times ranging from several hours to a few days, with results made publicly accessible. Another key finding from several years of real-time monitoring is that the value of fundamental research lies in its practical application through cost-effective and easily implementable solutions—including equipment, maintenance, monitoring, and data analysis software. Full article

Rapid and accurate detection of primary waves (P-waves) using high-rate Global Navigation Satellite System (GNSS) data is essential for earthquake monitoring and tsunami early warning systems, where traditional seismic methods are less effective in noisy environments. We applied a wavelet-based method using a Mexican hat wavelet and dynamic threshold to thoroughly analyze the three-component displacement waveforms of the 2009 Padang, 2012 Simeulue, and 2018 Palu Indonesian earthquakes. Data from the Sumatran GPS Array and Indonesian Continuously Operating Reference Stations were analyzed to determine accurate displacements and P-waves. Validation with Indonesian geophysical agency seismic records indicated reliable detection of the horizontal component, with a time delay of less than 90 s, whereas the vertical component detection was inconsistent, owing to noise. Spectrogram analysis revealed P-wave energy in the pseudo-frequency range of 0.02–0.5 Hz and confirmed the method’s sensitivity to low-frequency signals. This approach illustrates the utility of GNSS data as a complement to seismic networks for the rapid characterization of earthquakes in complex tectonic regions. Improving the vertical component noise suppression might further help secure their utility in real-time early warning systems. Full article

Earthquakes cause enormous social and economic damage. Consequently, the seismic process requires regular monitoring and systematic forecasting of strong earthquakes. This study introduces an enhanced iteration of the method of the minimum area of alarm (MMAA), refined to advance earthquake forecasting technology closer to its practical application. In the new version, a forecast is considered successful when all target earthquake epicenters within a specified time interval are contained within predefined alarm zones. Our updated algorithm optimizes the probability of successfully detecting earthquakes across forecast cycles and the probability for subsequent periods. A case study from the Kamchatka region demonstrates the practical application of this systematic forecasting approach. We propose that this computational technology can serve as an operational tool for generating early warnings of potential seismic hazards, and a research platform for conducting detailed investigations of precursor phenomena. Full article

The Internet of Things (IoT) offers transformative capabilities in enhancing public safety, disaster response, and emergency management by leveraging interconnected devices and real-time data. Through the IoT, smart sensors and networks are deployed across cities and environments to monitor critical parameters including air quality, structural integrity, and environmental changes. These systems provide early warnings for natural disasters such as earthquakes, floods, and wildfires, enabling authorities to respond proactively. In emergency management, IoT devices help coordinate resources and improve situational awareness during crises. Real-time data from wearable devices, smart infrastructure, and communication systems allow responders to track people, manage evacuations, and deploy resources more effectively. For example, IoT-enabled drones and autonomous vehicles are used to deliver supplies or assess damage in hazardous areas without risking human lives. IoT technologies improve post-disaster recovery by continuously monitoring areas for safety hazards and supporting infrastructure restoration. Smart traffic management systems assist in controlling traffic flow for emergency vehicles, while IoT-based communication networks ensure connectivity when traditional systems fail. The IoT significantly enhances the speed, accuracy, and effectiveness of disaster response and public safety operations, leading to the better protection of communities and faster recovery from emergencies. Full article

Earthquakes, as serious natural disasters, have greatly harmed human beings. In recent years, the combination of acoustic emission technology and information entropy has shown good prospects in earthquake prediction. In this paper, we study the application of acoustic emission b-values and information entropy in earthquake prediction in China and analyze their changing characteristics and roles. The acoustic emission b-value is based on the Gutenberg–Richter law, which quantifies the relationship between magnitude and occurrence frequency. Lower b-values are usually associated with higher earthquake risks. Meanwhile, information entropy is used to quantify the uncertainty of the system, which can reflect the distribution characteristics of seismic events and their dynamic changes. In this study, acoustic emission data from several stations around the 2008 Wenchuan 8.0 earthquake are selected for analysis. By calculating the acoustic emission b-value and information entropy, the following is found: (1) Both the b-value and information entropy show obvious changes before the main earthquake: during the seismic phase, the acoustic emission b-value decreases significantly, and the information entropy also shows obvious decreasing entropy changes. The b-values of stations AXI and DFU continue to decrease in the 40 days before the earthquake, while the b-values of stations JYA and JMG begin to decrease significantly in the 17 days or so before the earthquake. The information entropy changes in the JJS and YZP stations are relatively obvious, especially for the YZP station, which shows stronger aggregation characteristics of seismic activity. This phenomenon indicates that the regional underground structure is in an extremely unstable state. (2) The stress evolution process of the rock mass is divided into three stages: in the first stage, the rock mass enters a sub-stabilized state about 40 days before the main earthquake; in the second stage, the rupture of the cracks changes from a disordered state to an ordered state, which occurs about 10 days before the earthquake; and in the third stage, the impending destabilization of the entire subsurface structure is predicted, which occurs in a short period before the earthquake. In summary, the combined analysis of the acoustic emission b-value and information entropy provides a novel dual-parameter synergy framework for earthquake monitoring and early warning, enhancing precursor recognition through the coupling of stress evolution and system disorder dynamics. Full article

Early detection of earthquakes is essential for minimizing potential damage and ensuring public safety. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), provide a promising alternative for analyzing seismic waves. In contrast, traditional methods such as the short-term average/long-term average (STA/LTA) algorithm and the Akaike information criterion (AIC) have limitations in detecting primary (P) waves in high-noise conditions, caused by industrial and anthropogenic disturbances. This study presents a CNN-based automatic P-wave detection model tailored for the Almaty city region. The seismic dataset used in this research was obtained from the IRIS database and includes data collected from seven stations within a 333 km radius of Almaty, Kazakhstan. The proposed model achieves a recall rate of 89.1% and an accuracy of 94.1% compared to other deep learning-based models. Experimental results demonstrate that this method enhances the reliability of automatic early earthquake warning systems and improves the accuracy of P-wave detection. The research outputs presented for the local region are unique. Applying CNNs in seismic monitoring facilitates the development of efficient automated systems that minimize risks and improve response measures for natural disasters. Full article

Earthquakes are among the most destructive natural phenomena, leading to significant loss of human life and substantial economic damage that severely impacts affected communities. Rapid detection and characterization of seismic parameters, including location and magnitude, are crucial for real-time seismological applications, including Earthquake Early Warning (EEW) systems. Machine learning (ML) has emerged as a powerful tool to enhance the accuracy of these applications, enabling more efficient responses to seismic events of different magnitudes. This systematic review aims to provide researchers and professionals with a summary of the current state of ML applications in seismology, particularly on early earthquake magnitude estimations and related topics such as earthquake detection and seismic phase identification. A systematic search was conducted in Scopus, ScienceDirect, IEEE Xplore, and Web of Science databases, covering the period from early 2014 to 7 March 2025. The search terms included the following: (“earthquake magnitude” OR “earthquake early warning”) AND (prediction OR forecasting OR estimation OR forecast OR classification) AND (“machine learning” OR “deep learning” OR “artificial intelligence”). Out of the 472 articles initially identified, 28 were selected based on pre-defined inclusion criteria. The described methods and algorithms illustrate the strong performance of ML in earthquake magnitude estimation despite limited implementation in real-time systems. This highlights the need to develop standardized benchmark datasets to promote future progress in this field. Full article

In recent years, although a variety of deep learning models have been developed for magnitude estimation, the complex and variable nature of earthquakes limits the generalizability and accuracy of these models. In this study, we selected the waveform data of the Japan earthquake. We applied four deep learning techniques (MagNet combined with bidirectional long- and short-term memory network Bi-LSTM, DCRNN with deepened CNN layers, DCRNNAmp with the introduction of a global scale factor, and Exams with a multilayered CNN architecture) for real-time magnitude estimation. By comparing the estimation errors of each model in the first 3 s after the earthquake, it is found that the DCRNNAmp performs the best, with an MAE of 0.287, an RMSE of 0.397, and an R² of 0.737 in the first 3 s after the arrival of the P-wave, and the inclusion of S-wave seismic-phase information is found to significantly improve the accuracy of the magnitude estimation, which suggests that S-wave seismic-phase waveform features can enrich the model’s understanding of the relationship between the seismic phases. It shows that S-wave phase waveform features can enrich the model’s knowledge of the relationship between seismic fluctuations and magnitude. The epicentral distance positively correlates with the magnitude estimation, and the model can converge faster with the improved signal-to-noise ratio. Despite the shortcomings of model design and opaque internal mechanisms, this study provides important evidence for deep learning in earthquake estimation, demonstrating its potential to improve the accuracy of on-site earthquake early warning (EEW) systems. The estimation capability can be further improved by optimizing the model and exploring new features. Full article