Prediction of Ground Motion Intensity Measures Using an Artificial Neural Network

Sreejaya, K.P.; Basu, Jahnabi; Raghukanth, S. T. G.; Srinagesh, D.

doi:10.1007/s00024-021-02752-9

Cited by 18 publications

(7 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14] different supervised learning algorithms applied to Ecuador, Haiti, Nepal, and South Korean earthquakes data to classify damage grades to buildings. A ground motion prediction by ANN of MLP-architecture is considered in [15], performing training, validating, and testing on the Indian strong motion database including 659 records from 138 earthquakes. Paper [16] considers the landslide displacement prediction by GNSS time series analysis carried out with LSTM network.…”

Section: Introductionmentioning

confidence: 99%

Classification of Video Observation Data for Volcanic Activity Monitoring Using Computer Vision and Modern Neural NetWorks (on Klyuchevskoy Volcano Example)

et al. 2021

View full text Add to dashboard Cite

Currently, video observation systems are actively used for volcano activity monitoring. Video cameras allow us to remotely assess the state of a dangerous natural object and to detect thermal anomalies if technical capabilities are available. However, continuous use of visible band cameras instead of special tools (for example, thermal cameras), produces large number of images, that require the application of special algorithms both for preliminary filtering out the images with area of interest hidden due to weather or illumination conditions, and for volcano activity detection. Existing algorithms use preselected regions of interest in the frame for analysis. This region could be changed occasionally to observe events in a specific area of the volcano. It is a problem to set it in advance and keep it up to date, especially for an observation network with multiple cameras. The accumulated perennial archives of images with documented eruptions allow us to use modern deep learning technologies for whole frame analysis to solve the specified task. The article presents the development of algorithms to classify volcano images produced by video observation systems. The focus is on developing the algorithms to create a labelled dataset from an unstructured archive using existing and authors proposed techniques. The developed solution was tested using the archive of the video observation system for the volcanoes of Kamchatka, in particular the observation data for the Klyuchevskoy volcano. The tests show the high efficiency of the use of convolutional neural networks in volcano image classification, and the accuracy of classification achieved 91%. The resulting dataset consisting of 15,000 images and labelled in three classes of scenes is the first dataset of this kind of Kamchatka volcanoes. It can be used to develop systems for monitoring other stratovolcanoes that occupy most of the video frame.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Video Observation Data for Volcanic Activity Monitoring Using Computer Vision and Modern Neural NetWorks (on Klyuchevskoy Volcano Example)

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, after incorporating more ground motion data, restrictions of the originally adopted linear regression models may limit their capabilities in extracting complex nonlinear behaviors in the data. Thus, the use of machine learning as a statistical method is beneficial for constructing complex relationships between model parameters and site/earthquake characteristics 84,90–92 . Besides, the deep learning‐based ground motion models also show a more powerful predictive capacity, 93 especially for big data without the assumption of predefined functional forms.…”

Section: Further Discussionmentioning

confidence: 99%

“…Thus, the use of machine learning as a statistical method is beneficial for constructing complex relationships between model parameters and site/earthquake characteristics. 84,[90][91][92] Besides, the deep learning-based ground motion models also show a more powerful predictive capacity, 93 especially for big data without the assumption of predefined functional forms. These data-driven methods can extract critical information from massive earthquake records and find high-dimensional features to achieve better results.…”

Section: Further Improvement In the Usable Scope Of Sgmmmentioning

confidence: 99%

Surrogate model‐aided global sensitivity analysis framework for seismic consequences estimation in buildings

Du,

Wang

2024

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

Seismic consequences estimation for individual buildings is valuable for various stakeholders, including government entities, building owners, and insurers. The robustness of estimation results in the presence of incomplete input information can typically be investigated through sensitivity analysis. However, the estimation process's complexity and the sensitivity analysis's computational burden hinder its practical application, which requires a more efficient procedure to facilitate broader use. This paper proposes a novel framework for sensitivity analysis of seismic consequences estimation to improve the efficiency and reliability of such analysis. The proposed approach encompasses three key components: (1) stochastic ground motion modeling (SGMM)‐based seismic consequences estimation to evaluate the economic, environmental, and social consequences given specific buildings by considering different hazard levels, (2) the training of surrogate model (Gaussian process model) for structural analysis to reduce the computational cost of the evaluation process, and (3) variance‐based global sensitivity analysis to investigate the importance of parameters of concern in the estimation process. The entire procedure is implemented in Python, adhering to object‐oriented programming, and does not rely on external software. Then, the proposed methodology is applied to two distinct three‐story steel moment‐resistant frames (SMRFs) subjected to four different hazard levels to demonstrate its effectiveness. The SGMM method can generate specific ground motions for each hazard level, mitigating the potential for result bias from using ground motions with unrealistic characteristics. Furthermore, the SGMM method is particularly suitable for automated analysis processes reducing the laborious task of screening ground motions from the database. Comparative analysis with surrogate‐free estimation reveals that the surrogate‐based analysis delivers reliable results with significantly reduced computational cost. The results of analyzing different structures under varying hazard levels reflect the variability in sensitivity analysis of consequences estimation, highlighting the necessity of the proposed flexible and efficient framework. Furthermore, the proposed framework's advantages, limitations, and future research needs are discussed.

show abstract

“…Using the ANN technique,Sreejaya et al (2021) [33] generated a prediction framework for ground-movement intensity measures for active shallow crustal earthquakes in India. The model was composed of 659 ground motion records gathered from 138 earthquakes recorded by different seismic networks with the aim of seismic hazard analysis.Pandit et al (2021) …”

mentioning

confidence: 99%

“…Note that the values in the graph are not scaled. Figure[33] shows the error function profile (predicted value -actual value) of the ANN-2 model. We can see that there is a uniform distribution with a precision of 0.01, indicating that the model's predictions are accurate.…”

mentioning

confidence: 99%

Prediction of earthquake magnitude and seismic vulnerability mapping using artificial intelligence techniques: a case study of Turkey

Biswas

Kumar

Bera

2023

Preprint

View full text Add to dashboard Cite

Earthquake threats can result in fatalities, property destruction, and other cascading effects. Since it is nearly impossible to prevent earthquakes, anticipating the location of future earthquakes and figuring out their likelihood could be very helpful in reducing the seismic threat. In this work, seismic hazard prediction is executed to forecast adverse results using a range of potential artificial intelligence (AI) techniques, including ML and ANN. In the case study, we have looked at Turkey, which was recently and badly damaged by two earthquakes in February 2023. To predict earthquake magnitude, this study used a variety of regression algorithms, including Decision Tree Regressor, Extra-Trees Regressor, Random Forest Regressor, Bayesian Ridge Regressor, and advanced gradient boosting decision tree (GBDT) algorithms such as XGBoost, LightGBM, and CatBoost, as well as three artificial neural networks (ANN). The predicted magnitude and risk zone of an earthquake are mapped using a geographic information system (GIS), and the maps performed well in terms of prediction. The generated maps is showing the expected earthquake risk based on historical data using the statistical computations. The ANN models perform exceptionally well, with R2 scores of 0.99 and 0.98 for training and case study data, respectively, and low values for MSE, MAE, and RMSE. ML models have demonstrated an exceptional ability to properly generalize from a single dataset, which implies they can accurately anticipates results for new and untested data. The results would be helpful to many local emergency preparedness and infrastructure planning organizations.

show abstract

Prediction of Ground Motion Intensity Measures Using an Artificial Neural Network

Cited by 18 publications

References 70 publications

Classification of Video Observation Data for Volcanic Activity Monitoring Using Computer Vision and Modern Neural NetWorks (on Klyuchevskoy Volcano Example)

Classification of Video Observation Data for Volcanic Activity Monitoring Using Computer Vision and Modern Neural NetWorks (on Klyuchevskoy Volcano Example)

Surrogate model‐aided global sensitivity analysis framework for seismic consequences estimation in buildings

Prediction of earthquake magnitude and seismic vulnerability mapping using artificial intelligence techniques: a case study of Turkey

Contact Info

Product

Resources

About