Prediction of Peak Horizontal Acceleration Using an Artificial Neural Network Model

Emami, Somayeh; Harada, Takanori; Iwao, Yushiro

doi:10.2208/jscej.1996.549_19

Cited by 6 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commonly used transfer functions include the tansigmoid, log-sigmoid and linear functions. For example, Emami et al (1996) and Garcia et al (2007) adopted the sigmoid function, Ahmad et al (2008) tan-sigmoid function, Günaydin and Günaydin (2008) considered combinations of tan-sigmoid and log-sigmoid functions for the estimation of the peak ground motion parameters.…”

Section: Basic Concepts Of Artificial Neural Networkmentioning

confidence: 99%

“…The ANN has three interconnected components: input layer, hidden layer(s) and output layer; the observed historical or experimental input and output information are used to train (synaptic) weights and biases to predict outputs (Rumelhart et al, 1986;Funahashi, 1989;Haykin, 1999;Principe et al, 1999). The application of the ANN to predict the ground motion measures has been presented by Wang (1993), Emami et al (1996), Kerh and Chu (2002), Garcia et al (2007), Ahmad et al (2008), and Günaydin and Günaydin (2008). These s-tudies considered ground motion parameters such as the PGA, PGV, and PGD.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Observations on the application of artificial neural network to predicting ground motion measures

2012

View full text Add to dashboard Cite

Application of the artificial neural network (ANN) to predict pseudospectral acceleration or peak ground acceleration is explored in the study. The training of ANN model is carried out using feed-forward backpropagation method and about 600 records from 39 California earthquakes. The statistics of the residuals or modeling error for the trained ANN-based models are almost the same as those for the parametric ground motion prediction equations, derived through regression analysis; the residual or modeling error can be modeled as a normal variate. The similarity and differences between the predictions by these two approaches are shown. The trained ANN-based models, however, are not robust because the models with almost identical mean square errors do not always lead to the same predictions. This undesirable behaviour for predicting the ground motion measures has not been shown or discussed in the literature; the presented results, at least, serve to raise questions and caution on this problem. A practical approach to ameliorate this problem, perhaps, is to consider several trained ANN models, and to take the average of the predicted values from the trained ANN models as the predicted ground motion measure.

show abstract

Section: Basic Concepts Of Artificial Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Observations on the application of artificial neural network to predicting ground motion measures

2012

View full text Add to dashboard Cite

show abstract

“…The sigmoid function has no linearity and activates in every layer except the input layer (Emami et al, 1996;Yagawa and Okuda, 1996). Back-propagation algorithm (BPA), which is one of the most famous training algorithms for the MLP (Altinkok and Koker, 2004), is a gradient descent technique to minimize the error for a particular training pattern.…”

Section: Overview Of Ann and Proposed Ann Modelmentioning

confidence: 99%

“…Once the ANN is adequately trained, it can generalize to similar cases, which it has never seen. Detailed information about ANN and its working principles can be found in references (Altinkok and Koker, 2004;Wu and Lim, 1993;Emami et al, 1996;Yagawa and Okuda, 1996).…”

Section: Overview Of Ann and Proposed Ann Modelmentioning

confidence: 99%

Prediction of martensite and austenite start temperatures of the Fe-based shape memory alloys by artificial neural networks

Eyerci̇oğlu

Kanca

Pala

et al. 2008

Journal of Materials Processing Technology

View full text Add to dashboard Cite

“…While machine learning methods are often considered to be "black box" algorithms, they are helpful in informing human understanding of relationships between input parameters and ground motions. Machine learning techniques like ANNs have been used to predict peak ground motions with data from Western North America (Emami, Iwao, Harada 1996;Trugman and Shearer, 2018), the Next Generation Attenuation of Ground Motion (NGA) database (Alavi and Gandomi 2011;Aagaard, 2017;Dhanya and Rachukanth, 2018), Europe (Derras, Bard, Cotton, 2014), Japan (Derras, Bard, Cotton, 2012), Central and Eastern North America (Khosravikia et al, 2018), and Northwest Turkey (Günaydın and Günaydın, 2008). While many of these papers compare their ANN GMMs to existing GMMs, they do not develop and compare their ANN model to a regression GMM developed with the exact same dataset.…”

mentioning

confidence: 99%

Comparing Artificial Neural Networks with Traditional Ground-Motion Models for Small-Magnitude Earthquakes in Southern California

Klimasewski

Sahakian

Thomas

2021

Bulletin of the Seismological Society of America

View full text Add to dashboard Cite

Traditional, empirical ground-motion models (GMMs) are developed by prescribing a functional form between predictive parameters and ground-motion intensity measures. Machine-learning techniques may serve as a fully data-driven alternative to widely used regression techniques, as they do not require explicitly defining these relationships. Although, machine-learning methods offer a nonparametric alternative to regression methods, there are few studies that develop and assess performance of traditional versus machine-learning GMMs side by side. We compare the performance and behavior of these two approaches: a mixed-effects maximum-likelihood (MEML) model and a feed-forward artificial neural network (ANN). We develop and train both models on the same dataset from southern California. We subsequently test both models on a dataset from the 2019 Ridgecrest sequence, in a new region and on magnitudes outside the range of the training dataset, to examine model portability. Our models estimate horizontal peak ground acceleration, and the input parameters include moment magnitude (M) and hypocentral distance (Rhyp), and some include a site parameter, either VS30 or κ0. We find that, with our small set of input parameters, the ANN generally shows more site-specific predictions than the MEML model with more variation between sites, and, performs better than their corresponding MEML model, when applied “blind” to our testing dataset (in which the MEML random effects cannot be considered). Although, previous studies have found that κ0 may be a better predictor of site effects than VS30, we found similar performance, suggesting that including a site parameter may be more important than the physical meaning of the parameter. Finally, when applying our models to our Ridgecrest dataset, we find that both methods perform well; however, the MEML models perform better with the new dataset than the ANN models, suggesting that future applications of ANN models may need to consider how to accommodate model portability.

show abstract

Prediction of Peak Horizontal Acceleration Using an Artificial Neural Network Model

Cited by 6 publications

References 17 publications

Observations on the application of artificial neural network to predicting ground motion measures

Observations on the application of artificial neural network to predicting ground motion measures

Prediction of martensite and austenite start temperatures of the Fe-based shape memory alloys by artificial neural networks

Comparing Artificial Neural Networks with Traditional Ground-Motion Models for Small-Magnitude Earthquakes in Southern California

Contact Info

Product

Resources

About