Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks
Fuente:
Redalyc
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artículo científico |
| Lingua: | en |
| Pubblicazione: |
Universidad Nacional Autónoma de México
2007
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1876479894860333056 |
|---|---|
| author | Juan M. Mayoral |
| author_facet | Juan M. Mayoral |
| contents | Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks Juan M. Mayoral Silvia R. García Miguel P. Romo Ciencias de la Tierra PGAs subduction attenuation Neuronal network An extensive analysis of the strong ground motion Mexican data base was conducted using Soft Computing (SC) techniques.A Neural Network NN is used to estimate both orthogonal components of the horizontal (PGAh) and vertical (PGAv) peak groundaccelerations measured at rock sites during Mexican subduction zone earthquakes. The work discusses the development, training,and testing of this neural model. Attenuation phenomenon was characterized in terms of magnitude, epicentral distance and focaldepth. Neural approximators were used instead of traditional regression techniques due to their fl exibility to deal with uncertaintyand noise. NN predictions follow closely measured responses exhibiting forecasting capabilities better than those of most establishedattenuation relations for the Mexican subduction zone. Assessment of the NN, was also applied to subduction zones in Japan andNorth America. For the database used in this paper the NN and the-better-fi tted- regression approach residuals are compared. 2007 artículo científico 0016-7169 https://www.redalyc.org/articulo.oa?id=56846103 en http://www.redalyc.org/revista.oa?id=568 Geofísica Internacional application/pdf Universidad Nacional Autónoma de México Geofísica Internacional (México) Num.1 Vol.46 |
| format | Artículo científico |
| id | redalyc_56846103 |
| institution | Redalyc |
| language | en |
| publishDate | 2007 |
| publisher | Universidad Nacional Autónoma de México |
| spellingShingle | Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks Juan M. Mayoral Ciencias de la Tierra PGAs subduction attenuation Neuronal network Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks Juan M. Mayoral Silvia R. García Miguel P. Romo Ciencias de la Tierra PGAs subduction attenuation Neuronal network An extensive analysis of the strong ground motion Mexican data base was conducted using Soft Computing (SC) techniques.A Neural Network NN is used to estimate both orthogonal components of the horizontal (PGAh) and vertical (PGAv) peak groundaccelerations measured at rock sites during Mexican subduction zone earthquakes. The work discusses the development, training,and testing of this neural model. Attenuation phenomenon was characterized in terms of magnitude, epicentral distance and focaldepth. Neural approximators were used instead of traditional regression techniques due to their fl exibility to deal with uncertaintyand noise. NN predictions follow closely measured responses exhibiting forecasting capabilities better than those of most establishedattenuation relations for the Mexican subduction zone. Assessment of the NN, was also applied to subduction zones in Japan andNorth America. For the database used in this paper the NN and the-better-fi tted- regression approach residuals are compared. 2007 artículo científico 0016-7169 https://www.redalyc.org/articulo.oa?id=56846103 en http://www.redalyc.org/revista.oa?id=568 Geofísica Internacional application/pdf Universidad Nacional Autónoma de México Geofísica Internacional (México) Num.1 Vol.46 |
| title | Estimation of peak ground accelerations for Mexican subduction zone earthquakes using neural networks |
| topic | Ciencias de la Tierra PGAs subduction attenuation Neuronal network |
| url | https://www.redalyc.org/articulo.oa?id=56846103 |