A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Tsunamigenic Seismic Activity (Earthquakes) Prediction from III- Component Seismic Data
https://orcid.org/http://orcid.org/0000-0002-3332-8083
In this study, two classification methods such as the artificial neural network with feed-forward backpropagation (ANN) and random forest regression (RFR) were used to identify tsunamigenic earthquakes at a regional distance with shallow focus depth (less than 70 km). To attain the tsunamigenic earthquake classification, depth (H), distance (D), azimuth (A), moment magnitude (Mw), and fault parameter (ϕs, δ, λ) were used as a input parameters. The total collected data was divided into two parts such as for training (70% of total data) and testing (remaining 30% data). The trained ANN and RFR were found to successfully categorize as tsunamigenic or non-tsunamigenic 100% and 89%, respectively. The ANN and RFR methods may be useful where insufficient weak tsunami alert systems (TAS) are available in the vicinity.
Tsunamigenic Seismic Activity (Earthquakes) Prediction from III- Component Seismic Data
https://orcid.org/http://orcid.org/0000-0002-3332-8083
In this study, two classification methods such as the artificial neural network with feed-forward backpropagation (ANN) and random forest regression (RFR) were used to identify tsunamigenic earthquakes at a regional distance with shallow focus depth (less than 70 km). To attain the tsunamigenic earthquake classification, depth (H), distance (D), azimuth (A), moment magnitude (Mw), and fault parameter (ϕs, δ, λ) were used as a input parameters. The total collected data was divided into two parts such as for training (70% of total data) and testing (remaining 30% data). The trained ANN and RFR were found to successfully categorize as tsunamigenic or non-tsunamigenic 100% and 89%, respectively. The ANN and RFR methods may be useful where insufficient weak tsunami alert systems (TAS) are available in the vicinity.
Tsunamigenic Seismic Activity (Earthquakes) Prediction from III- Component Seismic Data
https://orcid.org/http://orcid.org/0000-0002-3332-8083
In this study, two classification methods such as the artificial neural network with feed-forward backpropagation (ANN) and random forest regression (RFR) were used to identify tsunamigenic earthquakes at a regional distance with shallow focus depth (less than 70 km). To attain the tsunamigenic earthquake classification, depth (H), distance (D), azimuth (A), moment magnitude (Mw), and fault parameter (ϕs, δ, λ) were used as a input parameters. The total collected data was divided into two parts such as for training (70% of total data) and testing (remaining 30% data). The trained ANN and RFR were found to successfully categorize as tsunamigenic or non-tsunamigenic 100% and 89%, respectively. The ANN and RFR methods may be useful where insufficient weak tsunami alert systems (TAS) are available in the vicinity.
Tsunamigenic Seismic Activity (Earthquakes) Prediction from III- Component Seismic Data
Lecture Notes in Civil Engineering
Sitharam, T. G. (editor) / Kolathayar, Sreevalsa (editor) / Sharma, Mukat Lal (editor) / Gnananandarao, Tammineni (author) / Kumar Dutta, Rakesh (author) / Khatri, Vishwas Nandkishor (author)
2021-03-23
10 pages
Article/Chapter (Book)
Electronic Resource
English
Colorado Earthquakes and Seismic Hazard
| ASCE | 2010
Earthquakes and seismic hazard in Finland
| Elsevier | 1983
The seismic characteristics of Turkish earthquakes
| British Library Conference Proceedings | 1996
High seismic factors in recent earthquakes
| Engineering Index Backfile | 1933