Choice of optimal configuration of neuron net in case of modeling the travel-time curves of seismic waves and estimation of adequacy of the model to real situations
DOI:
https://doi.org/10.24028/gzh.0203-3100.v34i2.2012.116616Abstract
The choice of the optimal neural net topology is performed for seismic phase onset simulation. Based on «Odessa» seismic station earthquake signal records excited by the sources of the Black Sea region the reliability of model outputs, operation stability related to source distribution density and seismic radiation flow direction are evaluated. The graphic examples are presented.References
Горбань А. Н. Обучение нейронных сетей. - Москва: СП ПараГраф, 1990. - 160 с.
Лазаренко М. А, Герасименко О. А. Моделювання сейсмічної анізотропії кори і верхньої мантії акваторії Чорного моря за допомогою мереж штучних нейронів // Вісник Київ. нац. ун-ту. - 2008. - Вип. 45. - C. 18-23.
Лазаренко М. А, Герасименко О. А. Нейросетевое моделирование локальных годографов сейсмических волн // Геофиз. журн. - 2010. - 32, № 5. - С. 126-141.
Лазаренко М. А., Герасименко О. А., Остапчук Н. Н. Особенности нейросетевого моделирования локальных годографов сейсмических волн // Геофиз. журн. - 2011. - 39, № 6. - С. 112-114.
Тарков М. С. Нейрокомпьютерные системы. - Москва: Бином, 2006. - 140 с.
Хайкин С. Нейронные сети: Полный курс. - 2-е изд., испр. - Москва: Издательский дом Вильямс, 2006. - 1103 с.
Cybenko G. Approximation by superpositions of sigmoidal functions // Math. Control Sygnal Systems. - 1989. - 2. - P. 303-314.
Jeffreys H., Bullen K. E. Seismological Tables. - London: British Association Seismological Committee, 1940. - 145 р.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Geofizicheskiy Zhurnal
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).