Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Использование искусственных нейронных сетей для выделения по морским мультичастотным сейсмоакустическим данным опасных геологических процессов и явлений. / Galaev, V. E.; Iakushkin, O. O.; Tokarev, M. Yu; Terekhina, Ya E.; Nikolskaya, A. N.; Bulanova, I. A.
17th Conference and Exhibition Engineering and Mining Geophysics 2021. European Association of Geoscientists and Engineers, 2021. (Engineering and Mining Geophysics 2021).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Использование искусственных нейронных сетей для выделения по морским мультичастотным сейсмоакустическим данным опасных геологических процессов и явлений
AU - Galaev, V. E.
AU - Iakushkin, O. O.
AU - Tokarev, M. Yu
AU - Terekhina, Ya E.
AU - Nikolskaya, A. N.
AU - Bulanova, I. A.
N1 - Publisher Copyright: © Conference and Exhibition Eng. and Mining Geophysics 2021. All rights reserved.
PY - 2021
Y1 - 2021
N2 - This work considers the task of automatic identification of discontinuities from high resolution 2D seismoacoustic data. The training of artificial intelligence in this work was performed exclusively on real multifrequency seismoacoustic data, which were marked by an expert. As a result of the work the main problems arising at the decision of a task of creation of the automated marking tool on the basis of the real data marked out by the person have been allocated. The importance of selecting a loss function and the possibility of applying radical data compression while keeping the result close to human markup were noted.
AB - This work considers the task of automatic identification of discontinuities from high resolution 2D seismoacoustic data. The training of artificial intelligence in this work was performed exclusively on real multifrequency seismoacoustic data, which were marked by an expert. As a result of the work the main problems arising at the decision of a task of creation of the automated marking tool on the basis of the real data marked out by the person have been allocated. The importance of selecting a loss function and the possibility of applying radical data compression while keeping the result close to human markup were noted.
UR - http://www.scopus.com/inward/record.url?scp=85114241564&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/76de059f-632b-3466-8095-924fc4cab3a5/
U2 - 10.3997/2214-4609.202152203
DO - 10.3997/2214-4609.202152203
M3 - статья в сборнике материалов конференции
AN - SCOPUS:85114241564
SN - 9789462823723
T3 - Engineering and Mining Geophysics 2021
BT - 17th Conference and Exhibition Engineering and Mining Geophysics 2021
PB - European Association of Geoscientists and Engineers
T2 - Инженерная и рудная геофизика 2021
Y2 - 26 April 2021 through 30 April 2021
ER -
ID: 85751619