|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ЦЭМИ РАН |
||
Use of Adaptive Neural Network Based Algorithms of Data Classification in the Solution of the Inverse Problem of Electrical Prospectingдоклад на конференции
- Авторы: Персианцев И.Г., Оборнев Е.А., Доленко С.А., Шимелевич М.И.
- Международная Конференция : 9th International Conference "Pattern Recognition and Image Analysis: New Information Technologies" (PRIA-9-2008)
- Даты проведения конференции: 2008
- Тип доклада: не указан
- Докладчик: не указан
- Место проведения: Nizhnii Novgorod
-
Аннотация доклада:
One of the important directions of research in geophysical electrical prospecting is solution of inverse problems (IP), in particular, the IP of magnetotellurics – the problem of determining the distribution of electrical conductivity in the thickness of earth by the values of electromagnetic field induced by ionosphere sources, observed on earth surface. Simplification of the model of the section with its subsequent resolution makes it possible to limit oneself with solving a small number of known to be more stable IP in narrower classes of geoelectrical sections. This study includes comparative analysis of the application results of different methods of adaptive classification to determine the one of these narrow classes to which the result of the next observation belongs.
- Добавил в систему: Доленко Сергей Анатольевич