Seismic data processing effect evaluation method based on neural network

The invention provides a seismic data processing effect evaluation method based on a neural network, and the method comprises the steps: 1, extracting a plurality of seismic attributes, and carrying out the standardization processing; 2, for each seismic data processing stage, performing principal c...

Full description

Saved in:
Bibliographic Details
Main Authors DONG TAO, ZHANG JUNWEI, FU QIAOJUAN, DUAN MIAO, QIU XIAOGUO, LIU FANG, LI ZHANQIANG, SUN YOUKAI, LI NAIJU, ZHU YINGKE
Format Patent
LanguageChinese
English
Published 01.08.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DETECTING MASSES OR OBJECTS
ELECTRIC DIGITAL DATA PROCESSING
GEOPHYSICS
GRAVITATIONAL MEASUREMENTS
MEASURING
PHYSICS
TESTING
Online AccessGet full text

Cover

More Information
Summary:The invention provides a seismic data processing effect evaluation method based on a neural network, and the method comprises the steps: 1, extracting a plurality of seismic attributes, and carrying out the standardization processing; 2, for each seismic data processing stage, performing principal component analysis of seismic attributes, and establishing a seismic data feature data set; 3, constructing a three-layer neural network for each seismic data processing stage; 4, training the neural network until the prediction error is smaller than the expectation; and step 5, constructing a feature vector based on the attribute set of the seismic data after true processing and the attribute set of the seismic data after prediction processing, calculating a vector similarity by using an included angle cosine distance algorithm, and performing quantitative evaluation of a processing effect. According to the seismic data processing effect evaluation method based on the neural network, the accuracy of the prediction
Bibliography:Application Number: CN202210072420