Open AccessA New Improved Algorithm for Aeromagnetic Compensation
Author(s) -
Xiao Zhao,
Ping Yu,
Jiao Ji
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/660/1/012132
Subject(s) - compensation (psychology) , collinearity , coefficient matrix , autoencoder , algorithm , dimension (graph theory) , computer science , representation (politics) , feature (linguistics) , artificial intelligence , matrix (chemical analysis) , correlation coefficient , pattern recognition (psychology) , artificial neural network , mathematics , machine learning , statistics , philosophy , materials science , psychoanalysis , law , linguistics , composite material , psychology , quantum mechanics , political science , eigenvalues and eigenvectors , physics , politics , pure mathematics
Magnetic compensation is a necessary step in aeromagnetic data processing. The aeromagnetic compensation model is a linear regression model, but the model has multiple collinearity problems, which will reduce the performance of the compensation model. In view of this problem, we propose a deep autoencoder (DAE) aeromagnetic compensation algorithm. The DAE network extracts the features of the data by learning the compressed representation of the coefficient matrix, thereby weakening the correlation between the coefficient matrix variables. The feature obtained after dimension reduction is used for compensation calculation. The DAE algorithm is verified by Unmanned Aerial Vehicles, and the results show that the compensation quality of the DAE is better than the least squares algorithm.