DocumentCode :
21464
Title :
Learning Machine Identification of Ferromagnetic UXO Using Magnetometry
Author :
Bray, Matthew P. ; Link, Curtis A.
Author_Institution :
Geophys. Eng. Dept., Montana Tech, Butte, MT, USA
Volume :
8
Issue :
2
fYear :
2015
fDate :
Feb. 2015
Firstpage :
835
Lastpage :
844
Abstract :
The fundamental problem in applying geophysical mapping to locate unexploded ordnance (UXO) is distinguishing true UXO from non-UXO. Enhancing the accuracy of UXO detection has multiple benefits, especially in the areas of cost savings and safety. We investigated discrimination approaches using both magnetic field data and numerically modeled data. Libraries of total field magnetic (TFM) responses were calculated using finite element modeling for three UXO types found at a Montana National Guard training site. UXO model parameters were varied over ranges of azimuth, declination, and depth resulting in approximately 600 models per UXO type. The modeled responses of finite-element model (FEM) and actual TFM field data were then used as training data in discrimination and classification approaches comparing neural networks (NN), random forests (RF), and support vector machines (SVMs). The prediction targets in the training process comprised three classes: 1) binary [UXO or noninteresting object (NIO)]; 2) multiclass (UXO round type and NIO); and 3) classes derived from multiclass self-organizing feature map (SOFM) analysis. The multiclass SOFM targets generated from site-specific field data were found to be optimal for UXO discrimination. The best performing combination of class selection types using recentered data for UXO detection rates of 100% resulted in a false alarm rate (FAR) of 28%.
Keywords :
explosive detection; ferromagnetic materials; finite element analysis; geophysics computing; learning (artificial intelligence); magnetometry; pattern classification; self-organising feature maps; FAR; FEM; TFM field data; TFM response; UXO discrimination approach; UXO model parameters variation; classification approach; false alarm rate; ferromagnetic UXO detection rate; finite element modeling; geophysical mapping; learning machine identification; magnetic field; magnetometry; multiclass SOFM analysis; numerical modeling; self-organizing feature map; total field magnetic; training process; unexploded ordnance; Artificial neural networks; Magnetic moments; Magnetometers; Neurons; Shape; Support vector machines; Training; Classification; finite-element model (FEM); magnetics; neural networks (NN); random forest (RF); support vector machine (SVM); unexploded ordnance (UXO);
fLanguage :
English
Journal_Title :
Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of
Publisher :
ieee
ISSN :
1939-1404
Type :
jour
DOI :
10.1109/JSTARS.2014.2362920
Filename :
6942185
Link To Document :
بازگشت