Unexploded ordnance discrimination using time-domain electromagnetic induction and self-organizing maps

Self-organizing maps (SOM) are implemented for discrimination of geologic noise, buried metal objects and unexploded ordnance using the geophysical method of time-domain electromagnetic induction. The learning and misfit measures are based on a Euclidean metric. The U*-matrix method is shown to be a reliable tool for determining data clusters and cluster boundaries. The performance of SOM for data-type discrimination was tested using three synthetic, idealized geophysical datasets consisting of exponential, multi-exponential and stretched-exponential decaying transients. In addition, experimental data were acquired using a modified Geonics EM63 instrument. Results from the synthetic examples show that SOM clusters the data based on their functional origin, when represented using U*-matrices. The percentage of correct classification is 100%. Unsupervised learning using the field dataset obtained with the Geonics EM63 succeeded in producing a multi-clustered map in which the background transients cluster themselves and are separated from clusters associated with metal clutter objects and UXO. Even though in some cases the SOM did not produce a single cluster for each type of causative body, it was able to separate clutter data from target data by producing several small clusters. The results are encouraging in view of the heterogeneity and sparsity of the training dataset.

[1]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[2]  Lin Zhang,et al.  Classification of salt-contaminated velocities with self-organizing map neural network , 2002 .

[3]  Fernando Bação,et al.  The self-organizing map, the Geo-SOM, and relevant variants for geosciences , 2005, Comput. Geosci..

[4]  Fabien Moutarde,et al.  U*F clustering: a new performant "cluster-mining" method based on segmentation of Self-Organizing Maps , 2005 .

[5]  Mark E. Everett,et al.  Non-linear inversion of controlled source multi-receiver electromagnetic induction data for unexploded ordnance using a continuation method , 2007 .

[6]  Richard Uden,et al.  Data mining of 3D poststack seismic attribute volumes using Kohonen self-organizing maps , 2002 .

[7]  Michael Commer,et al.  A parallel finite-difference approach for 3D transient electromagnetic modeling with galvanic sources , 2004 .

[8]  Leonard R. Pasion,et al.  Locating and Characterizing Unexploded Ordnance Using Time Domain Electromagnetic Induction , 2001 .

[9]  H. C. Chen,et al.  Identification of lithofacies using Kohonen self-organizing maps , 2002 .

[10]  Mary M. Poulton,et al.  Location of subsurface targets in geophysical data using neural networks , 1992 .

[11]  Mark E. Everett,et al.  An experimental study of the time-domain electromagnetic response of a buried conductive plate , 2005 .

[12]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[13]  Arkady Aizenberg,et al.  3D diffraction modeling of singly scattered acoustic wavefields based on the combination of surface integral propagators and transmission operators , 2007 .

[14]  Leslie M. Collins,et al.  A comparison of the performance of statistical and fuzzy algorithms for unexploded ordnance detection , 2001, IEEE Trans. Fuzzy Syst..

[15]  David W. Scott,et al.  Multivariate Density Estimation: Theory, Practice, and Visualization , 1992, Wiley Series in Probability and Statistics.

[16]  A. Ultsch.  Maps for the Visualization of high-dimensional Data Spaces , 2003 .

[17]  Stephen D. Billings,et al.  Discrimination and classification of buried unexploded ordnance using magnetometry , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Klaus Schulten,et al.  Self-organizing maps: ordering, convergence properties and energy functions , 1992, Biological Cybernetics.

[19]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[20]  Michael Georgiopoulos,et al.  Applications of Neural Networks in Electromagnetics , 2001 .

[21]  M. Matos,et al.  Unsupervised seismic facies analysis using wavelet transform and self-organizing maps , 2007 .

[22]  Y. Das,et al.  Analysis of an electromagnetic induction detector for real-time location of buried objects , 1990 .

[23]  Jack Stalnaker,et al.  Mutual induction and the effect of host conductivity on the EM induction response of buried plate targets using 3-D finite-element analysis , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[24]  B. Everitt,et al.  Cluster Analysis (2nd ed). , 1982 .

[25]  G. Polzlbauer,et al.  A visualization technique for self-organizing maps with vector fields to obtain the cluster structure at desired levels of detail , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[26]  Dwain K. Butler.  Report on a workshop on electromagnetic induction methods for UXO detection and discrimination , 2004 .

[27]  Christian D. Klose,et al.  Self-organizing maps for geoscientific data analysis: geological interpretation of multidimensional geophysical data , 2006 .

[28]  Mary M. Poulton,et al.  Neural network pattern recognition of subsurface EM images , 1992 .

[29]  Sven Treitel,et al.  Identification and classification of multiple reflections with self-organizing maps , 2001 .

[30]  Thomas Elbert,et al.  Semantic Categorization in the Human Brain , 2003, Psychological science.