Demonstration and Validation of Statistical Analysis Techniques for TOI Discrimination Using Advanced EMI Sensor Systems

MR-201156

Demonstration Summary

This project will demonstrate the ability of advanced analysis techniques, previously developed with SERDP support, to achieve high-fidelity discrimination between buried munitions or targets of interest (TOIs) and clutter. These advanced methods will be applied to next-generation electromagnetic induction (EMI) sensor data acquired as part of the live site demonstrations. Manual involvement in the processing decisions will be augmented and then supplanted by automated techniques. At the conclusion of the project, a mature process for automated TOI discrimination will be documented and potentially validated, including data pre-processing, feature extraction, and classification. Continued refinement and maturation of the techniques will reduce the cost and complexity of the analysis process for site remediation. If successful, these techniques may be automated and transitioned to production unexploded ordnance (UXO) cleanups and lead to significant cost savings by allowing harmless clutter items to remain in the ground.

Back to Top

Technology Description

This project will combine several advanced techniques that incorporate and are centered in a Bayesian approach to quantify statistical uncertainty--automated anomaly segmentation algorithms, physics-based target/sensor models, robust inversion algorithms for feature extraction, algorithms for data-driven feature selection, supervised and semi-supervised Bayesian classification algorithms, information-gain-based active learning for efficient label selection, multi-task learning (MTL) for sharing information from one site to the next, and principled cost- and cross-validation-based threshold selection. Each of these techniques plays a role in an overall discrimination-based approach to site remediation. The statistical rigor of these approaches enables them to make more informed decisions both in data collection (improving efficiency) and in target declaration (ensuring accuracy). The techniques represent the pairing of advanced robust data collection techniques and optimization of state-of-the-art digital geophysics.

Back to Top

Project Documents

Points of Contact

Principal Investigator

Mr. Levi Kennedy

Signal Innovations Group, Inc.

Phone: 919-323-5612

Program Manager

Munitions Response

SERDP and ESTCP

Project Documents

Document Types

  • Fact Sheet - Brief project summary with links to related documents and points of contact.
  • Final Report - Comprehensive report for every completed SERDP and ESTCP project that contains all technical results.
  • Cost & Performance Report - Overview of ESTCP demonstration activities, results, and conclusions, standardized to facilitate implementation decisions.
  • Technical Report - Additional interim reports, laboratory reports, demonstration reports, and technology survey reports.
  • Guidance - Instructional information on technical topics such as protocols and user’s guides.
  • Workshop Report - Summary of workshop discussion and findings.
  • Multimedia - On demand videos, animations, and webcasts highlighting featured initiatives or technologies.
  • Model/Software - Computer programs and applications available for download.
  • Database - Digitally organized collection of data available to search and access.