Storytelling with Receiver Operating Characteristic (ROC) Curves for Environmental Remediation of Unexploded Ordnance (UXO)

Abstract

Receiver operating characteristic (ROC) curves are often used to assess the performance of binary classification systems, allowing stakeholders to understand tradeoffs between Type I (false positive) and Type II (false negative) errors. This works well in textbook cases. In real-world experiments, however, ROC curves can have unexpected subtleties that make them difficult to construct and interpret. For example, the Department of Defense is sponsoring the development of novel sensors and software to identify unexploded ordnance (UXO) in the midst of clutter. UXO are duds--munitions that were previously armed and fired but failed to explode. UXO can still pose a risk of detonation even decades later, threatening the safety of nearby humans, animals, vegetation, and structures. Conducting blind tests to demonstrate finding UXO is fraught with safety, logistical, and cost constraints that make it difficult to construct the textbook ROC curves. Yet, with careful planning and a few key assumptions, ROC-like curves can still be crafted to quickly tell the story of how well novel sensors and software can detect, classify, and locate UXO versus clutter in terrestrial and underwater experiments.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2021
Accession Number
AD1199469

Entities

People

  • Jacob B. Bartel
  • Shelley M. Cazares

Organizations

  • Institute for Defense Analyses

Tags

Communities of Interest

  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Ammunition
  • Classification
  • Demonstrations
  • Department Of Defense
  • Detection
  • Detectors
  • Detonations
  • Divers
  • Environmental Restoration And Remediation
  • Environmental Security
  • False Alarms
  • Geolocation
  • Global Positioning Systems
  • Governments
  • Munitions
  • Physics Laboratories
  • Plants
  • Second World War
  • Security
  • Textbooks
  • Unexploded Ammunition
  • Warning Systems

Fields of Study

  • Computer science

Readers

  • Military/Explosive Ordnance Disposal (EOD) Technology
  • Regression Analysis.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy