An Expert System Approach for Prediction of Maritime Visibility Obscuration

Abstract

An Expert system for Shipboard Obscuration Prediction (AESOP), and Artificial Intelligence (AI) approach to forecasting maritime visibility obscurations, has been designed, developed, and tested. AESOP is rule-based, using backward chaining. The current version, AESOP 2.1, has 290 rules and has been designed in terms of nowcasts (0-1 hr) and forecasts (1-6 hr). An extensive explanation feature allows the user to understand the reasoning process behind a particular forecast. AESOP has been evaluated against 100 independent test cases, in which clear, hazy, or foggy conditions are predicted. The overall performance of AESOP is 68% correct. This value indicates considerable forecast skill when compared to 36% for random chance. When the distinction between clear and haze is ignored, the expert system correctly forecasts 79% of the Fog/No fog situations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1990
Accession Number
ADA238305

Entities

People

  • James A. Peak

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Air Platforms
  • Ground and Sea Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Computer Programs
  • Computers
  • Delphi Method
  • Expert Systems
  • Inference Engines
  • Language
  • Navy
  • Obscuration
  • Reasoning
  • Research Facilities
  • Sea Surface Temperature
  • Shipboard
  • Simulations
  • Surface Temperature
  • Visibility

Readers

  • Atmospheric Remote Sensing.
  • Atmospheric Science/Meteorology
  • Wave Propagation and Nonlinear Chaotic Dynamics.

Technology Areas

  • AI & ML