ONR GRADUATE STUDENT TRAINEESHIP: UNDERWATER ACOUSTIC SOURCE LOCALIZATION IN A MACHINE LEARNING FRAMEWORK

Abstract

The primary objective of this research is to improve source localization for sources of opportunity in shallow water by applying mac"hine learning (ML) methods. Specifically, this research aims to investigate long-range and low SNR settings, multiple source localiz""ation problems, extraction of environmental knowledge via learned functional approximations, and effects of variation in training an"d test data sets. These will be examined under the data-driven framework of ML with additional effort to include physical constraint"s. Due to the unique propagation conditions in ocean acoustics, it will be important to incorporate ocean acoustic models into this" effort. The Shallow-water Characterization Experiment (SCE) 2017 will first be used to test the methods.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 23, 2018
Source ID
N000141812065

Entities

People

  • Peter Gerstoft

Organizations

  • Office of Naval Research
  • United States Navy
  • University of California, San Diego

Tags

Readers

  • Acoustical Oceanography.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks