Obstacle segmentation based on the wave equation and deep learning

Adar Kahana, Eli Turkel, Shai Dekel, Dan Givoli

Research output: Contribution to journalArticlepeer-review


We model the inverse physical problem of identifying an underwater obstacle by using the acoustic wave equation. Measurements are collected in a set of sensors placed in the medium. We use this partial information to approximate a segmentation of the obstacle in its correct location. This is an ill-posed problem. We propose a novel deep learning architecture that takes as input the sensor data and computes an approximate segmentation map of the obstacle.

Original languageEnglish
Article number109458
JournalJournal of Computational Physics
StatePublished - 15 Jul 2020


  • Deep learning
  • Inverse problems
  • Obstacle identification
  • Wave equation


Dive into the research topics of 'Obstacle segmentation based on the wave equation and deep learning'. Together they form a unique fingerprint.

Cite this