Predicting underwater ocean noise with genetic algorithms

In this Letter we employ recent developments on nonlinear physics and time series prediction to study the physical characteristics of measured underwa ter ambient noise. Specifically, we examine the predictability of a sample of ocean ambient noise recorded in the Strait of Sicily. Italy. To do that, an approach based on genetic algorithms has been employed. Results indicat e that, while showing a complex time variability, the recorded signal is hi ghly predictable due to the probable contribution of shipping noise. More g eneral, the Letter addresses the possible development of future time domain noise mitigation strategies. very relevant to underwater communications, b ased on methodologies of nonlinear physics. (C) 2001 Elsevier Science B.V. All rights reserved.