Integrating modeled environmental variability into neural network training for underwater source localization
- 1 June 2023
- journal article
- research article
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 153 (6) , 3201
Abstract
Supervised machine learning (ML) is a powerful tool that has been applied to many fields of underwater acoustics, including acoustic inversion. ML algorithms depend on the existence of extensive labeled datasets, which are difficult to obtain for the task of underwater source localization. A feed-forward neural network (FNN) trained on imbalanced or biased data may end up suffering from a problem analogous to model mismatch in matched field processing (MFP), that is, producing incorrect results due to a difference between the environment sampled by the training data and the actual environment. To overcome this issue, physical and numerical propagation models can act as data augmentation tools to compensate for the lack of comprehensive acoustic data. This paper examines how modeled data can be effectively used for training FNNs. Mismatch tests compare the output from a FNN and MFP and show that the network becomes more robust to various kinds of mismatches when trained on diverse environments. A systematic analysis of how the training dataset's variability impacts a FNN's localization performance on experimental data is carried out. Results show that networks trained with synthetic data achieve better and more robust performance than regular MFP when environment variability is taken into account.Keywords
This publication has 33 references indexed in Scilit:
- Conceptual complexity and the bias/variance tradeoffCognition, 2011
- Matched-field processing using measured replica fieldsThe Journal of the Acoustical Society of America, 2000
- Mirages in shallow water matched field processingThe Journal of the Acoustical Society of America, 1999
- Training with Noise is Equivalent to Tikhonov RegularizationNeural Computation, 1995
- Noise injection into inputs in back-propagation learningIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Using additive noise in back-propagation trainingIEEE Transactions on Neural Networks, 1992
- An artificial neural network for range and depth discrimination in matched field processingThe Journal of the Acoustical Society of America, 1991
- Environmental and system effects on source localization in shallow water by the matched-field processing of a vertical arrayThe Journal of the Acoustical Society of America, 1989
- Effects of water-depth mismatch on matched-field localization in shallow waterThe Journal of the Acoustical Society of America, 1988
- Use of calculated sound fields and matched-field detection to locate sound sources in shallow waterThe Journal of the Acoustical Society of America, 1976