“…Various studies have found that ML achieved lower error in source ranging than MFP, especially in complex ocean environments with low SNR [5][6][7]. In addition, progressively increasing network architectures, such as FNN [5,6], TDNN [7,8], CNN [9,10], ResNet [11][12][13], and Inceptions [10], are applied to underwater acoustic localization to mine deep features and decouple sound source information from the underwater acoustic environment. This application of ML to source ranging has been demonstrated to achieve good localization results in both synthetic and experimental data sets collected on the sea.…”