Machine-learning based detection of marine mammal vocalizations in snapping-shrimp dominated ambient noise.

Passive acoustics is an effective method for monitoring marine mammals, facilitating both detection and population estimation. In warm tropical waters, this technique encounters challenges due to the high persistent level of ambient impulsive noise originating from the snapping shrimp present throughout this region. This study presents the development and application of a neural-network based detector for marine-mammal vocalizations in long term acoustic data recorded by us at ten locations in Singapore waters. The detector's performance is observed to be impeded by the high shrimp noise activity. To counteract this, we investigate several techniques to improve detection capabilities in shrimp noise including the use of simple nonlinear denoisers and a machine-learning based denoiser. These are shown to enhance the detection performance significantly. Finally, we discuss some of the vocalizations detected over three years of our acoustic recorder deployments using the robust detectors developed.

A dolphin-inspired compact sonar for underwater acoustic imaging.

Underwater imaging sonars are widely used for oceanic exploration but are bulky and expensive for some applications. The sonar system of dolphins, which uses sound pulses called clicks to investigate their environment, offers superior shape discrimination capability compared to human-derived imaging sonars of similar size and frequency. In order to gain better understanding of dolphin sonar imaging, we train a dolphin to acoustically interrogate certain objects and match them visually. We record the echoes the dolphin receives and are able to extract object shape information from these recordings. We find that infusing prior information into the processing, specifically the sparsity of the shapes, yields a clearer interpretation of the echoes than conventional signal processing. We subsequently develop a biomimetic sonar system that combines sparsity-aware signal processing with high-frequency broadband click signals similar to that of dolphins, emitted by an array of transmitters. Our findings offer insights and tools towards compact higher resolution sonar imaging technologies.

Possible limitations of dolphin echolocation: a simulation study based on a cross-modal matching experiment.

Dolphins use their biosonar to discriminate objects with different features through the returning echoes. Cross-modal matching experiments were conducted with a resident bottlenose dolphin (Tursiops aduncus). Four types of objects composed of different materials (water-filled PVC pipes, air-filled PVC pipes, foam ball arrays, and PVC pipes wrapped in closed-cell foam) were used in the experiments, respectively. The size and position of the objects remained the same in each case. The data collected in the experiment showed that the dolphin's matching accuracy was significantly different across the cases. To gain insight into the underlying mechanism in the experiments, we used finite element methods to construct two-dimensional target detection models of an echolocating dolphin in the vertical plane, based on computed tomography scan data. The acoustic processes of the click's interaction with the objects and the surrounding media in the four cases were simulated and compared. The simulation results provide some possible explanations for why the dolphin performed differently when discriminating the objects that only differed in material composition in the previous matching experiments.