Observational study on the non-linear response of dolphins to the presence of vessels.

With the large increase in human marine activity, our seas have become populated with vessels that can be overheard from distances of even 20 km. Prior investigations showed that such a dense presence of vessels impacts the behaviour of marine animals, and in particular dolphins. While previous explorations were based on a linear observation for changes in the features of dolphin whistles, in this work we examine non-linear responses of bottlenose dolphins (Tursiops Truncatus) to the presence of vessels. We explored the response of dolphins to vessels by continuously recording acoustic data using two long-term acoustic recorders deployed near a shipping lane and a dolphin habitat in Eilat, Israel. Using deep learning methods we detected a large number of 50,000 whistles, which were clustered to associate whistle traces and to characterize their features to discriminate vocalizations of dolphins: both structure and quantities. Using a non-linear classifier, the whistles were categorized into two classes representing the presence or absence of a nearby vessel. Although our database does not show linear observable change in the features of the whistles, we obtained true positive and true negative rates exceeding 90% accuracy on separate, left-out test sets. We argue that this success in classification serves as a statistical proof for a non-linear response of dolphins to the presence of vessels.

A remote sensing approach for exploring the dynamics of jellyfish, relative to the water current.

Drifting in large numbers, jellyfish often interfere in the operation of nearshore electrical plants, cause disturbances to marine recreational activity, encroach upon local fish populations, and impact food webs. Understanding the dynamic mechanisms behind jellyfish behavior is of importance in order to create migration models. In this work, we focus on the small-scale dynamics of jellyfish and offer a novel method to accurately track the trajectory of individual jellyfish with respect to the water current. The existing approaches for similar tasks usually involve a surface float tied to the jellyfish for location reference. This operation may induce drag on the jellyfish, thereby affecting its motion. Instead, we propose to attach an acoustic tag to the jellyfish's bell and then track its geographical location using acoustic beacons, which detect the tag's emissions, decode its ID and depth, and calculate the tag's position via time-difference-of-arrival acoustic localization. To observe the jellyfish's motion relative to the water current, we use a submerged floater that is deployed together with the released tagged jellyfish. Being Lagrangian on the horizontal plane while maintaining an on-demand depth, the floater drifts with the water current; thus, its trajectory serves as a reference for the current's velocity field. Using an acoustic modem and a hydrophone mounted to the floater, the operator from the deploying boat remotely changes the depth of the floater on-the-fly, to align it with that of the tagged jellyfish (as reported by the jellyfish's acoustic tag), thereby serving as a reference for the jellyfish's 3D motion with respect to the water current. We performed a proof-of-concept to demonstrate our approach over three jellyfish caught and tagged in Haifa Bay, and three corresponding floaters. The results present different dynamics for the three jellyfish, and show how they can move with, and even against, the water current.

Automated detection of dolphin whistles with convolutional networks and transfer learning.

Effective conservation of maritime environments and wildlife management of endangered species require the implementation of efficient, accurate and scalable solutions for environmental monitoring. Ecoacoustics offers the advantages of non-invasive, long-duration sampling of environmental sounds and has the potential to become the reference tool for biodiversity surveying. However, the analysis and interpretation of acoustic data is a time-consuming process that often requires a great amount of human supervision. This issue might be tackled by exploiting modern techniques for automatic audio signal analysis, which have recently achieved impressive performance thanks to the advances in deep learning research. In this paper we show that convolutional neural networks can indeed significantly outperform traditional automatic methods in a challenging detection task: identification of dolphin whistles from underwater audio recordings. The proposed system can detect signals even in the presence of ambient noise, at the same time consistently reducing the likelihood of producing false positives and false negatives. Our results further support the adoption of artificial intelligence technology to improve the automatic monitoring of marine ecosystems.

A Simple Approach to Estimate the Drag Coefficients of a Submerged Floater.

The calculation of the drag force is a fundamental requirement in the design of any submerged system intended for marine exploration. The calculation can be performed by analytic analysis, numerical modeling, or by a direct calculation performed in a designated testing facility. However, for complex structures and especially those with a non-rigid design, the analytic and numerical analyses are not sufficiently accurate, while the direct calculation is a costly operation. In this paper, we propose a simple approach for how to calculate the drag coefficient in-situ. Aimed specifically at the complex case of elastic objects whose modeling via Computer-Aided Design (CAD) is challenging, our approach evaluates the relation between the object's speed at steady-state and its mass to extract the drag coefficient in any desired direction, the hydro-static force, and, when relevant, also the thruster's force. We demonstrate our approach for the special case of a highly complex elastic-shaped floater that profiles the water column. The analysis of two such floaters in two different sea environments shows accurate evaluation results and supports our claim for robustness. In particular, the simplicity of the approach makes it appealing for any arbitrary shaped object.

Acoustic projectors make covert bioacoustic chirplet signals discoverable.

To disguise man-made communications as natural signals, underwater transceivers have the option to pre-record animal vocalizations, and play them back in a way that carries meaningful information for a trained receiver. This operation, known as biomimicking, has been used to perform covert communications and to emit broadband signals for localization, either by playing pre-recorded animal sounds back into the environment, or by designing artificial waveforms whose spectrum is close to that of bioacoustic sounds.However, organic sound-emitting body structures in animals have very different trans-characteristics with respect to electro-acoustic transducers used in underwater acoustic transceivers. In this paper, we observe the distortion induced by transmitting pre-recorded animal vocalization through a transducer's front-end, and argue that such distortion can be detected via appropriate entropy metrics. We test ten different metrics for this purpose, both via emulated transmission and in two field experiments. Our result indicate which signals and entropy metrics lead to the highest probability of detecting transducer-originated distortions, thus exposing ongoing covert communications. Our research emphasizes the limitations that man-made equipment incurs when reproducing bioacoustic sounds, and prompts for the choice of biomimicking signals that are possibly suboptimal for communications or localization, but help avoid exposing disguised transmissions.

Toward understanding the communication in sperm whales.

Machine learning has been advancing dramatically over the past decade. Most strides are human-based applications due to the availability of large-scale datasets; however, opportunities are ripe to apply this technology to more deeply understand non-human communication. We detail a scientific roadmap for advancing the understanding of communication of whales that can be built further upon as a template to decipher other forms of animal and non-human communication. Sperm whales, with their highly developed neuroanatomical features, cognitive abilities, social structures, and discrete click-based encoding make for an excellent model for advanced tools that can be applied to other animals in the future. We outline the key elements required for the collection and processing of massive datasets, detecting basic communication units and language-like higher-level structures, and validating models through interactive playback experiments. The technological capabilities developed by such an undertaking hold potential for cross-applications in broader communities investigating non-human communication and behavioral research.

A Graph Localization Approach for Underwater Sensor Networks to Assist a Diver in Distress.

In this paper, we focus on the problem of locating a scuba diver in distress using a sensor network. Without GPS reception, submerged divers in distress will transmit SOS messages using underwater acoustic communication. The study goal is to enable the quick and reliable location of a diver in distress by his fellow scuba divers. To this purpose, we propose a distributed scheme that relies on the propagation delay information of these acoustic SOS messages in the scuba divers' network to yield a range and bearing evaluation to the diver in distress by any neighboring diver. We formalize the task as a non-convex, multi-objective graph localization constraint optimization problem. The solution finds the best configuration of the nodes' graph under constraints in the form of upper and lower bounds derived from the inter-connections between the graph nodes/divers. Considering the need to rapidly propagate the SOS information, we flood the network with the SOS packet, while also using rateless coding to leverage information from colliding packets, and to utilize time instances when collisions occur for propagation delay evaluation. Numerical results show a localization accuracy on the order of a few meters, which contributes to quickly locating the diver in distress. Similar results were demonstrated in a controlled experiment in a water tank, and by playback data from a sea experiment for five network topologies.

Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets.

Accurate detection and tracking of moving targets in underwater environments pose significant challenges, because noise in acoustic measurements (e.g., SONAR) makes the signal highly stochastic. In continuous marine monitoring a further challenge is related to the computational complexity of the signal processing pipeline-due to energy constraints, in off-shore monitoring platforms algorithms should operate in real time with limited power consumption. In this paper, we present an innovative method that allows to accurately detect and track underwater moving targets from the reflections of an active acoustic emitter. Our system is based on a computationally- and energy-efficient pre-processing stage carried out using a deep convolutional denoising autoencoder (CDA), whose output is then fed to a probabilistic tracking method based on the Viterbi algorithm. The CDA is trained on a large database of more than 20,000 reflection patterns collected during 50 designated sea experiments. System performance is then evaluated on a controlled dataset, for which ground truth information is known, as well as on recordings collected during different sea experiments. Results show that, compared to the benchmark, our method achieves a favorable trade-off between detection and false alarm rate, as well as improved tracking accuracy.

Enhanced Fuzzy-based Local Information Algorithm for Sonar Image Segmentation.

The recent boost in undersea operations has led to the development of high-resolution sonar systems mounted on autonomous vehicles. These vehicles are used to scan the seafloor in search of different objects such as sunken ships, archaeological sites, and submerged mines. An important part of the detection operation is the segmentation of sonar images, where the object's highlight and shadow are distinguished from the seabed background. In this work, we focus on the automatic segmentation of sonar images. We present our enhanced fuzzybased with Kernel metric (EnFK) algorithm for the segmentation of sonar images which, in an attempt to improve segmentation accuracy, introduces two new fuzzy terms of local spatial and statistical information. Our algorithm includes a preliminary de-noising algorithm which, together with the original image, feeds into the segmentation procedure to avoid trapping to local minima and to improve convergence. The result is a segmentation procedure that specifically suits the intensity inhomogeneity and the complex seabed texture of sonar images. We tested our approach using simulated images, real sonar images, and sonar images that we created in two different sea experiments, using multibeam sonar and synthetic aperture sonar. The results show accurate segmentation performance that is far beyond the stateof-the-art results.

Bathymetry-aided underwater acoustic localization using a single passive receiver.

This paper considers the problem of estimating the trajectory of an autonomous underwater vehicle (AUV) via a single passive receiver, without any anchor nodes or receiving arrays, and with the only help of a sequence of known acoustic signals emitted by the AUV. This scenario is of interest in case multilateration-based alternatives would require the deployment of many receivers and imply exceedingly high costs, e.g., for the coverage of wide areas. The proposed method exploits the knowledge of environmental parameters such as the sound speed profile, bathymetry and bottom sediments in order to estimate the location of the AUV, taking advantage of the spatial dependency of channel impulse responses that arises from the diverse bathymetry around the receiver. This dependency is captured by comparing channel estimates against a database of channel responses, pre-computed through an acoustic propagation model. This yields multiple likely AUV locations, which are filtered via a path tracking method similar to the Viterbi algorithm, in order to estimate the trajectory of the AUV. Results obtained both from simulations and from a sea experiment show that the proposed method can estimate node locations and paths with a small error, especially considering the use of a single receiver.

Observability analysis of DVL/PS aided INS for a maneuvering AUV.

Recently, ocean exploration has increased considerably through the use of autonomous underwater vehicles (AUV). A key enabling technology is the precision of the AUV navigation capability. In this paper, we focus on understanding the limitation of the AUV navigation system. That is, what are the observable error-states for different maneuvering types of the AUV? Since analyzing the performance of an underwater navigation system is highly complex, to answer the above question, current approaches use simulations. This, of course, limits the conclusions to the emulated type of vehicle used and to the simulation setup. For this reason, we take a different approach and analyze the system observability for different types of vehicle dynamics by finding the set of observable and unobservable states. To that end, we apply the observability Gramian approach, previously used only for terrestrial applications. We demonstrate our analysis for an underwater inertial navigation system aided by a Doppler velocity logger or by a pressure sensor. The result is a first prediction of the performance of an AUV standing, rotating at a position and turning at a constant speed. Our conclusions of the observable and unobservable navigation error states for different dynamics are supported by extensive numerical simulation.