A machine learning pipeline for classification of cetacean echolocation clicks in large underwater acoustic datasets

Machine learning with taxonomic family delimitation aids in the classification of ephemeral beaked whale events in passive acoustic monitoring

Passive acoustic monitoring is an essential tool for studying beaked whale populations. This approach can monitor elusive and pelagic species, but the volume of data it generates has overwhelmed researchers' ability to quantify species occurrence for effective conservation and management efforts. Automation of data processing is crucial, and machine learning algorithms can rapidly identify species using their sounds. Beaked whale acoustic events, often infrequent and ephemeral, can be missed when co-occurring with signals of more abundant, and acoustically active species that dominate acoustic recordings. Prior efforts on large-scale classification of beaked whale signals with deep neural networks (DNNs) have approached the class as one of many classes, including other odontocete species and anthropogenic signals. That approach tends to miss ephemeral events in favor of more common and dominant classes. Here, we describe a DNN method for improved classification of beaked whale species using an extensive dataset from the western North Atlantic. We demonstrate that by training a DNN to focus on the taxonomic family of beaked whales, ephemeral events were correctly and efficiently identified to species, even with few echolocation clicks. By retrieving ephemeral events, this method can support improved estimation of beaked whale occurrence in regions of high odontocete acoustic activity.

Topological learning in multiclass data sets

We specialize techniques from topological data analysis to the problem of characterizing the topological complexity (as defined in the body of the paper) of a multiclass data set. As a by-product, a topological classifier is defined that uses an open subcovering of the data set. This subcovering can be used to construct a simplicial complex whose topological features (e.g., Betti numbers) provide information about the classification problem. We use these topological constructs to study the impact of topological complexity on learning in feedforward deep neural networks (DNNs). We hypothesize that topological complexity is negatively correlated with the ability of a fully connected feedforward deep neural network to learn to classify data correctly. We evaluate our topological classification algorithm on multiple constructed and open-source data sets. We also validate our hypothesis regarding the relationship between topological complexity and learning in DNN's on multiple data sets.

Ecological inferences about marine mammals from passive acoustic data

Monitoring on the basis of sound recordings, or passive acoustic monitoring, can complement or serve as an alternative to real-time visual or aural monitoring of marine mammals and other animals by human observers. Passive acoustic data can support the estimation of common, individual-level ecological metrics, such as presence, detection-weighted occupancy, abundance and density, population viability and structure, and behaviour. Passive acoustic data also can support estimation of some community-level metrics, such as species richness and composition. The feasibility of estimation and certainty of estimates is highly context dependent, and understanding the factors that affect the reliability of measurements is useful for those considering whether to use passive acoustic data. Here, we review basic concepts and methods of passive acoustic sampling in marine systems that often are applicable to marine mammal research and conservation. Our ultimate aim is to facilitate collaboration among ecologists, bioacousticians, and data analysts. Ecological applications of passive acoustics require one to make decisions about sampling design, which in turn requires consideration of sound propagation, sampling of signals, and data storage. One also must make decisions about signal detection and classification and evaluation of the performance of algorithms for these tasks. Investment in the research and development of systems that automate detection and classification, including machine learning, are increasing. Passive acoustic monitoring is more reliable for detection of species presence than for estimation of other species-level metrics. Use of passive acoustic monitoring to distinguish among individual animals remains difficult. However, information about detection probability, vocalisation or cue rate, and relations between vocalisations and the number and behaviour of animals increases the feasibility of estimating abundance or density. Most sensor deployments are fixed in space or are sporadic, making temporal turnover in species composition more tractable to estimate than spatial turnover. Collaborations between acousticians and ecologists are most likely to be successful and rewarding when all partners critically examine and share a fundamental understanding of the target variables, sampling process, and analytical methods.

SoundScape learning: An automatic method for separating fish chorus in marine soundscapes

Marine soundscapes provide the opportunity to non-invasively learn about, monitor, and conserve ecosystems. Some fishes produce sound in chorus, often in association with mating, and there is much to learn about fish choruses and the species producing them. Manually analyzing years of acoustic data is increasingly unfeasible, and is especially challenging with fish chorus, as multiple fish choruses can co-occur in time and frequency and can overlap with vessel noise and other transient sounds. This study proposes an unsupervised automated method, called SoundScape Learning (SSL), to separate fish chorus from soundscape using an integrated technique that makes use of randomized robust principal component analysis (RRPCA), unsupervised clustering, and a neural network. SSL was applied to 14 recording locations off southern and central California and was able to detect a single fish chorus of interest in 5.3 yrs of acoustically diverse soundscapes. Through application of SSL, the chorus of interest was found to be nocturnal, increased in intensity at sunset and sunrise, and was seasonally present from late Spring to late Fall. Further application of SSL will improve understanding of fish behavior, essential habitat, species distribution, and potential human and climate change impacts, and thus allow for protection of vulnerable fish species.

Odontocete spatial patterns and temporal drivers of detection at sites in the Hawaiian islands

Successful conservation and management of marine top predators rely on detailed documentation of spatiotemporal behavior. For cetacean species, this information is key to defining stocks, habitat use, and mitigating harmful interactions. Research focused on this goal is employing methodologies such as visual observations, tag data, and passive acoustic monitoring (PAM) data. However, many studies are temporally limited or focus on only one or few species. In this study, we make use of an existing long-term (2009-2019), labeled PAM data set to examine spatiotemporal patterning of at least 10 odontocete (toothed whale) species in the Hawaiian Islands using compositional analyses and modeling techniques. Species composition differs among considered sites, and this difference is robust to seasonal movement patterns. Temporally, hour of day was the most significant predictor of detection across species and sites, followed by season, though patterns differed among species. We describe long-term trends in species detection at one site and note that they are markedly similar for many species. These trends may be related to long-term, underlying oceanographic cycles that will be the focus of future study. We demonstrate the variability of temporal patterns even at relatively close sites, which may imply that wide-ranging models of species presence are missing key fine-scale movement patterns. Documented seasonal differences in detection also highlights the importance of considering season in survey design both regionally and elsewhere. We emphasize the utility of long-term, continuous monitoring in highlighting temporal patterns that may relate to underlying climatic states and help us predict responses to climate change. We conclude that long-term PAM records are a valuable resource for documenting spatiotemporal patterns and can contribute many insights into the lives of top predators, even in highly studied regions such as the Hawaiian Islands.

Silbido profundo: An open source package for the use of deep learning to detect odontocete whistles

This work presents an open-source matlab software package for exploiting recent advances in extracting tonal signals from large acoustic data sets. A whistle extraction algorithm published by Li, Liu, Palmer, Fleishman, Gillespie, Nosal, Shiu, Klinck, Cholewiak, Helble, and Roch [(2020). Proceedings of the International Joint Conference on Neural Networks, July 19-24, Glasgow, Scotland, p. 10] is incorporated into silbido, an established software package for extraction of cetacean tonal calls. The precision and recall of the new system were over 96% and nearly 80%, respectively, when applied to a whistle extraction task on a challenging two-species subset of a conference-benchmark data set. A second data set was examined to assess whether the algorithm generalized to data that were collected across different recording devices and locations. These data included 487 h of weakly labeled, towed array data collected in the Pacific Ocean on two National Oceanographic and Atmospheric Administration (NOAA) cruises. Labels for these data consisted of regions of toothed whale presence for at least 15 species that were based on visual and acoustic observations and not limited to whistles. Although the lack of per whistle-level annotations prevented measurement of precision and recall, there was strong concurrence of automatic detections and the NOAA annotations, suggesting that the algorithm generalizes well to new data.

Machine Learning Approach for Predictive Maintenance of the Electrical Submersible Pumps (ESPs)

Electrical submersible pumps (ESPs) are considered the second-most widely used artificial lift method in the petroleum industry. As with any pumping artificial lift method, ESPs exhibit failures. The maintenance of ESPs expends a lot of resources, and manpower and is usually triggered and accompanied by the reactive process monitoring of multivariate sensor data. This paper presents a methodology to deploy the principal component analysis and extreme gradient boosting trees (XGBoosting) in predictive maintenance in order to analyze real-time sensor data to predict failures in ESPs. The system contributes to an efficiency increase by reducing the time required to dismantle the pumping system, inspect it, and perform failure analysis. This objective is achieved by applying the principal component analysis as an unsupervised technique; then, its output is pipelined with an XGBoosting model for further prediction of the system status. In comparison to traditional approaches that have been utilized for the diagnosis of ESPs, the proposed model is able to identify deeper functional relationships and longer-term trends inferred from historical data. The novel workflow with the predictive model can provide signals 7 days before the actual failure event, with an F1-score more than 0.71 on the test set. Increasing production efficiencies through the proactive identification of failure events and the avoidance of deferment losses can be accomplished by means of the real-time alarming system presented in this work.

Identification of western North Atlantic odontocete echolocation click types using machine learning and spatiotemporal correlates

A combination of machine learning and expert analyst review was used to detect odontocete echolocation clicks, identify dominant click types, and classify clicks in 32 years of acoustic data collected at 11 autonomous monitoring sites in the western North Atlantic between 2016 and 2019. Previously-described click types for eight known odontocete species or genera were identified in this data set: Blainville's beaked whales (Mesoplodon densirostris), Cuvier's beaked whales (Ziphius cavirostris), Gervais' beaked whales (Mesoplodon europaeus), Sowerby's beaked whales (Mesoplodon bidens), and True's beaked whales (Mesoplodon mirus), Kogia spp., Risso's dolphin (Grampus griseus), and sperm whales (Physeter macrocephalus). Six novel delphinid echolocation click types were identified and named according to their median peak frequencies. Consideration of the spatiotemporal distribution of these unidentified click types, and comparison to historical sighting data, enabled assignment of the probable species identity to three of the six types, and group identity to a fourth type. UD36, UD26, and UD28 were attributed to Risso's dolphin (G. griseus), short-finned pilot whale (G. macrorhynchus), and short-beaked common dolphin (D. delphis), respectively, based on similar regional distributions and seasonal presence patterns. UD19 was attributed to one or more species in the subfamily Globicephalinae based on spectral content and signal timing. UD47 and UD38 represent distinct types for which no clear spatiotemporal match was apparent. This approach leveraged the power of big acoustic and big visual data to add to the catalog of known species-specific acoustic signals and yield new inferences about odontocete spatiotemporal distribution patterns. The tools and call types described here can be used for efficient analysis of other existing and future passive acoustic data sets from this region.

Discriminating and classifying odontocete echolocation clicks in the Hawaiian Islands using machine learning methods

Passive acoustic monitoring (PAM) has proven a powerful tool for the study of marine mammals, allowing for documentation of biologically relevant factors such as movement patterns or animal behaviors while remaining largely non-invasive and cost effective. From 2008-2019, a set of PAM recordings covering the frequency band of most toothed whale (odontocete) echolocation clicks were collected at sites off the islands of Hawai'i, Kaua'i, and Pearl and Hermes Reef. However, due to the size of this dataset and the complexity of species-level acoustic classification, multi-year, multi-species analyses had not yet been completed. This study shows how a machine learning toolkit can effectively mitigate this problem by detecting and classifying echolocation clicks using a combination of unsupervised clustering methods and human-mediated analyses. Using these methods, it was possible to distill ten unique echolocation click 'types' attributable to regional odontocetes at the genus or species level. In one case, auxiliary sightings and recordings were used to attribute a new click type to the rough-toothed dolphin, Steno bredanensis. Types defined by clustering were then used as input classes in a neural-network based classifier, which was trained, tested, and evaluated on 5-minute binned data segments. Network precision was variable, with lower precision occurring most notably for false killer whales, Pseudorca crassidens, across all sites (35-76%). However, accuracy and recall were high (>96% and >75%, respectively) in all cases except for one type of short-finned pilot whale, Globicephala macrorhynchus, call class at Kaua'i and Pearl and Hermes Reef (recall >66%). These results emphasize the utility of machine learning in analysis of large PAM datasets. The classifier and timeseries developed here will facilitate further analyses of spatiotemporal patterns of included toothed whales. Broader application of these methods may improve the efficiency of global multi-species PAM data processing for echolocation clicks, which is needed as these datasets continue to grow.

Caller ID for Risso's and Pacific White-sided dolphins

Tracking species with expanding ranges is crucial to conservation efforts and some typically temperate marine species are spreading northward into the Arctic Ocean. Risso's (Gg) and Pacific white-sided (Lo) dolphins have been documented spreading poleward. Further, they make very similar sounds, so it is difficult for both human analysts and classification algorithms to tell them apart. Using automatic detectors and classifiers on large acoustic datasets would improve the efficiency of monitoring these species. variational mode decomposition (VMD) provides both an easier visualization tool for human analysts and exhibited robustness to background noise while extracting features in pulsed signals with very similar spectral properties. The goal of this work was to develop a new visualization tool using VMD and a statistics-based classification algorithm to differentiate similar pulsed signals. The proposed VMD method achieved 81% accuracy, even when using audio files with low SNR that did not have concurrent visual survey data. While many dolphins whistle, pulsed signals are one of the more useful vocalizations to use in detection and classification because of their species-specific acoustic features. Automating the VMD method and expanding it to other dolphin species that have very similar pulsed signals would complement current detection and classification methods and lead to a more complete understanding of ecosystem dynamics under a changing climate.

Performance metrics for marine mammal signal detection and classification

Automatic algorithms for the detection and classification of sound are essential to the analysis of acoustic datasets with long duration. Metrics are needed to assess the performance characteristics of these algorithms. Four metrics for performance evaluation are discussed here: receiver-operating-characteristic (ROC) curves, detection-error-trade-off (DET) curves, precision-recall (PR) curves, and cost curves. These metrics were applied to the generalized power law detector for blue whale D calls [Helble, Ierley, D'Spain, Roch, and Hildebrand (2012). J. Acoust. Soc. Am. 131(4), 2682-2699] and the click-clustering neural-net algorithm for Cuvier's beaked whale echolocation click detection [Frasier, Roch, Soldevilla, Wiggins, Garrison, and Hildebrand (2017). PLoS Comp. Biol. 13(12), e1005823] using data prepared for the 2015 Detection, Classification, Localization and Density Estimation Workshop. Detection class imbalance, particularly the situation of rare occurrence, is common for long-term passive acoustic monitoring datasets and is a factor in the performance of ROC and DET curves with regard to the impact of false positive detections. PR curves overcome this shortcoming when calculated for individual detections and do not rely on the reporting of true negatives. Cost curves provide additional insight on the effective operating range for the detector based on the a priori probability of occurrence. Use of more than a single metric is helpful in understanding the performance of a detection algorithm.