Improved Latin hypercube sampling initialization-based whale optimization algorithm for COVID-19 X-ray multi-threshold image segmentation.

Image segmentation techniques play a vital role in aiding COVID-19 diagnosis. Multi-threshold image segmentation methods are favored for their computational simplicity and operational efficiency. Existing threshold selection techniques in multi-threshold image segmentation, such as Kapur based on exhaustive enumeration, often hamper efficiency and accuracy. The whale optimization algorithm (WOA) has shown promise in addressing this challenge, but issues persist, including poor stability, low efficiency, and accuracy in COVID-19 threshold image segmentation. To tackle these issues, we introduce a Latin hypercube sampling initialization-based multi-strategy enhanced WOA (CAGWOA). It incorporates a COS sampling initialization strategy (COSI), an adaptive global search approach (GS), and an all-dimensional neighborhood mechanism (ADN). COSI leverages probability density functions created from Latin hypercube sampling, ensuring even solution space coverage to improve the stability of the segmentation model. GS widens the exploration scope to combat stagnation during iterations and improve segmentation efficiency. ADN refines convergence accuracy around optimal individuals to improve segmentation accuracy. CAGWOA's performance is validated through experiments on various benchmark function test sets. Furthermore, we apply CAGWOA alongside similar methods in a multi-threshold image segmentation model for comparative experiments on lung X-ray images of infected patients. The results demonstrate CAGWOA's superiority, including better image detail preservation, clear segmentation boundaries, and adaptability across different threshold levels.

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.

Universal wing- and fin-beat frequency scaling.

We derive an equation that applies for the wing-beat frequency of flying animals and to the fin-stroke frequency of diving animals like penguins and whales. The equation states that the wing/fin-beat frequency is proportional to the square root of the animal's mass divided by the wing area. Data for birds, insects, bats, and even a robotic bird-supplemented by data for whales and penguins that must swim to stay submerged-show that the constant of proportionality is to a good approximation the same across all species; thus the equation is universal. The wing/fin-beat frequency equation is derived by dimensional analysis, which is a standard method of reasoning in physics. We finally demonstrate that a mathematically even simpler expression without the animal mass does not apply.

Modeling individual growth reveals decreasing gray whale body length and correlations with ocean climate indices at multiple scales.

Changes in body size have been documented across taxa in response to human activities and climate change. Body size influences many aspects of an individual's physiology, behavior, and ecology, ultimately affecting life history performance and resilience to stressors. In this study, we developed an analytical approach to model individual growth patterns using aerial imagery collected via drones, which can be used to investigate shifts in body size in a population and the associated drivers. We applied the method to a large morphological dataset of gray whales (Eschrichtius robustus) using a distinct foraging ground along the NE Pacific coast, and found that the asymptotic length of these whales has declined since around the year 2000 at an average rate of 0.05-0.12 m/y. The decline has been stronger in females, which are estimated to be now comparable in size to males, minimizing sexual dimorphism. We show that the decline in asymptotic length is correlated with two oceanographic metrics acting as proxies of habitat quality at different scales: the mean Pacific Decadal Oscillation index, and the mean ratio between upwelling intensity in a season and the number of relaxation events. These results suggest that the decline in gray whale body size may represent a plastic response to changing environmental conditions. Decreasing body size could have cascading effects on the population's demography, ability to adjust to environmental changes, and ecological influence on the structure of their community. This finding adds to the mounting evidence that body size is shrinking in several marine populations in association with climate change and other anthropogenic stressors. Our modeling approach is broadly applicable across multiple systems where morphological data on megafauna are collected using drones.

Annual phenology and migration routes to breeding grounds in western-central North Pacific sei whales.

The sei whale (Balaenoptera borealis) is an important species among baleen whales in the North Pacific and plays a significant role in the ecosystem. Despite the importance of this species, information regarding its migration patterns and breeding locations remains limited. To enhance the understanding of the phenology of North Pacific sei whales, we deployed satellite-monitored tags on these whales in the western and central North Pacific from 2017 to 2023. We fitted 55 sei whale tracks to a state-space model to describe the whales' seasonal movements at feeding grounds and their migratory behavior. The whales typically leave their feeding grounds between November and December, with migration pathways extending from off Japan to the west of the Hawaiian Islands. These southward transits converge in the waters of the Marshall Islands and north of Micronesia between 20° N and 7° N, which appear to be breeding grounds. After a brief stay at these breeding grounds, the whales migrate northward from January to February, reaching their feeding grounds around 30°N by March. To the best of our knowledge, this is the first study to present the phenology of feeding and breeding seasons and the migration pattern of North Pacific sei whales.

Whale evolution: Ancient toothed relative of baleen whales breaches northward.

The mysticetes - baleen whales and their toothed ancestors - have a long evolutionary history that, despite many recent paleontological discoveries, remains highly debated. The description of a new mysticete from the latest Eocene of North America opens promising new research directions.

Accurate species classification of Arctic toothed whale echolocation clicks using one-third octave ratios.

Passive acoustic monitoring has been an effective tool to study cetaceans in remote regions of the Arctic. Here, we advance methods to acoustically identify the only two Arctic toothed whales, the beluga (Delphinapterus leucas) and narwhal (Monodon monoceros), using echolocation clicks. Long-term acoustic recordings collected from moorings in Northwest Greenland were analyzed. Beluga and narwhal echolocation signals were distinguishable using spectrograms where beluga clicks had most energy >30 kHz and narwhal clicks had a sharp lower frequency limit near 20 kHz. Changes in one-third octave levels (TOL) between two pairs of one-third octave bands were compared from over one million click spectra. Narwhal clicks had a steep increase between the 16 and 25 kHz TOL bands that was absent in beluga click spectra. Conversely, beluga clicks had a steep increase between the 25 and 40 kHz TOL bands that was absent in narwhal click spectra. Random Forest classification models built using the 16 to 25 kHz and 25 to 40 kHz TOL ratios accurately predicted the species identity of 100% of acoustic events. Our findings support the use of echolocation TOL ratios in future automated click classifiers for acoustic monitoring of Arctic toothed whales and potentially for other odontocete species.

Click detection rate variability of central North Pacific sperm whales from passive acoustic towed arrays.

Passive acoustic monitoring (PAM) is an optimal method for detecting and monitoring cetaceans as they frequently produce sound while underwater. Cue counting, counting acoustic cues of deep-diving cetaceans instead of animals, is an alternative method for density estimation, but requires an average cue production rate to convert cue density to animal density. Limited information about click rates exists for sperm whales in the central North Pacific Ocean. In the absence of acoustic tag data, we used towed hydrophone array data to calculate the first sperm whale click rates from this region and examined their variability based on click type, location, distance of whales from the array, and group size estimated by visual observers. Our findings show click type to be the most important variable, with groups that include codas yielding the highest click rates. We also found a positive relationship between group size and click detection rates that may be useful for acoustic predictions of group size in future studies. Echolocation clicks detected using PAM methods are often the only indicator of deep-diving cetacean presence. Understanding the factors affecting their click rates provides important information for acoustic density estimation.

Debris flow volume prediction model based on back propagation neural network optimized by improved whale optimization algorithm.

Debris flow is a sudden natural disaster in mountainous areas, which seriously threatens the lives and property of nearby residents. Therefore, it is necessary to predict the volume of debris flow accurately and reliably. However, the predictions of back propagation neural networks are unstable and inaccurate due to the limited dataset. In this study, the Cubic map optimizes the initial population position of the whale optimization algorithm. Meanwhile, the adaptive weight adjustment strategy optimizes the weight value in the shrink-wrapping mechanism of the whale optimization algorithm. Then, the improved whale optimization algorithm optimizes the final weights and thresholds in the back propagation neural network. Finally, to verify the performance of the final model, sixty debris flow gullies caused by earthquakes in Longmenshan area are selected as the research objects. Through correlation analysis, 4 main factors affecting the volume of debris flow are determined and inputted into the model for training and prediction. Four methods (support vector machine regression, XGBoost, back propagation neural network optimized by artificial bee colony algorithm, back propagation neural network optimized by grey wolf optimization algorithm) are used to compare the prediction performance and reliability. The results indicate that loose sediments from co-seismic landslides are the most important factor influencing the flow of debris flows in the earthquake area. The mean absolute percentage error, mean absolute error and R2 of the final model are 0.193, 29.197 × 104 m3 and 0.912, respectively. The final model is more accurate and stable when the dataset is insufficient and under complexity. This is attributed to the optimization of WOA by Cubic map and adaptive weight adjustment. In general, the model of this paper can provide reference for debris flow prevention and machine learning algorithms.

Geographical distribution of close kin in southern right whales on feeding grounds.

This study investigated the close kinship structure of southern right whales on feeding grounds during austral summer seasons. The study was based on biopsy samples of 171 individual whales, which were genotyped with 14 microsatellite DNA loci. Kinship was investigated by using the LOD (Log Odds) score, a relatedness index for a pair of genotypes. Based on a cut-off point of LODPO > 6, which was chosen to balance false positives and negatives, a total of 28 dyads were inferred. Among these, 25 were classified as parent-offspring pairs. Additional genetic (mitochondrial DNA haplotypes) and biological (estimated body length, sex) data were used to provide additional information on the inferred close kin pairs. The elapsed time between sampling varied from 0 (close kin detected in the same austral summer season) to 17 years. All the kin pairs occurred within the Antarctic Indo sector (85°-135°E) and no pair occurred between whales within and outside of this sector. Six pairs were between individuals in high (Antarctic) and lower latitudes. Results of the present analysis on kinship are consistent with the views that whales in the Indo sector of the Antarctic are related with the breeding ground in Southwest Australia, and that whales from this population can occupy different feeding grounds. The present study has the potential to contribute to the conservation of the southern right whales through the monitoring of important population parameters such as population sizes and growth rate, in addition to assist the interpretation of stock structure derived from standard population genetic analyses.

Three decades of nearshore surveys reveal long-term patterns in gray whale habitat use, distribution, and abundance in the Northern California Current.

The nearshore waters of the Northern California Current support an important seasonal foraging ground for Pacific Coast Feeding Group (PCFG) gray whales. We examine gray whale distribution, habitat use, and abundance over 31 years (1992-2022) using standardized nearshore (< 5 km from shore) surveys spanning a large swath of the PCFG foraging range. Specifically, we generated density surface models, which incorporate detection probability into generalized additive models to assess environmental correlates of gray whale distribution and predict abundance over time. We illustrate the importance of coastal upwelling dynamics, whereby increased upwelling only yields higher gray whale density if interspersed with relaxation events, likely because this combination optimizes influx and retention of nutrients to support recruitment and aggregation of gray whale prey. Several habitat features influence gray whale distribution, including substrate, shelf width, prominent capes, and river estuaries. However, the influence of these features differs between regions, revealing heterogeneity in habitat preferences throughout the PCFG foraging range. Predicted gray whale abundance fluctuated throughout our study period, but without clear directional trends, unlike previous abundance estimates based on mark-recapture models. This study highlights the value of long-term monitoring, shedding light on the impacts of variable environmental conditions on an iconic nearshore marine predator.

Exploring indirect effects of a classic trophic cascade between urchins and kelp on zooplankton and whales.

Kelp forest trophic cascades have been extensively researched, yet indirect effects to the zooplankton prey base and gray whales have not been explored. We investigate the correlative patterns of a trophic cascade between bull kelp and purple sea urchins on gray whales and zooplankton in Oregon, USA. Using generalized additive models (GAMs), we assess (1) temporal dynamics of the four species across 8 years, and (2) possible trophic paths from urchins to kelp, kelp as habitat to zooplankton, and kelp and zooplankton to gray whales. Temporal GAMs revealed an increase in urchin coverage, with simultaneous decline in kelp condition, zooplankton abundance and gray whale foraging time. Trophic path GAMs, which tested for correlations between species, demonstrated that urchins and kelp were negatively correlated, while kelp and zooplankton were positively correlated. Gray whales showed nuanced and site-specific correlations with zooplankton in one site, and positive correlations with kelp condition in both sites. The negative correlation between the kelp-urchin trophic cascade and zooplankton resulted in a reduced prey base for gray whales. This research provides a new perspective on the vital role kelp forests may play across multiple trophic levels and interspecies linkages.

Disentangling the influence of entanglement on recruitment in North Atlantic right whales.

North Atlantic right whales are Critically Endangered and declining, with entanglements in fishing gear a key contributor to their decline. Entanglement events can result in lethal and sub-lethal (i.e. increased energetic demands and reduced foraging ability) impacts, with the latter influencing critical life-history states, such as reproduction. Using a multi-event framework, we developed a Bayesian mark-recapture model to investigate the influence of entanglement severity on survival and recruitment for female right whales. We used information from 199 known-aged females sighted between 1977 and 2018, combined with known entanglements of varying severity that were classified as minor, moderate or severe. Severe entanglements resulted in an average decline in survival of 27% for experienced non-breeders, 9% for breeders and 26% for pre-breeding females compared with other entanglements and unentangled individuals. Surviving individuals with severe entanglements had low transitional probabilities to breeders, but surprisingly, individuals with minor entanglements had the lowest transitional probabilities, contrary to expectations underpinning current management actions. Management actions are needed to address the lethal and sub-lethal impacts of entanglements, regardless of severity classification.

Hybrid whale algorithm with evolutionary strategies and filtering for high-dimensional optimization: Application to microarray cancer data.

The standard whale algorithm is prone to suboptimal results and inefficiencies in high-dimensional search spaces. Therefore, examining the whale optimization algorithm components is critical. The computer-generated initial populations often exhibit an uneven distribution in the solution space, leading to low diversity. We propose a fusion of this algorithm with a discrete recombinant evolutionary strategy to enhance initialization diversity. We conduct simulation experiments and compare the proposed algorithm with the original WOA on thirteen benchmark test functions. Simulation experiments on unimodal or multimodal benchmarks verified the better performance of the proposed RESHWOA, such as accuracy, minimum mean, and low standard deviation rate. Furthermore, we performed two data reduction techniques, Bhattacharya distance and signal-to-noise ratio. Support Vector Machine (SVM) excels in dealing with high-dimensional datasets and numerical features. When users optimize the parameters, they can significantly improve the SVM's performance, even though it already works well with its default settings. We applied RESHWOA and WOA methods on six microarray cancer datasets to optimize the SVM parameters. The exhaustive examination and detailed results demonstrate that the new structure has addressed WOA's main shortcomings. We conclude that the proposed RESHWOA performed significantly better than the WOA.

A Quantitative Analysis of Microplastics in the Gastrointestinal Tracts of Odontocetes in the Southeast Region of the United States.

Microplastics (<5 mm in diameter) are ubiquitous in the oceanic environment, yet microplastic accumulation in marine mammals is vastly understudied. In recent years, efforts have been made to document microplastic profiles in odontocetes. The objective of the present study was to describe and quantify microplastics in the gastrointestinal (GI) tracts of deceased odontocetes that stranded in the southeastern United States. Our study included 24 bottlenose dolphins (Tursiops truncatus), two pygmy sperm whales (Kogia breviceps), one pantropical spotted dolphin (Stenella attenuata), one short-snouted spinner dolphin (Stenella clymene), one Risso's dolphin (Grampus griseus), and one dwarf sperm whale (Kogia sima) obtained from stranding networks in Texas, Alabama, Florida, and Puerto Rico. Contents found in the GI tracts, namely, the stomach and portions of the intestinal tract, were subjected to a laboratory procedure to isolate microplastics. The physical characteristics of microparticles were analyzed with a stereomicroscope, and microplastics were classified by polymer type via Fourier-transform infrared spectroscopy. There was an average of 47.6 ± 41.4 microparticles, ranging from 1 to 193 items per stomach. More specifically, there was an average of 5.6 ± 4.7 microplastics per stomach. The predominant morphologies, colors, and polymer types were fibers, white-colored items, and polyester, respectively. This research contributes to the current knowledge of microplastic exposure in top marine mammal predators and sets the stage for further exploration into the associated risks of microplastics in odontocetes within the United States and worldwide. Environ Toxicol Chem 2024;43:1260-1273. © 2024 SETAC.

The oldest mysticete in the Northern Hemisphere.

Extant baleen whales (Mysticeti) uniquely use keratinous baleen for filter-feeding and lack dentition, but the fossil record clearly shows that "toothed" baleen whales first appeared in the Late Eocene.1 Globally, only two Eocene mysticetes have been found, and both are from the Southern Hemisphere: Mystacodon selenensis from Peru, 36.4 mega-annum (Ma) ago1,2 and Llanocetus denticrenatus from Antarctica, 34.2 Ma ago.3,4 Based on a partial skull from the lower part of the Lincoln Creek Formation in Washington State, USA, we describe the Northern Hemisphere's geochronologically earliest mysticete, Fucaia humilis sp. nov. Geology, biostratigraphy, and magnetostratigraphy places Fucaia humilis sp. nov. in the latest Eocene (ca. 34.5 Ma ago, near the Eocene/Oligocene transition at 33.9 Ma ago), approximately coeval with the oldest record of fossil kelps, also in the northeastern Pacific.5 This observation leads to our hypothesis that the origin and development of a relatively stable, nutrient-rich kelp ecosystem5,6 in the latest Eocene may have fostered the radiation of small-sized toothed mysticetes (Family Aetiocetidae) in the North Pacific basin, a stark contrast to the larger Llanocetidae (whether Mystacodon belongs to llanocetids or another independent clade remains unresolved) with the latest Eocene onset of the Antarctic Circumpolar Current in the Southern Hemisphere.7,8,9 Our discovery suggests that disparate mechanisms and ecological scenarios may have nurtured contrasting early mysticete evolutionary histories in the Northern and Southern hemispheres.

A longitudinal study of endocrinology and foraging ecology of subadult gray whales prior to death based on baleen analysis.

Individual-level assessments of wild animal health, vital rates, and foraging ecology are critical for understanding population-wide impacts of exposure to stressors. Large whales face multiple stressors, including, but not limited to, ocean noise, pollution, and ship strikes. Because baleen is a continuously growing keratinized structure, serial extraction, and quantification of hormones and stable isotopes along the length of baleen provide a historical record of whale physiology and foraging ecology. Furthermore, baleen analysis enables the investigation of dead specimens, even decades later, allowing comparisons between historic and modern populations. Here, we examined baleen of five sub-adult gray whales and observed distinct patterns of oscillations in δ15N values along the length of their baleen plates which enabled estimation of baleen growth rates and differentiation of isotopic niche widths of the whales during wintering and summer foraging. In contrast, no regular patterns were apparent in δ13C values. Prolonged elevation of cortisol in four individuals before death indicates that chronic stress may have impacted their health and survival. Triiodothyronine (T3) increased over months in the whales with unknown causes of death, simultaneous with elevations in cortisol, but both hormones remained stable in the one case of acute death attributed to killer whale predation. This parallel elevation of cortisol and T3 challenges the classic understanding of their interaction and might relate to increased energetic demands during exposure to stressors. Reproductive hormone profiles in subadults did not show cyclical trends, suggesting they had not yet reached sexual maturity. This study highlights the potential of baleen analysis to retrospectively assess gray whales' physiological status, exposure to stressors, reproductive status, and foraging ecology in the months or years leading up to their death, which can be a useful tool for conservation diagnostics to mitigate unusual mortality events.

Gray whale (Eschrichtius robustus) post-mortem findings from December 2018 through 2021 during the Unusual Mortality Event in the Eastern North Pacific.

Beginning in December 2018, increased numbers of gray whale (Eschrichtius robustus) strandings were reported along the west coast of Mexico, the United States, and Canada, prompting declaration of a gray whale Unusual Mortality Event (UME) by the United States National Marine Fisheries Service. Although strandings declined in 2020 and 2021 from a peak in 2019, the UME is still ongoing as of fall 2023. Between 17 December 2018 and 31 December 2021, 503 animals stranded along the west coast of North America, with 226 strandings in Mexico, 71 in California, 12 in Oregon, 56 in Washington, 21 in British Columbia, and 117 in Alaska. These included 187 males, 167 females, and 149 whales of undetermined sex; and 193 adults, 194 subadults, 40 calves, 1 fetus, and 75 whales of undetermined age class. We report on 61 of the 503 carcasses (12%) that had external and internal gross necropsy and/or histopathology data: of these 61 whales, findings that contributed to death were identified in 33 (54%) whales. Sixteen of the 61 (26%) were severely emaciated. Gross lesions of blunt force trauma consistent with vessel strike were identified in 11 of the 61 animals (18%), only two of which were emaciated. Two whales (3%) were entangled at time of death, and one died from entrapment. Signs of killer whale (Orcinus orca) interaction were documented in 19 of the 61 animals; five were deemed from recent interactions and three (5%) likely contributed to mortality. A specific cause of death could not be identified in 28 of 61 whales (46%). Additionally, logistical challenges and the advanced state of decomposition of most examined carcasses precluded detection of potential infectious or toxic causes of morbidity or mortality. Up to 2016, the eastern North Pacific population of gray whale population had generally been increasing since the cessation of historic whaling and a prior UME in 1999-2000. However, recent abundance and calf production estimates have declined, a trend that overlaps the current UME. The relative contributions of carrying capacity, environmental change, prey shifts, and infectious, toxic, and other processes to the increased gray whale mortalities have not yet been resolved. Nevertheless, the marked temporal increase in strandings, including findings of malnutrition in some of the whales, along with low calf production, likely represent consequences of complex and dynamic ecological interactions in the ocean impacting the population.

Effects of whaling and krill fishing on the whale-krill predation dynamics: bifurcations in a harvested predator-prey model with Holling type I functional response.

In the Antarctic, the whale population had been reduced dramatically due to the unregulated whaling. It was expected that Antarctic krill, the main prey of whales, would grow significantly as a consequence and exploratory krill fishing was practiced in some areas. However, it was found that there has been a substantial decline in abundance of krill since the end of whaling, which is the phenomenon of krill paradox. In this paper, to study the krill-whale interaction we revisit a harvested predator-prey model with Holling I functional response. We find that the model admits at most two positive equilibria. When the two positive equilibria are located in the region { ( N , P ) | 0 ≤ N < 2 N c , P ≥ 0 } , the model exhibits degenerate Bogdanov-Takens bifurcation with codimension up to 3 and Hopf bifurcation with codimension up to 2 by rigorous bifurcation analysis. When the two positive equilibria are located in the region { ( N , P ) | N > 2 N c , P ≥ 0 } , the model has no complex bifurcation phenomenon. When there is one positive equilibrium on each side of N = 2 N c , the model undergoes Hopf bifurcation with codimension up to 2. Moreover, numerical simulation reveals that the model not only can exhibit the krill paradox phenomenon but also has three limit cycles, with the outmost one crosses the line N = 2 N c under some specific parameter conditions.