Search

The residency pattern and site fidelity of Risso’s dolphin Grampus griseus were studied using sightings data collected during standardized vessel-based surveys carried out from 2013 to 2018 in the Gulf of Taranto (Northern Ionian Sea, Central-Eastern Mediterranean Sea). The photo-identification of 91 individuals of G. griseus and the occurrence of re-sighted dolphins up to 8 times provide the evidence that this mid-sized odontocetes persistently occurred in the study area. The presence of transient individuals, visitors, and seasonal residents in the Gulf of Taranto, along with the 29 multi-year resident Risso’s dolphins observed from 2 to 4 times on different years, indicated some degree of inter-annual variability in its temporal use of the area. Moreover, the occurrence of newborns and calves through the study period suggests the possibility to consider the Gulf of Taranto as both nursery and feeding area for females caring for their offspring. The importance of the Gulf of Taranto as critical habitat for the Risso’s dolphin as well as the common bottlenose dolphin and the striped dolphin candidates this area as potential Important Marine Mammal Area, in which enforce specific conservation measures are aimed to mitigate the anthropogenic pressure on different cetacean species according to ACCOBAMS and the MMPATF indication.

Photo-identification is one of the best practices to estimate the abundance of cetaceans and, as such, it can help to obtain the biological information necessary to decision-making and actions to preserve the marine environment and its biodiversity. The Risso's dolphin is one of the least-known cetacean species on a global scale, and the distinctive scars on its dorsal fin proved to be extremely useful to photo-identify single individuals. The main novelty of this paper is the development of a new method based on deep learning, called Neural Network Pool (NNPool), and specifically devoted to the photo-identification of Risso's dolphins. This new method also includes the unique function of recognizing unknown vs known dolphins in large datasets with no interaction by the user. Moreover, the new version of DolFin catalogue, collecting Risso's dolphins data and photos acquired between 2013-2018 in the Northern Ionian Sea (Central-eastern Mediterranean Sea), is presented and used here to carry out the experiments. Results have been validated using a further data set, containing new images of Risso's dolphins from the Northern Ionian Sea and the Azores, acquired in 2019. The performance of the NNPool appears satisfying and increases proportionally to the number of images available, thus highlighting the importance of building large-scale data set for the application at hand.

The increasing recognition of the importance of biodiversity and genetic variation has led to more frequent calls for their preservation. Moreover, novel molecular and advanced genomic tools can be effectively employed to incorporate genetic variability and genomic information into conservation planning and sustainable programs, aimed at species conservation and slowing the erosion of biological diversity. The particular geomorphological and hydrographic features of Gulf of Taranto (Northern Ionian Sea, Central Mediterranean Sea), supports the occurrence of different cetacean species among that the striped dolphin is the more frequent and abundant species. The aim of this study was to investigate the genetic variability of this species in the study area, deepening the possibility to identify a subpopulation in the basin.

The presence of cetaceans in a sea basin indicates the quality of that ecosystem. To support the conservation of these species, it is essential to deepen our knowledge of their habitual life. Given data about sighting of cetaceans in the Ionian Sea occurring between 2009 and 2019, the aim of this work is to study a set of morphological and meteorological features in order to understand if they can help in estimating cetacean abundance and build predictive models fit for purpose.

In the last decade, Unmanned Aerial Vehicles (UAVs) were applied in monitoring studies addressing to marine and terrestrial wildlife for their multiple advantages. Due to their operational flexibility and low cost, UAVs have been applied in studies aimed at studying behavior, estimating group size and abundance of species as well as at measuring the individuals through photogrammetry methods. In this work, numerical estimates of group size of Risso’s dolphin sighted in the Gulf of Taranto from UAVs video-analysis were compared from those recorded by MMO on board of a research vessel. Data were collected from April 2018 to September 2020 for a total of 109:58 minutes of recording. Aerial shots together traditional survey methods allowed a more thorough analysis of the number of individuals observed, offering a better estimates overview, with the possibility of viewing videos several times and taking screenshots. Using UAVs could provide more accurate estimates on Risso’s dolphin population. In conclusion, given the efficiency such systems found in this work, the use of UAV could be instrumental in broadening perspectives on marine mammal studies.

Dolphin and whale watching has become worldwide a popular ecotourism activity. However, it can itself be a source of disturbance/stress to animals. Therefore, it is necessary quantify its impacts on cetacean species and possible behavioural responses to interaction between vessels and cetaceans. This study provided first preliminary information of the possible impact of a research vessel on behavioural activity of the Risso’s dolphin recorded in the Gulf of Taranto from April 2019 to September 2020. Information about positive, neutral and responses of Risso’s dolphins to research vessel was collected according focal-group protocol with instantaneous scan-sampling during 60 sightings, for a total of 300 sampling sessions of 3-min. Travelling resulted the most observed activity state (62%) followed by resting (24%), socializing (7%) and feeding (7%). A neutral response were observed in 81.3% of cases, a negative one in 17% of cases and positive in 1.7% of cases. For each activity state recorded, the most observed behavioural response was neutral, followed by negative reaction. Results provided in this study seems to indicate that Risso’s dolphins displayed a neutral response in the most of sightings. However, further studies are necessary to better understand if the presence of whale watching vessels may induce changes, and to what degree, in the essential behaviour of this and other species occurring in the area.

The aim of this work was to investigate the possibility to apply photo-identification method on the striped dolphin. As non-invasive and inexpensive methods, the photo-identification could improve our knowledge about abundance, temporal distribution, movements, social organization of striped dolphin population in the Gulf of Taranto. In this work, two different criteria were tested to identify individuals: the first based on the dorsal fin, the second based on the pigmentation pattern variability and long-term markers on the body.Multiple notches and multiple nicks resulted the most useful markers on dorsal fin for the photo-identification of striped dolphin, followed by the presence of one large notch, one small nick and deformities. These markers allowed the identification of 150 striped dolphins of which 40 were re-sighted from 2 to 7 times. The photo-identification based on the pigmentation pattern resulted in 47 individuals of which only one was resighted during the study period.

The photo-identification of individuals within an animal population is an important objective for the description of the environment itself, for studies relating to the distribution of species and their habitat-use as well as their conservation. The manual analysis of the photos collected by experts is generally very expensive in terms of time and requires specific knowledge. In the field of cetology, photo-identification based on the dorsal fin of individuals is widespread. The software here presented aims to effectively isolate the outline of the dorsal fin, so that it can be used in applications that exploit nicks, notches and other irregularities for the identification and classification process. It implements a series of innovative and specific operations that make the tool applicable to very large datasets with good performances and it has been successfully used for the extraction of the fin outline on dolphin images acquired in the Gulf of Taranto (Northern Ionian Sea - Central Mediterranean Sea).

This study aims to develop a CNN-based system for dolphins’ photo-identification. Starting from 1,960 photos of dolphin fins each one labeled with the related dolphin name, we have developed a predictive model able to classify unknown fins. In particular, the system is composed by two different CNNs. The first one automatically learns how to create a mask to extract the foreground, i.e. the fin, from each original image. Then, these masks are used as starting point for the GrabCut algorithm, which creates more precise binary masks. Finally, the obtained masked images are given as input to the second CNN, which aims to recognize an unknown dolphin’s fin, providing a probability for each known individual.

The Mediterranean subpopulation of short-beaked common dolphin Delphinus delphis is ranked as endangered on the IUCN (International Union for Conservation of Nature) Red List because it has sharply declined during the last decades, resulting in sparse and decreasing populations. Monitoring the conservation status of this endangered dolphin species is particularly relevant to fulfil targets under the range of several international agreements. Moreover, estimating the abundance of D. delphis is essential to verify the effectiveness of conservation action to maintain safe population levels in the Mediterranean Sea and to suggest appropriate modifications to limit potential threats. In this regard, a monitoring program of the short-beaked common dolphin in Samos Island (Greece) was carried out from 2016 to 2019, adopting a random line transect sampling method. The overall density and abundance estimates of D. delphis, obtained by applying conventional distance sampling (CDS) on sighting data, were 0.15 individuals/km2 (CV = 13.27%, 95% CI = 0.11&ndash, 0.19 individuals/km2) and 51 individuals (CV = 13.27%, 95% CI = 40-66 individuals), respectively. Although, a longer time series of sighting data should be collected and a larger area should be investigated to better understand the population trend of D. delphis and its residency pattern, the results contribute to setting up a baseline reference for future assessment of its population in the Eastern Aegean Sea.

Cetacean stranding events are an important source of information and biological samples, providing data on species occurrence, distribution and population dynamics as well as on mortality rate induced by human activities or natural causes. This is even truer for species such as Z. cavirostris, whose elusive behavior has made its field observation difficult in many Mediterranean areas. Although the occurrence of single or serial strandings of this species and the rise in survey effort have increased the knowledge on its presence, there are still gaps in some Mediterranean areas, especially in the Gulf of Taranto (North-western Ionian Sea, Italy), where a critical habitat suitable for different cetacean species has been identified. Despite no sightings of Z. cavirostris having been recorded so far, ACCOBAMS designates the Gulf of Taranto as an Area of Special Concern for Beaked Whales (ASC-BW) on the basis of atypical mass strandings of 12 individuals which occurred in the Ionian Sea in 2011. Moreover, the conservation status of the Z. cavirostris has recently passed from Data Deficient to Vulnerable, according the IUCN criteria adopted for the Mediterranean Sea, thus showing the urgent need for basic information on its bio-ecological features, suitable habitat and threats at local or wider scale. This study is the first attempt at application in the Mediterranean Sea of a Lagrangian prediction model simulating the carcass drift trajectories to investigate the at-site sea origin of an individual of Z. cavirostris stranded in the Gulf of Taranto. Moreover, a necropsy was carried out to detect the possible cause of death and the results of bacteriological, biomolecular and toxicological analysis are provided. Finally, a collection of osteological data as well as the process of turning and displaying the skeleton in a museum are detailed, highlighting the importance of these exhibits from a scientific and educational point of view.

This study provides the first estimates of density and abundance of the striped dolphin Stenella coeruleoalba and common bottlenose dolphin Tursiops truncatus in the Gulf of Taranto (Northern Ionian Sea, Central Mediterranean Sea) and identifies the predictive variables mainly influencing their occurrence and concentration in the study area. Conventional Distance Sampling (CDS) and the Delta approach on Random Forest (DaRF) methods have been applied to sightings data collected between 2009 and 2016 during standardized vessel-based surveys, providing similar outcomes. The mean value of density over the entire study area was 0.72 ± 0.26 specimens/km2 for the striped dolphin and 0.47 ± 0.09 specimens/km2 for the common bottlenose dolphin. The abundance estimated by DaRF in the Gulf of Taranto was 10080 ± 3584 specimens of S. coeruleoalba and 6580 ± 1270 specimens of T. truncatus, respectively. Eight predictive variables were selected, considering both the local physiographic features and human activities existing in the investigated area. The explanatory variables depth, distance from the coast, distance from industrial areas and distance from areas exploited by fishery seem to play a key role in influencing the spatial distribution of both species, whereas the geomorphological variables proved to be the most significant factors shaping the concentration of both dolphins. The establishment of a Specially Protected Area of Mediterranean Importance (SPAMI) according the SPA/BD Protocol in the Gulf of Taranto is indicated as an effective management tool for the conservation of both dolphin populations in the Central-eastern Mediterranean Sea.

Algorithms based on a clever exploitation of artificial intelligence (AI) techniques are the key for modern multidisciplinary applications that are being developed in the last decades. AI approaches’ ability of extracting relevant information from data is essential to perform comprehensive studies in new multidisciplinary topics such as ecological informatics. For example, improving knowledge on cetaceans’ distribution patterns enables the acquisition of a strategic expertise for developing tools aimed to the preservation of the marine environment. In this paper we present an innovative approach, based on Random Forest and RUSBoost, aimed to define predictive models for presence/absence and abundance estimation of two classes of cetaceans: the striped dolphin Stenella coeruleoalba and the common bottlenose dolphin Tursiops truncatus. Sightings data from 2009 to 2017 have been collected and enriched by geo-morphological and meteorological data in order to build a comprehensive dataset of real observations used to train and validate the proposed algorithms. Results in terms of classification and regression accuracy demonstrate the feasibility of the proposed approach and suggest the application of such artificial intelligence based techniques to larger datasets, with the aim of enabling large scale studies as well as improving knowledge on data deficient species.

Heterogeneity in geomorphological and hydrographical conditions throughout the Mediterranean Sea could be the driving factors behind the significant differences between putative sub-populations, although the existence of a large panmictic population of striped dolphin Stenella coeruleoalba (Meyen 1833) in this marine region could not be excluded. However, understanding the ecological implications of such genetic differentiation is difficult, as inferences about gene flow are usually made on evolutionary time scales and not along the ecological time frame over which most management and conservation practices are applied. In fact, as stated by the IUCN Red List, in the case of species assessed as vulnerable, the degree of genetic exchange between populations within a biogeographic region and its ecological implications represent a fascinating challenge that should be very deeply explored. This is even more significant in the Gulf of Taranto (Northern Ionian Sea, Central-eastern Mediterranean Sea), where the geomorphological and hydrographic characteristics support the hypothesis of a separated striped dolphin population genetically diverging from its original Mediterranean counterpart. To assess this hypothesis, a genetic analysis was carried out on DNA fragments of the mitochondrial cyt b gene to explore the evolutionary origin of S. coeruleoalba in the investigated area and its genetic diversity in comparison with available sequences from other Mediterranean and Atlantic populations. Results were discussed indicating ecological implications and suggesting conservation objectives. Moreover, a delphinid systematic was also suggested.

Photo-identification is a commonly used non-invasive technique that has been profitably employed in biological studies throughout the years. It starts from the assumption that a single individual can be recognized in multiple photos captured at different times by exploiting its unique representative and visible physical qualities such as marks, notches or any other definite feature. Hence, photo-identification is performed to infer knowledge about wild species' spatial and temporal distributions as well as population dynamics, thus providing valuable information especially when the species being investigated is ranked as data deficient. Furthermore, the technological improvements of the last decades and the large availability of devices with powerful computing capabilities are driving the research towards a common goal of enriching bio-ecological studies with innovative computer science approaches. In this scenario, computer vision plays a fundamental role, as it can successfully assist researchers in the analysis of large amounts of data. The aim of this paper is, in fact, to effectively provide a computer vision approach for the photo-identification of the Risso's dolphin, exploiting specific visual cues with a feature-based approach relying on SIFT and SURF feature detectors. The experiments have been conducted on image data acquired in the Gulf of Taranto from 2013 to 2017, conducting a comparative analysis of the performance of both SIFT and SURF, as well as a comparison with the state-of-the-art software DARWIN, and they proved the effectiveness of the proposed approach and suggested its application would be suitable to large scale studies. In conclusion, this paper shows an innovative computer vision application for the identification of unknown Risso's dolphin individuals that relies on a feature-based automated approach. The results suggest that the proposed approach can efficiently assist researchers during the photo-identification task of large amounts of data collected in such a challenging domain.

Although the EU Marine Strategy Framework Directive (MSFD) is largely based on the establishment of environmental targets and associated proxies to achieve Good Environmental Status (GES), a full suite of ecological indicators for all the ecosystem components is not currently available for ongoing assessment and regular update of GES targets. This is because effective indicators and management actions aimed at preserving/rebuilding marine biodiversity should be found from the knowledge of the spatial distribution of target species and extension of critical habitats as well as their overlapping with human activities, pressure and impacts. In this regard, the spatial distributions of the striped dolphin Stenella coeruleoalba and the common bottlenose dolphin Tursiops truncatus in the Gulf of Taranto (Northern Ionian Sea, Central-eastern Mediterranean Sea) were investigated by means of a generalized additive model (GAM) and a Random Forest (RF) based on sighting data collected during standardized vessel-based surveys carried out from 2009 to 2015. Eight predictive variables were considered, taking into account both the local physiographic features and human activities existing in the investigated area, suggesting an innovative approach to habitat modeling. In particular, the explanatory variables depth, distance from industrial areas and distance from the coast proved to significantly influence the distribution of both dolphin species. In addition, the distribution of S. coeruleoalba and T. truncatus were also significantly shaped by the distance from the navy exercise areas and the fishing areas, respectively. On the contrary, the slope and the distance from the main commercial routes never provided any significant influence. The reliability of GAM and RF models in predicting the spatial distribution of both dolphins was tested by applying the Youden Index method to the ROC curves. The RF model allowed the projection of the expected presence/absence pattern of S. coeruleoalba and T. truncatus to produce the preference habitat versus non habitat map. In particular, the RF model predicted that the striped dolphin is widely present in the central and deeper part of the Gulf of Taranto. In contrast, the common bottlenose dolphin seems to be mainly distributed along the coasts in both the eastern and western sector of the basin. A clear overlapping of the preference habitats estimated for S. coeruleoalba and T. truncatus is shown north of Punta Alice and in front of Policoro as well as offshore from Ugento in the eastern and western parts of the investigated area, respectively. Finally, the critical habitats of S. coeruleoalba and T. truncatus are the outcome of both the influence of environmental conditions and anthropogenic pressures presently occurring in the Gulf of Taranto, basically indicating the need for conservation measures, especially considering that the area is expected to be considered for hydrocarbon prospecting. These results contribute to setting up a baseline reference for future assessment of environmental marine disturbances using cetaceans, which are considered a key group in the MSFD, as an ecological indicator.

Photo-identification is a widely used non-invasive technique in biological studies for understanding if a specimen has been seen multiple times only relying on specific unique visual characteristics. This information is essential to infer knowledge about the spatial distribution, site fidelity, abundance or habitat use of a species. Today there is a large demand for algorithms that can help domain experts in the analysis of large image datasets. For this reason, it is straightforward that the problem of identify and crop the relevant portion of an image is not negligible in any photo-identification pipeline. This paper approaches the problem of automatically cropping cetaceans images with a hybrid technique based on domain analysis and deep learning. Domain knowledge is applied for proposing relevant regions with the aim of highlighting the dorsal fins, then a binary classification of fin vs. no-fin is performed by a convolutional neural network. Results obtained on real images demonstrate the feasibility of the proposed approach in the automated process of large datasets of Risso&rsquo, s dolphins photos, enabling its use on more complex large scale studies. Moreover, the results of this study suggest to extend this methodology to biological investigations of different species.

The Risso’s dolphin is a widely distributed species, found in deep temperate and tropical waters. Estimates of its abundance are available in a few regions, details of its distribution are lacking, and its status in the Mediterranean Sea is ranked as Data Deficient by the IUCN Red List. In this paper, a synergy between bio-ecological analysis and innovative strategies has been applied to construct a digital platform, DolFin. It contains a collection of sighting data and geo-referred photos of Grampus griseus, acquired from 2013 to 2016 in the Gulf of Taranto (Northern Ionian Sea, North-eastern Central Mediterranean Sea), and the first automated tool for Smart Photo Identification of the Risso’s dolphin (SPIR). This approach provides the capability to collect and analyse significant amounts of data acquired over wide areas and extended periods of time. This effort establishes the baseline for future large-scale studies, essential to providing further information on the distribution of G. griseus. Our data and analysis results corroborate the hypothesis of a resident Risso’s dolphin population in the Gulf of Taranto, showing site fidelity in a relatively restricted area characterized by a steep slope to around 800 m in depth, north of the Taranto Valley canyon system.

Photo-identification (photo-ID) studies are strategic to fill the gap of knowledge of data deficient species such as Risso’s dolphin. Unfortunately, the photo-ID process is very time consuming and strongly depends on the user-ability. Some photo-ID algorithms are available, which can, automatically or semi-automatically, find the closest match between the dolphin in the query and a catalogue of previously sighted dolphins. However the limitation of these algorithms is that in any case they will return a prevision of the dolphin identity, in other words these can not identify the individuals never sighted before, i.e. unknown dolphins. Hence the automation of the photo-ID process through the use of innovative algorithms is still needed. In this paper the opportunity of employing machine learning strategies for the automated photo-ID of Risso’s dolphin is investigated. In particular the performances of RUSBoost algorithm result to be very good in identifying the unknown dolphins, even if in general these depend on the available data for training the model. Experimental results highlight the great potential of machine learning in the automation of photo-ID process, as well as focus on the need of collecting more and more data in order to perform a more effective data analysis.

The photo-identification is largely employed technique used by biologists in numerous studies, based on a noninvasive approach and aimed to the identification of an individual starting from multiple images. The procedure is based on the exploitation of discriminating features and on the fundamental hypothesis that a single individual can be uniquely recognized if depicted on an image. Currently, this technique is effectively used to investigate on spatial/temporal wild species distributions or, generally speaking, to improve knowledge on data-deficient species. In this paper we focus on an innovative computer vision approach, aimed to the automatic photo-identification of Risso’s dolphins, based on Speeded Up Robust Features (SURF) computed on the dorsal fin to recognize an unknown individual among a set of models with a best matching approach. Experiments on real data acquired in the Gulf of Taranto as well as a comparison with the state-of-the-art DARWIN software confirm the profitability of the proposed approach in terms of accuracy improvements and reduced computational time.

Dolphins emit a large variety of acoustic signals on which they rely for navigation, communication and searching for food. Nevertheless, each species uses quantitative and qualitative species-specific characteristics for tonal and pulsed signals, and the different behavioral contexts may affect the use of these signals. The main aim of this work is to evaluate if the emission rate of acoustic signals can be used as a cue to recognize species, and as an intra-specific feature for recognizing behavioral contexts. We collected acoustic and behavioral data during 27 sightings of bottlenose and striped dolphins in the Gulf of Taranto, (Northern Ionian Sea, Central-Eastern Mediterranean Sea). 396.31minutes of recordings were considered for analysis. The emission rate, calculated as the number of vocalizations/minutes of recording per animals within the group, was compared among species and behaviors. A higher emission rate was recorded for bottlenose dolphins clicks during traveling compared to striped dolphins involved in the same behavior, and for striped dolphins whistles during socializing compared to other behaviors of the same species. However, we must consider that smaller groups were analyzed for bottlenose dolphins. Results suggest that dolphins share click echoes in larger groups and increase communication signals during social activities. Our preliminary results can help inform management and conservation actions, in the framework of EU regulations, in this high impacted area.

The relationship between a species and its habitat is complex but it is essential to study the distribution and habitat use of a protected species in order to identify regions where human activities and disturbances are likely to impact its population. The Marine Strategy Framework Directive informs that studies focusing on spatial and temporal species distribution and ecosystem variations (including links between habitats and species of marine mammals) are recommended to achieve Good Environmental Status (GES) of the EU’s marine water by 2020. However, the current level of information on the spatial-temporal distribution of marine mammals is often lacking. The striped dolphin is the most abundant cetacean of the Mediterranean Sea; nevertheless its Mediterranean population is listed as "vulnerable" by IUCN experts. In order to investigate the spatial distribution of striped dolphin within the Adriatic-Ionian Region, a cooperative project among different research groups was set up and a multi-source data approach was employed. Presence data collected during monitoring activity carried out from 2008 to 2018 were analysed by means of Maxent. Main topographic variables as bathymetry, slope and distance from coastline were considered and five distribution models were performed to highlight suitable areas for striped dolphin within the entire study area. Models are presented and discussed. The results of this study show that to investigate the distribution of a species at a regional scale it is necessary to monitor area with different environmental characteristics. In this regards, cooperative regional projects represent an opportunity for pooling together data that taken singularly would not necessarily reflect the distribution of species at a larger scale, but that analysed together would allow to acquire information on suitable habitats at a regional level.