AI-enhanced real-time cattle identification system through tracking across various environments.

Video-based monitoring is essential nowadays in cattle farm management systems for automated evaluation of cow health, encompassing body condition scores, lameness detection, calving events, and other factors. In order to efficiently monitor the well-being of each individual animal, it is vital to automatically identify them in real time. Although there are various techniques available for cattle identification, a significant number of them depend on radio frequency or visible ear tags, which are prone to being lost or damaged. This can result in financial difficulties for farmers. Therefore, this paper presents a novel method for tracking and identifying the cattle with an RGB image-based camera. As a first step, to detect the cattle in the video, we employ the YOLOv8 (You Only Look Once) model. The sample data contains the raw video that was recorded with the cameras that were installed at above from the designated lane used by cattle after the milk production process and above from the rotating milking parlor. As a second step, the detected cattle are continuously tracked and assigned unique local IDs. The tracked images of each individual cattle are then stored in individual folders according to their respective IDs, facilitating the identification process. The images of each folder will be the features which are extracted using a feature extractor called VGG (Visual Geometry Group). After feature extraction task, as a final step, the SVM (Support Vector Machine) identifier for cattle identification will be used to get the identified ID of the cattle. The final ID of a cattle is determined based on the maximum identified output ID from the tracked images of that particular animal. The outcomes of this paper will act as proof of the concept for the use of combining VGG features with SVM is an effective and promising approach for an automatic cattle identification system.

Handling and Tagging Techniques for Implanting Juvenile American Shad with a New Acoustic Microtransmitter.

The use of telemetry techniques to better understand the behavior and survival of juvenile American shad (Alosa sapidissima), as they migrate through hydropower systems, has been challenging because shad are widely known to be particularly sensitive to handling. The goal of this study was to develop a tagging protocol using a new, acoustic micro transmitter that minimizes the detrimental effects of the tagging process and maximizes post-tagging survival of juvenile American shad. Limiting out-of-water handling and the use of brackish saltwater (7.5 parts per thousand) before and after tagging improved survival for shad tagged using a simple pectoral implantation method. This protocol provides a detailed, step-by-step procedure for tagging juvenile shad with acoustic transmitters. Fish tagged using this procedure and held in the laboratory for 60 days had an 81.5% survival rate, compared to 70% for their untagged counterparts. The successful tagging and handling practices developed in this study could be applied to field telemetry studies of juvenile shad and other sensitive species.

Integrating computer vision algorithms and RFID system for identification and tracking of group-housed animals: an example with pigs.

Precision livestock farming aims to individually and automatically monitor animal activity to ensure their health, well-being, and productivity. Computer vision has emerged as a promising tool for this purpose. However, accurately tracking individuals using imaging remains challenging, especially in group housing where animals may have similar appearances. Close interaction or crowding among animals can lead to the loss or swapping of animal IDs, compromising tracking accuracy. To address this challenge, we implemented a framework combining a tracking-by-detection method with a radio frequency identification (RFID) system. We tested this approach using twelve pigs in a single pen as an illustrative example. Three of the pigs had distinctive natural coat markings, enabling their visual identification within the group. The remaining pigs either shared similar coat color patterns or were entirely white, making them visually indistinguishable from each other. We employed the latest version of the You Only Look Once (YOLOv8) and BoT-SORT algorithms for detection and tracking, respectively. YOLOv8 was fine-tuned with a dataset of 3,600 images to detect and classify different pig classes, achieving a mean average precision of all the classes of 99%. The fine-tuned YOLOv8 model and the tracker BoT-SORT were then applied to a 166.7-min video comprising 100,018 frames. Results showed that pigs with distinguishable coat color markings could be tracked 91% of the time on average. For pigs with similar coat color, the RFID system was used to identify individual animals when they entered the feeding station, and this RFID identification was linked to the image trajectory of each pig, both backward and forward. The two pigs with similar markings could be tracked for an average of 48.6 min, while the seven white pigs could be tracked for an average of 59.1 min. In all cases, the tracking time assigned to each pig matched the ground truth 90% of the time or more. Thus, our proposed framework enabled reliable tracking of group-housed pigs for extended periods, offering a promising alternative to the independent use of image or RFID approaches alone. This approach represents a significant step forward in combining multiple devices for animal identification, tracking, and traceability, particularly when homogeneous animals are kept in groups.

In precision livestock farming, monitoring animal activity is crucial to ensure their health, well-being, and productivity. While digital cameras and computer vision algorithms offer a promising solution for this task, tracking individual animals of similar appearance when housed in groups can be challenging. Close interaction among animals can lead to a loss of individual identity, which affects tracking accuracy. To overcome this problem, we developed a framework that combines camera images with radio frequency identification (RFID) ear tags. This methodology was applied to a pen housing 12 pigs, with an RFID reader located inside the feeder. Among the pigs, three had unique coat markings, enabling them to be tracked most of the time without losing their identity (87% of the time). The remaining pigs could not be visually distinguished from each other, so information from the RFID system was used to recover lost IDs every time pigs entered the feeder. The framework achieves 97% accuracy in tracking, offering a reliable solution for monitoring group-housed pigs.

Development of underground detection system using a metal detector and aluminum tag for, Copris ochus (Coleoptera: Scarabaeidae).

Tracking of soil-dwelling insects poses greater challenges compared to aboveground-dwelling animals in terrestrial systems. A metal detector system consisting of a commercially available detector and aluminum tags was developed for detecting dung beetle, Copris ochus Motschulsky (Coleoptera: Scarabaeidae). First, detection efficacy of the system was evaluated by varying volumes of aluminum tags attached on a plastic model of the insect and also by varying angles. Then, detection efficacy was evaluated by varying depths of aluminum-tagged models under soil in 2 vegetation types. Finally, the effects of tag attachment on C. ochus adults were assessed for survivorship, burrowing depth, and horizontal movement. Generally, an increase in tag volume resulted in greater detection distance in semi-field conditions. Maximum detection distance of aluminum tag increased up to 17 cm below soil surface as the tag size (0.5 × 1.0 cm [width × length]) and thickness (16 layers) were maximized, resulting in a tag weight of 31.4 mg, comprising ca. 9% of average weight of C. ochus adult. Furthermore, the detection efficacy did not vary among angles except for 90°. In the field, metal detectors successfully detected 5 aluminum-tagged models in 20 × 10 m (W × L) arena within 10 min with detection rates ≥85% for up to depth of 10 cm and 45%-60% at depth of 20 cm. Finally, aluminum tagging did not significantly affect survivorship and behaviors of C. ochus. Our study indicates the potential of metal detector system for tracking C. ochus under soil.

Pinpointing pigs: performance and challenges of an ultra-wideband real-time location system for tracking growing-finishing pigs under practical conditions.

Real-Time Location Systems (RTLSs) are promising precision livestock farming tools and have been employed in behavioural studies across various farm animal species. However, their application in research with fattening pigs is so far unexplored. The implementation of these systems has great potential to gain insight into pigs' spatial behaviour such as the use of functional areas and pigs' proximity to each other as indicators for social relationships. The aim of this study was therefore to validate the accuracy, precision, and data quality of the commercial Noldus Information Technology BV TrackLab system. We conducted different measurement sets: first, we performed static measurements in 12 pens at four different locations in each pen at three heights each using a single ultra-wideband tag (UWB). We recorded unfiltered x- and y-coordinates at 1 Hz. We repeated these measurements with six tags aligned in a 2 × 3 grid with varied spacing to test interference between the tags. We also tested dynamic performance by moving the tags along the centre line of the pens. Finally, we measured the data quality with 55 growing pigs in six pens, including the identification of location 'jumps' from the inside to the outside of the pen. Each pen housed ten animals fitted with a UWB tag attached to their farm ear tag. We collected data for 10 days and analysed seven 24-h periods of raw and filtered data. The mean accuracy of the RTLS measurements was 0.53 m (precision: 0.14 m) for single and 0.46 m (precision: 0.07 m) for grouped tags. Accuracy improved with increasing measurement height for single tags but less clearly for grouped tags (P [height single] = 0.01; P [height grouped] = 0.22). When tags were fitted to animals, 63.3% of the filtered data was lost and 21.8% of the filtered location estimates were outside the pens. Altogether, the TrackLab system was capable of fairly accurate and precise assignment of the functional areas where individual animals were located, but was insufficient for the analysis of social relationships. Furthermore, the frequent occurrence of gaps in signal transmission and the overall high data loss rates presented significant limitations. Additionally, the challenging hardware requirements for attaching sensors to the animals underline the need for further technological advances in RTLS for the application with growing-finishing pigs.

Effects of handling and surgical implant on juvenile wild trout: Physiological and behavioral impact.

Fish involved in telemetry studies are usually handled, anaesthetized, and subjected to internal tag implantation, all of which have the potential to disrupt the fish's physiology, migratory patterns, food-seeking behavior, growth, and survival. As fish tagging is a widespread standard method in aquaculture, it is crucial to gain a better understanding of the short- and long-term effects on various aspects of fish welfare. The experimental outcomes of each phase of the surgical process and how it affects the fish's ability to recover during the post-tagging period, particularly in small salmonids, are poorly understood. Thus, it is essential to measure the extent of these adverse effects to precisely extrapolate differences in surgical intervention for tagged fish compared to their unmanipulated counterparts. In our study, we explored the post-tagging impacts on wild-captured brown trout (Salmo trutta) (1+) juveniles. We examined the time effect on fish recovery after each phase of the surgical procedure, which included anaesthetized fish, followed by surgery with/without internal tagging, within the first 2 and 25 h post-surgery. Common blood parameters (glucose levels and haematocrit) and endpoints related to swimming behavior, including fish movement, direction, and social distancing aspects, were studied. The findings of the study indicated no significant changes in glucose and haematocrit levels over the observational period. Fish subjected to anesthesia and tagging procedures exhibited a significant decrease in swimming activity, recovering to baseline levels 1 h after anesthesia and 24 h after surgical (tagging) procedures in recirculating aquaculture systems. Tagged fish showed less social proximity than non-tagged fish in the first 2 h post-surgery. A significant effect size was observed between nonsurgical (anesthesia) and surgical (non-tagged/tagged) groups, highlighting a more pronounced impact associated with surgical tag interventions. Our data indicate that the magnitude of behavioral response was significantly influenced by tag weight (~1.4% body/tag weight ratio in water) among manipulated fish groups. Consequently, our study reveals that wild-captured S. trutta juveniles, tagged with commercially available low-weight acoustic tags (V6, 69 kHz), experienced negative effects on swimming performance. In surgical studies, acknowledging potential influences is crucial for accurately inferring fish physiological and behavioral status. Emphasizing fish recovery potential in both short- and long-term periods is essential for quantifying tagging effects. Future research should prioritize exploring alternative tagging technologies and refining methodologies, with a particular focus on assessing telemetry's impact on socioeconomically relevant small salmonids.

Health Effects of Patagial Wing Tags in Red Kites (Milvus milvus) in the UK.

Patagial wing tags are commonly used for identification of Red Kites (Milvus milvus) for postrelease monitoring, as they are easy to apply, affordable, permanent, and are apparently safe. The Red Kite was successfully reintroduced in the UK in the second half of the 20th century and postrelease health surveillance has been achieved through radio and satellite tracking, monitoring nest sites, and pathologic investigation of Red Kites found dead. This study reports on pathologic findings associated with the use of patagial wing tags in three of 142 (2.1%) wing-tagged Red Kites examined postmortem since the beginning of the reintroduction project in 1989. In these three Red Kites the presence of the patagial wing tags was associated with inflammatory lesions. Further surveys of the potential short- and longer-term negative effects of patagial wing tags on Red Kites and other birds are advocated; the future use of patagial wing tags in raptors should be carefully monitored.

Estimating migration timing and abundance in partial migratory systems by integrating continuous antenna detections with physical captures.

Many populations migrate between two different habitats (e.g. wintering/foraging to breeding area, mainstem-tributary, river-lake, river-ocean, river-side channel) as part of their life history. Detection technologies, such as passive integrated transponder (PIT) antennas or sonic receivers, can be placed at boundaries between habitats (e.g. near the confluence of rivers) to detect migratory movements of marked animals. Often, these detection systems have high detection probabilities and detect many individuals but are limited in their ability to make inferences about abundance because only marked individuals can be detected. Here, we introduce a mark-recapture modelling approach that uses detections from a double-array PIT antenna system to imply movement directionality from arrays and estimate migration timing. Additionally, when combined with physical captures, the model can be used to estimate abundances for both migratory and non-migratory groups and help quantify partial migration. We first test our approach using simulation, and results indicate our approach displayed negligible bias for total abundance (less than ±1%) and slight biases for state-specific abundance estimates (±1%-6%). We fit our model to array detections and physical captures of three native fishes (humpback chub [Gila cypha], flannelmouth sucker [Catostomus latipinnis] and bluehead sucker [Catostomus discobolus]) in the Little Colorado River (LCR) in Grand Canyon, AZ, a system that exhibits partial migration (i.e. includes residents and migrants). Abundance estimates from our model confirm that, for all three species, migratory individuals are much more numerous than residents. There was little difference in movement timing between 2021 (a year without preceding winter/spring floods) and 2022 (a year with a small flood occurring in early April). In both years, flannelmouth sucker arrived in mid-March whereas humpback chub and bluehead sucker arrivals occurred early- to mid-April. With humpback chub and flannelmouth sucker, movement timing was influenced by body size so that large individuals were more likely to arrive early compared to smaller individuals. With more years of data, this model framework could be used to evaluate ecological questions pertaining to flow cues and movement timing or intensity, relative trends in migrants versus residents and ecological drivers of skipped spawning.

Individual identification of endangered amphibians using deep learning and smartphone images: case study of the Japanese giant salamander (Andrias japonicus).

Information obtained via individual identification is invaluable for ecology and conservation. Physical tags, such as PIT tags and GPS, have been used for individual identification; however, these methods could impact on animal behavior and survival rates, and the tags may become lost. Although non-invasive methods that do not affect the target species (such as manual photoidentification) are available, these techniques utilize stripes and spots that are unique to the individual, which requires training, and applying them to large datasets is challenging. Many studies that have applied deep learning for identification have focused on species-level identification, but few have addressed individual-level identification. In this study, we developed an image-based identification method based on deep learning that uses the head spot pattern of the Japanese giant salamander (Andrias japonicus), an endemic and endangered species in Japan. We trained and evaluated a dataset collected over two days from 11 individuals in captivity, which included 7075 images taken by a smartphone camera. Individuals were photographed three times a day at approximately 11:00 (morning), 15:00 (afternoon), and 18:00 (evening). As a result, individual identification by our method, which used the EfficientNetV2 achieved 99.86% accuracy, kappa coefficient of 0.99, and an F1 score of 0.99. Performance was lower for the evening  model than for the morning and afternoon models, which were trained and evaluated using photographs taken at the corresponding time of the day. The proposed method does not require direct contact with the target species, and the effect on the animals is minimal; moreover, individual-level information can be obtained under natural conditions. In the future, smartphone images can be applied to citizen science surveys and individual-level big data collection, which is difficult using current methods.

Effects of sensor ear tags with twin pin fixing system on health and well-being of cattle.

INTRODUCTION: A sensor ear tag (SET) containing Global Positioning System (GPS), accelerometer, Radio-Frequency Identification (RFID), and Bluetooth technologies was tested for wearing comfort and compliance with animal welfare requirements in cattle in a free stall barn and on summer pasture in Switzerland. The SET was equipped with a long-lasting battery via solar panel and used a «twin pin¼ fixing system. Right ears of 12 newborns and 26 adolescent animals were tagged with the SET. While left ears were tagged simultaneously with official ear tags in newborns, the adolescent animals already carried the official ear tags. The newborns stayed in a free stall barn during the entire experiment, while adolescent animals were housed in a free stall barn and on pasture during summer. All animals developed crusts beginning on day 7 after tagging with the SET. Pain reactions were observed occasionally in the first two weeks. Ear growth in newborns during 11 months of observation did not differ between ears with SET and official ear tags. Cortisol concentration in saliva of newborns decreased in the first week after tagging which is physiological for this age group. In older animals cortisol concentrations in saliva were not affected. We registered 19 incidences in 11 animals with the SET, that required veterinary or staff intervention. Two animals lost the SET with ear injury. Scars due to tag migration were observed in ears of all newborns after the 9th month of observation. In conclusion, SET with a weight of 32 g that need a twin pin fixation in cows do not seem to induce systemic or local inflammations more frequently compared to official ear tags; however, the higher risk of accidental injuries and migration in ear cartilage would not meet Swiss welfare standards and the attachment to the ear needs to be improved for general use.

INTRODUCTION: Une marque auriculaire à capteur (SET) contenant les technologies Global Positioning System (GPS), accéléromètre, identification par radiofréquence (RFID) et Bluetooth a été testée en termes de confort et de conformité aux exigences de bien-être animal chez des bovins dans une étable à stabulation libre et sur des pâturages d'estivage en Suisse. Le SET était équipé d'une batterie longue durée via un panneau solaire et utilisait un système de fixation «twin pin¼. Les oreilles droites de 12 veaux et de 26 génisses ont été équipées avec le SET. Les oreilles gauches ont été marquées en même temps avec les marques officielles chez les nouveau-nés alors que les génisses portaient déjà ces marques officielles. Les nouveau-nés ont été détenu dans une étable à stabulation libre, avec accès à une aire de sortie et aux paturages voisins pendant toute la durée de l'expérience tandis que les génisses ont été logés dans une étable à stabulation libre et en pâturage pendant l'été. Tous les animaux ont développé des croûtes à partir du 7e jour après le marquage avec le SET. Des réactions douloureuses ont occasionnellement été observées au cours des deux premières semaines. La croissance des oreilles des nouveau-nés au cours des 11 mois d'observation n'a pas différé entre les oreilles marquées par le SET et les oreilles marquées de manière standard. La concentration de cortisol dans la salive des nouveau-nés a diminué au cours de la première semaine successive au marquage, ce qui est physiologique pour ce groupe d'âge. Chez les animaux plus âgés, les concentrations de cortisol dans la salive n'ont pas été affectées. Nous avons enregistré 19 incidents chez 11 animaux avec le SET, qui ont nécessité l'intervention d'un vétérinaire ou d'un membre du personnel. Deux animaux ont perdu le SET avec blessure à l'oreille. Des cicatrices dues à la migration des marques ont été observées sur les oreilles de tous les nouveau-nés après le 9e mois d'observation. En conclusion, les SET d'un poids de 32 g qui nécessitent une fixation par deux tiges chez les bovins ne semblent pas induire d'inflammations systémiques ou locales plus fréquemment que les marques auriculaires officielles. Cependant le risque plus élevé de blessures accidentelles et de migration dans le cartilage de l'oreille ne correspondrait pas aux normes suisses en matière de bien-être et la fixation à l'oreille doit être améliorée pour une utilisation généralisée.

Biologging and Biotelemetry: Tools for Understanding the Lives and Environments of Marine Animals.

Addressing important questions in animal ecology, physiology, and environmental science often requires in situ information from wild animals. This difficulty is being overcome by biologging and biotelemetry, or the use of miniaturized animal-borne sensors. Although early studies recorded only simple parameters of animal movement, advanced devices and analytical methods can now provide rich information on individual and group behavior, internal states, and the surrounding environment of free-ranging animals, especially those in marine systems. We summarize the history of technologies used to track marine animals. We then identify seven major research categories of marine biologging and biotelemetry and explain significant achievements, as well as future opportunities. Big data approaches via international collaborations will be key to tackling global environmental issues (e.g., climate change impacts), and curiosity about the secret lives of marine animals will also remain a major driver of biologging and biotelemetry studies.

External morphology and biometry of newborn agouti (Dasyprocta prymnolopha, Wagler 1831) / Morfologia externa e biometria de neonates de cutias (Dasyprocta prymnolopha, Wagler 1831)

Morphological features are essential to assess neonates' viability. In order to characterize the morphology and biometry of newborn agouti, 36 animals born at 103 days of gestation under human care in Teresina-PI, Brazil were evaluated. After birth, the newborns were weighed on digital precision scales, measured with a flexible tape measure and their external morphology was assessed. The animals observed had coat color trait of adults, open eyes, hairs in the nasal region and four incisor teeth. The forelimbs had developed four digits and the hind limbs three digits, with white edged claws and a short hairless tail. The following were observed: weight of 144.58 ± 33.39g and lengths: crown-rump 14.73 ± 1.82cm, total 19.88 ± 1.52cm, head to tail 16.95 ± 1.55cm, head 7.33 ± 0.59cm, thoracic girth 11.78 ± 1.36cm, abdominal girth 10.73 ± 1.21cm, tail length 1.18 ± 0.25cm, eye diameter 1.27 ± 0.27cm and ear length 0.21 ± 0.35cm. The agoutis presented morphological maturity at birth with external morphology very similar to that of the adult animals. Most of the births in this species are the double type and newborns that weigh more than 90g have better chances of survival in captivity.

As características morfológicas são essenciais para avaliar a viabilidade dos neonatos. Para caracterizar a morfologia e biometria de cutias recém-nascidas, foram avaliados 36 animais nascidos aos 103 dias de gestação sob cuidados em Teresina-PI, Brasil. Após o nascimento, os recém-nascidos foram pesados em balança digital de precisão, medidos com fita métrica flexível e avaliada sua morfologia externa. Os animais observados apresentavam traço de pelagem de adultos, olhos abertos, pelos na região nasal e quatro dentes incisivos. Os membros anteriores desenvolveram quatro dedos e os membros posteriores três, com garras brancas afiadas e uma cauda curta e sem pêlos. Foram observados: peso de 144,58 ± 33,39g e comprimentos: garupa 14,73 ± 1,82cm, total 19,88 ± 1,52cm, cabeça a cauda 16,95 ± 1,55cm, cabeça 7,33 ± 0,59cm, perímetro torácico 11,78 ± 1,36cm, abdominal perímetro 10,73 ± 1,21 cm, comprimento da cauda 1,18 ± 0,25 cm, diâmetro do olho 1,27 ± 0,27 cm e comprimento da orelha 0,21 ± 0,35 cm. As cutias apresentaram maturidade morfológica ao nascimento com morfologia externa muito semelhante à dos animais adultos. A maioria dos nascimentos nesta espécie são do tipo duplo e recém-nascidos que pesam mais de 90g têm melhores chances de sobrevivência sob cuidados humanos.

Survival, growth and tag retention of juvenile European eel (Anguilla anguilla L.) with implanted 12 mm passive integrated transponder tags and acoustic tags.

To evaluate the efficiency of tagging juvenile European eels with implanted 12 mm passive integrated transponder (PIT) tags or Eel/Lamprey acoustic transmitters (ELATs), the authors studied tag retention, survival and growth of eels (7-25 g). Experimental eels were obtained from an eel farm, tagged and then released in a series of shallow dug-out ponds with a surface area of c. 200 m2 . Tagged and control eels were distributed evenly, with 50 tagged and 50 control eels in each of four ponds, giving a total of 200 tagged and 200 control eels mixed. After 76 days, the ponds were drained, and eels were sampled and measured. A total of 344 eels (86%) were recaptured, indicating high survival. Tag retention was 99% as only one of the recaptured PIT-tagged eels had lost the tag and none of the ELAT tagged. The results demonstrated that tagging juvenile eels >16 cm with these small tags is indeed feasible. The growth of tagged and control fish was differentiated but generally low in length and negative in mass but did not differ between the three groups.

Wound lesions caused by ear tagging in unweaned calves: assessing the prevalence of wound lesions and identifying risk factors.

Identification of cattle by ear tagging is legally required to ensure traceability. However, studies indicate that ear tagging causes pain-associated physiological and behavioural responses. The wound healing process and prevalence of wound lesions in calves remain mostly unknown. Therefore, this study sought to estimate the prevalence of wound lesions and identify associated risk factors by assessing ear tagging management in unweaned dairy calves. We conducted one field study with single visits to estimate the prevalence of wound lesions and associated risk factors (Study 1, 42 farms, 802 calves) and one follow-up study with repeated visits to assess farmers' view on ear tag management, the relationship between calf health and wound healing, and the development of wound lesions over time (Study 2, five farms, 42 calves). Study 1 comprised a short interview with the farmer (four questions regarding ear tagging). Ear tag position (on or between ridges) and wound lesions were evaluated using a three-level scoring system (1 = no blood, scab, or pus discharge; 2 = incrustation or scab and slight blood or pus discharge; and 3 = heavy purulent discharge, tissue deformation, or both). In Study 2, farmers were interviewed about ear tagging (30 questions), and 10 calves from each farm were assessed on the day of ear tagging and 1, 3, and 6 weeks after tag insertion. Calf health, ear tag position, and wound characteristics were assessed during all visits. Both studies were analysed descriptively, and odds ratios (ORs) for wound lesions in Study 1 were calculated using logistic regression. Of the ears assessed in Study 1, 31.1% showed clinical signs classified as category 2. Score 3 was less common and was found for 6.7% of all ears. Although the highest incidence of wound lesions was found in calves aged 2-4 weeks, wound lesions were also found in calves aged >10 weeks (18.5%). Identified risk factors for wound lesions were small farm size, calf age, single housing, group size, placement of ear tags on ridges, and other ear's score. Individual farmers in Study 2 were able to place ear tags very accurately, although awareness about ear tag lesions appeared to be low among farmers. Sensitising farmers to this issue, implementing routine check-ups of ear tag wounds 2 weeks after insertion, and considering the identified risk factors may reduce animal welfare impairments associated with ear tagging.

Observations on the use of passive integrated transponder (PIT) tags in teleosts and elasmobranchs at a public aquarium, 728 cases, 2007-2020.

Between 2007 and 2020 at New England Aquarium, Boston, MA, USA, we implanted passive integrated transponder (PIT) tags into 728 fish representing 105 teleost and elasmobranch species to identify animals as individuals. At the time of retrospective data analysis, mean longevity interval (median, range) after tag placement for animals that remained alive (n = 236) was 4.7 years (4.5, 0.3-13.8). Mean interval (median, range) between tag placement and death (n = 317) was 2.1 years (1.6, 0-11.2); and mean interval (median, range) between tag placement and transfer to other facilities (n = 175) was 2.5 years (3.1, 0.1-9.3). Possible adverse effects of tagging were extremely rare. Using the described methods, the equipment cost for every 10 PIT tag implantations was $2.83. PIT tag implantation in fishes is a safe and cost effective method to identify individuals, providing an opportunity to accumulate valuable data regarding individual longevity, welfare, basic demographics, and outcome of medical management. PIT tag implantation is recommended as a routine aspect of acquisition, quarantine, and medical management of fish under human care.

Deep learning increases the availability of organism photographs taken by citizens in citizen science programs.

Citizen science programs using organism photographs have become popular, but there are two problems related to photographs. One problem is the low quality of photographs. It is laborious to identify species in photographs taken outdoors because they are out of focus, partially invisible, or under different lighting conditions. The other is difficulty for non-experts to identify species. Organisms usually have interspecific similarity and intraspecific variation, which hinder species identification by non-experts. Deep learning solves these problems and increases the availability of organism photographs. We trained a deep convolutional neural network, Xception, to identify bee species using various quality of bee photographs that were taken by citizens. These bees belonged to two honey bee species and 10 bumble bee species with interspecific similarity and intraspecific variation. We investigated the accuracy of species identification by biologists and deep learning. The accuracy of species identification by Xception (83.4%) was much higher than that of biologists (53.7%). When we grouped bee photographs by different colors resulting from intraspecific variation in addition to species, the accuracy of species identification by Xception increased to 84.7%. The collaboration with deep learning and experts will increase the reliability of species identification and their use for scientific researches.