26 research outputs found

    Artificial Intelligence-powered fossil shark tooth identification: Unleashing the potential of Convolutional Neural Networks

    Full text link
    All fields of knowledge are being impacted by Artificial Intelligence. In particular, the Deep Learning paradigm enables the development of data analysis tools that support subject matter experts in a variety of sectors, from physics up to the recognition of ancient languages. Palaeontology is now observing this trend as well. This study explores the capability of Convolutional Neural Networks (CNNs), a particular class of Deep Learning algorithms specifically crafted for computer vision tasks, to classify images of isolated fossil shark teeth gathered from online datasets as well as from the authors′' experience on Peruvian Miocene and Italian Pliocene fossil assemblages. The shark taxa that are included in the final, composite dataset (which consists of more than one thousand images) are representative of both extinct and extant genera, namely, Carcharhinus, Carcharias, Carcharocles, Chlamydoselachus, Cosmopolitodus, Galeocerdo, Hemipristis, Notorynchus, Prionace and Squatina. We developed a CNN, named SharkNet-X, specifically tailored on our recognition task, reaching a 5-fold cross validated mean accuracy of 0.85 to identify images containing a single shark tooth. Furthermore, we elaborated a visualization of the features extracted from images using the last dense layer of the CNN, achieved through the application of the clustering technique t-SNE. In addition, in order to understand and explain the behaviour of the CNN while giving a paleontological point of view on the results, we introduced the explainability method SHAP. To the best of our knowledge, this is the first instance in which this method is applied to the field of palaeontology. The main goal of this work is to showcase how Deep Learning techniques can aid in identifying isolated fossil shark teeth, paving the way for developing new information tools for automating the recognition and classification of fossils.Comment: 40 pages, 8 figure

    The Influence of Gear – Vessel Combination on Artisanal Fishery Catch Composition: A Case Study of Kigamboni Municipal Coastal Area.

    Get PDF
    The study assessed the influence of gear-vessel combination on catch composition in artisanal fishery, which is characteristically multi-specie and multi-gear. Such complexity comes with major issues in managerial perspective. The study used secondary data recorded within twelve months (Feb 2020 to Feb 2021) from two landing sites (Mjimwema, and Buyuni). The study found prevalence Mean Trophic Level (MTL) of 3.8 that suggested possible trophic cascades when related to other studies conducted in the western Indian Ocean. ANOSIM and PERMANOVA significant results (p ˂ 0.05) suggested difference in catch composition. Location was also found to influence catch composition of Artisanal fisheries at the coast of Kigamboni Municipal. However in this study some limitations were observed in the analysis of seasonality carried by the use of ANOVA, one outliers were observed through the stem- and- leaf diagram, also Leven’s test of homogeneity of variance was found to be significant, moreover due to lack of sufficient data, Kimbiji was removed from the study hence narrowed the research area. Nevertheless the study concluded that catch composition is attributable to the use of different combination of fishing gear and vessels also the denuded assemblage of fish communities observed in the secondary data with a lot of zeros can be attributable to excessive fishing pressure exerted in the coral reef fish species. The study recommends TAFIRI, should emphasize and put up supportive infrastructures to private organization interested in conducting fisheries research; whereas suggested areas for further research include studies on environmental gradients that can also influence the catch composition together with documenting and understanding the mean trophic level (MTL) trend of Kigamboni artisanal fisheries. Keywords: Catch composition, Mean Trophic Level, Artisavnal Fisheries and Gear-vesse

    Educational Policy Committee Meeting – Open Session Packet 08/24/2023

    Get PDF

    Board of Directors Quarterly Meeting - Open Session Packet 09/08/2023

    Get PDF

    Educational Policy Committee Meeting – Open Session Book 02/22/2024

    Get PDF

    Evidence of overfishing in small-scale fisheries in Madagascar

    Get PDF
    This is the final version. Available from the publisher via the DOI in this record.The datasets generated for this study are available on request to the corresponding authorSmall-scale fisheries are an important source of food, income and cultural identity to millions of people worldwide. Despite many fisher people observing declining catches, a lack of data remains a barrier to understanding the status of small-scale fisheries and their effective management in many places. Where data exist, complex analyses and stock assessments are often beyond the capacity and budgets of local managers. Working with small-scale fisheries in western Madagascar, we analyze landings data to provide a description of the fishery and evaluate the top twenty most commonly caught species for evidence of overfishing. Using length composition data, we use Froese’s three simple rules: Let them spawn, let them grow and let the mega-spawners live, as well as Cope and Punt’s decision tree to infer if spawning biomass is less than target reference points. We then use length-based parameters to calculate fishing mortality and compare with published estimates of natural mortality to assess overfishing (F > M). Over 17,000 fishing trips were registered over a 2-year period (2010–2012), landing just short of 2 million individual fish. Length data were recorded for a sample of over 120,000 individuals. Fish comprised 95% of landings, with the remainder comprised of other groups including crustaceans (mostly shrimp, crab, and lobster), cephalopods, and holothurians. We provide some of the first evidence that fish species caught in the small-scale fisheries of the Menabe region of Madagascar are experiencing overfishing. The most notable result is that for 13 of the 20 most common species, fishing mortality exceeds natural mortality. Many species had a large proportion of individuals (in some cases 100%) being caught before they reached maturity. Very few species were fished at their optimal size, and there were low numbers of large individuals (mega-spawners) in catches. Overfishing in western Madagascar presents a serious threat to the income, food security and well-being of some of the most vulnerable people in the world. The results of this paper support the call for improved management. However, management approaches should take account of overlapping fisheries and be inclusive to ensure the impacts of management do not undermine the rights of small-scale fishers. Further data are needed to better understand the trends and to improve management but should not hinder pragmatic action.European Union’s Regional Coastal Management Programme of the Indian Ocean Countrie

    Rostrum abnormalities in the endangered Indian Ocean humpback dolphin (Sousa plumbea) in South Africa

    Get PDF
    SUPPORTING INFORMATION : Appendix 1. Photographs of the abnormal rostrum conditions characterized in this study with corresponding ID number (if available), locality, time, and credits.Morphological abnormalities in wild animals can be indicators of the underlying health of a population and may be determined through routine photographic surveys. Here, we assess unusual rostrum conditions in Indian Ocean humpback dolphins (Sousa plumbea) inhabiting South African coastal waters to understand the rate of prevalence of abnormal rostrums and formulate hypotheses on potential causes. Photographic data were collated from systematic boat surveys and opportunistic sightings, obtained between April 1998 and March 2021 in various regions along the South African coast. Overall, 31 unique individuals were found with abnormal rostrum conditions, varying from slight misalignments to severe wounds and/or aberrant morphologies. In most cases, injuries were likely caused by natural events during the animal's life history such as interactions with sharks and/or reef-associated hunting strategies. Mark–recapture data indicated that individuals had survived with these injuries for up to 10 years. This study reports the highest incidence of rostrum abnormalities in the species. As numbers reflect only those that have survived their injuries, they are considered a minimum estimate. A better understanding of the cause(s) of these injuries is important given the endangered status of this species.National Research Foundation; The Rufford Foundation; The Society for Marine Mammalogy.https://onlinelibrary.wiley.com/journal/17494877hj2023Mammal Research InstituteZoology and Entomolog

    Sex and size influence the spatiotemporal distribution of white sharks, with implications for interactions with fisheries and spatial management in the southwest Indian Ocean

    Get PDF
    The study was made possible through generous funding by Fischer Productions for fieldwork and equipment costs. TP was supported by a postdoctoral fellowship funded by the Nelson Mandela University Research Career Development Office (2016-2018) and funding from the South African Research Chairs Initiative awarded to Prof AT Lombard by the National Research Foundation, and by a Royal Society Newton International Fellowship (2018-2020, NF170682).Human activities in the oceans increase the extinction risk of marine megafauna. Interventions require an understanding of movement patterns and the spatiotemporal overlap with threats. We analysed the movement patterns of 33 white sharks (Carcharodon carcharias) satellite-tagged in South Africa between 2012 and 2014 to investigate the influence of size, sex and season on movement patterns and the spatial and temporal overlap with longline and gillnet fisheries and marine protected areas (MPAs). We used a hidden Markov model to identify ‘resident’ and ‘transient’ movement states and investigate the effect of covariates on the transition probabilities between states. A model with sex, total length and season had the most support. Tagged sharks were more likely to be in a resident state near the coast and a transient state away from the coast, while the probability of finding a shark in the transient state increased with size. White sharks moved across vast areas of the southwest Indian Ocean, emphasising the need for a regional management plan. White sharks overlapped with longline and gillnet fisheries within 25% of South Africa’s Exclusive Economic Zone and spent 15% of their time exposed to these fisheries during the study period. The demersal shark longline fishery had the highest relative spatial and temporal overlap, followed by the pelagic longline fishery and the KwaZulu-Natal (KZN) shark nets and drumlines. However, the KZN shark nets and drumlines reported the highest white shark catches, emphasising the need to combine shark movement and fishing effort with reliable catch records to assess risks to shark populations accurately. White shark exposure to shark nets and drumlines, by movement state, sex and maturity status, corresponded with the catch composition of the fishery, providing support for a meaningful exposure risk estimate. White sharks spent significantly more time in MPAs than expected by chance, likely due to increased prey abundance or less disturbance, suggesting that MPAs can benefit large, mobile marine megafauna. Conservation of white sharks in Southern Africa can be improved by implementing non-lethal solutions to beach safety, increasing the observer coverage in fisheries, and continued monitoring of movement patterns and existing and emerging threats.Publisher PDFPeer reviewe
    corecore