Invasive alien species (IAS) pose serious threats to biodiversity and ecosystem health, affecting human well-being. Many of those species have multiple roles, providing both benefits and burdens to ecosystems and stakeholders. Managing these Multiple-Role invasive species (MR-IAS) involves complex trade-offs, necessitating interdisciplinary approaches for optimal outcomes. EconVasions responds to the critical need to assess these trade-offs and develop solutions that reconcile conflicts from these species, in line with conservation goals and societal needs. Moving beyond reductive monetary comparisons of benefits and costs that fail to fully capture the complex realities of MR-IAS impacts, EconVasions will be developing a robust conceptual framework, initiating this process with expert elicitation, workshops and systematic reviews. This will result in a dynamic database, designed with protocols that ensure transparency and methodological rigor. The database will enable a broad spectrum of analyses, facilitating in-depth exploration of MR-IAS and revealing patterns, trade-offs and gaps in geographical, taxonomic and interdisciplinary research. Importantly, it will serve as a structured platform for analyzing successful case studies, focusing on their key attributes identified through improved wellbeing outcomes and insights from experts. The approach includes a comprehensive analysis of conditions under which MR-IAS benefits arise, focusing on the origins of their ambivalent impacts across spatial, temporal, and stakeholder scales. The assessment extends to social and economic-minded descriptors such as market dynamics, human settlement trends, property rights, historical land use, path dependence, uncertainties and intangible impacts, recreational and aesthetic values, economic assessment methods and socio-demographic elements. EconVasions further leverages bioeconomic models for data-rich case studies to delve into trade-offs in MR-IAS management, with a particular focus on navigating uncertainty. Expanding on the foundational understanding of MR-IAS and their management EconVasions transcends traditional academic boundaries, fostering the development of transparent and evidence-based policies. The project is further structured around three pivotal research axes: Equity, Marine, and Arctic ecosystems, each representing an uncharted research territory. The project’s focus on overlooked dimensions of equity will address unevenness in distribution of benefits and burdens from MR-IAS across different stakeholder groups. Examining perceptions of equity such as the privatization of benefits versus the socialization of costs from MR-IAS, EconVasions aims to advance invasion science and management, adding depth to the social science dimensions of natural resource management. EconVasion’s focus on advancing understanding of MR-IAS within under-researched marine ecosystems centers on socio-ecological dynamics in coastal communities and fisheries and is set to contribute to advances in marine sciences and efficacy of marine conservation efforts. EconVasions' focus on the rapidly evolving Arctic ecosystems stands to make groundbreaking contribution in a region of critical importance where social sciences on IAS are scarce. Recognizing the Arctic's unique position as largely underexplored yet rapidly evolving region at the crossroads of resource exploitation and conservation, it is as an ideal case study for advancing understanding of MR-IAS and their trade-offs. EconVasions delves into an uncharted and intricately contentious domain, designing and implementing novel interdisciplinary approaches that entail high-risk yet potential for high-gain outcomes, poised to significantly advance invasion science, environmental policy, and the integration of social science perspectives.

During the very last years, computer vision has made a significant breakthrough with the emergence of deep learning techniques. Indeed, it successfully benefits to image classification where deep learning outperforms the state-of-the-art in challenges such as the Imagenet Large Scale Visual Recognition Competition (ILSVRC) since 2012. In this project we propose to use this kind of method, more particularly convolutional neural networks (CNN), for the detection and the recognition of multiple small size objects in images. Two applications are considered in this project, the detection and mapping of wales using satellite imaging and the detection and recognition of objects (vehicles) in infrared images. For both applications, the object size ranges typically from 5x5 to 10x10 pixels. To address this detection and recognition problem we propose to design 2 different architectures. The first one is the most common approach and consist in a sliding window that extract patches (small part of the full image). Then, the patches are introduced in a trained CNN to differentiate objects from the background, and possibly, classify them. The second approach deals with the full image in one step. In this case, we design a deep classification net for semantic segmentation. In the final segmented map each pixel gets a label representing (hopefully) its class. These two approaches will be developed by the members of the consortium using the synthetic database provided by MBDA. Note that these CNN architectures must be designed regarding the operational constraints. Following this work, we will deal with the variability of the background in the test database in comparison with the background available in the training database. The objects to be detected and recognize will be considered available in the training database. The goal is to evaluate possible operational situations and the potential losses in the final results. We will also study how the CNN trained on simulated data performs on real data. To fulfil this experiment, new acquisitions in operational situations will be conducted by MDBA in order to complete the existing real images database. Considering the whale mapping application, the idea is to evaluate the adaptation capacity when lower resolutions are used in the test phase. Besides, thanks to the available real data, we also propose to evaluate common methods for incremental learning to specialize the proposed architecture. Along each step of the project, we will evaluate the performances of the CNN and the results obtained. The goal is to monitor the learning process and to use criteria to quantify the final detection and recognition results. Finally, as introduced before, the CNN design will take into account the possible operational constraints. Thus, we will analyse the potential solutions to reach real time implementation in embedded systems. We will deal with both the material (GPU, energy consumption…) and software (how to reduce the computational time) parts.

Abalone is a low trophic herbivorous gastropod feeding on seaweed. It has been consumed for centuries as a traditional dish in many parts of the world. This species is fished professionally and recreationally in France. However, wild abalone stocks have declined sharply in France due to massive mortalities caused by a pathogenic bacterium, Vibrio harveyi, with a mortality up to 80% in Brittany and Normandy at the end of the nineties when sea-water temperature reached over 18°C in summer. Impacted populations have not recovered. Ranching, which is an extensive rearing method consisting of implanting juveniles in the natural environment, stock enhancement, which consists of increasing or maintaining fisheries, and restocking, which consists of implanting juveniles to re-establish disappeared stocks, could be opportunities to develop new opportunities for the preservation of this emblematic species. The juveniles are reared in nurseries and produced from wild or domesticated broodstock depending of the objective. The implantation of abalone for stock enhancement has been carried out for many years in countries such as Japan, Mexico and South Africa. However, the technique for implanting abalone in the natural environment is not currently mastered in France, nor is the equipment associated with these implantations. Moreover, certain technical obstacles have still to be overcome. Technical obstacles remain, with a mortality of 90% in average, observed mainly just after seeding. ORMER, an experimental development project, aims at developing innovative tools to enable the establishment of sustainable abalone restocking with a transdisciplinary approach. The following hypothesis will be tested: 1) Initial mortality can be minimised by conditioning hatchery juveniles to predators and using optimised seeding techniques 2) improved knowledge of the ecosystem carrying capacity of seeding sites considering juvenile density and size can improve survival in ranching and stock enhancement programmes at an operational scale 3) Better understanding of the wild populations genetic structure, the assessment of health status and immune priming of juveniles prior to seeding can mitigate the risk associated with reseeding operations 4) Assessment of social acceptability, as well as long-term economic viability are necessary keystones to ensure sustainable development of restoration, stock-enhancement or ranching programmes. Partners from the socio-professional sector (including an aquaculture company and the Iroise Marine Natural Park) as well as researchers from different disciplines (ethology, ecology, genetics, pathology, economics and sociology) will work together to develop sustainable stocking programmes to provide the necessary keys to decision-makers (business leaders, fishers, national parks) on social, economic and technical aspects. The expectations of each stakeholder (professional and recreational fishers, aquaculture, ecological rehabilitation) will be included into the project.

Coastal eutrophication is one of the greatest threats to the health of coastal social-ecological systems (SES) worldwide. Despite long-term efforts, few eutrophic systems are now in recovery. GreenSeas aims to address this persistent sustainability problem, recognized as a “wicked” problem by building on the complex multi-site case of Brittany (France), one of the most severely affected coastal areas in Europe. The general objective is to investigate past and current adaptation of vulnerable coastal systems exposed to long-lasting eutrophication, and possible transformative pathways towards more sustainable and equitable futures. We will develop a transdisciplinary approach along the land-sea continuum, mixing interdisciplinary sciences (agronomy, ecology, biogeochemistry, social anthropology, environmental history, political science, and economics) and stakeholder expertise. The project will provide an integrated understanding of the SES adaptation dynamics, and the social and political changes affecting coastal areas at different organizational levels, towards sustainable management of these areas. It will identify conditions under which confronting long-standing environmental issues can lead to rapid transition towards sustainable SES, and contribute to co-designing appropriate eutrophication management strategies and public policies.