We are a research initiative from MERIDIAN (Marine Environmental Research Infrastructure for Data Integration and Application Network) hosted on MARS (Maritime Risk And Safety Research) group at Dalhousie University and funded by the Department of Fisheries and Oceans (DFO) of the Government of Canada. This project aims to facilitate using Automatic Identification System (AIS) data for marine vessel tracking to enhance our understanding of global maritime traffic and the impacts of vessel activity on marine ecosystems.

Our main objective is to build an easy-to-use open-source toolbox for raw AIS data extraction, processing, visualization, and vessel modeling. We aim to make AIS data accessible and comprehensible for a broad spectrum of users, from government bodies and policymakers to university researchers, non-government organizations (NGOs), coastal communities, and the general public.

AISviz was proposed to implement machine learning applications that work seamlessly with flexible data sources from terrestrial and satellite streams of AIS data. Besides, we intend to make the interaction with AIS data user-friendly, achieved through developing a Graphical User Interface (GUI). This approach will simplify data retrieval, integration, and basic manipulation processes. We also aim to enhance the applicability of AIS data by incorporating its integration with different maritime raster-based third-party data sources. The project and all its components will be made openly accessible, promoting collaboration, transparency, and public contribution.

Through AISviz, we aim to open new pathways of research and policy-making strategies related to environmental preservation, vessel traffic optimization, illegal fishing detection, aquatic invasive species prevention, noise pollution monitoring, and much more. Moreover, AISviz would equip anyone interested in understanding the patterns and impacts of vessel movement with the necessary tools and knowledge to do so. Even if you're just an enthusiast, educator, student, or concerned citizen, AISviz can help you grasp the crucial role of vessel traffic in shaping our world's oceans.

This project was born out of active collaboration, and we're ready to widen our circle. Regardless of your offering or background - whether you are a seasoned researcher, a programmer interested in AIS data, an organization focusing on marine conservation, or an eager learner fascinated by ocean sciences – our project welcomes you! Feel free to connect with us. We're always ready to answer your questions, consider your suggestions, and engage in discussions regarding AIS data.

• Spadon, G., Kumar, J., Smith, M., Vela, S., Gehrmann, R., Eden, D., van Berkel, J., Soares, A., Fablet, R., Pelot, R., & Matwin, S. (2023). Building a Safer Maritime Environment Through Multi-Path Long-Term Vessel Trajectory Forecasting. arXiv preprint arXiv:2310.18948. https://doi.org/10.48550/arXiv.2310.18948

• Song, R., Spadon, G., Bailey, S., Pelot, R., Matwin, S., & Soares, A. (2024). Gravity-Informed Deep Learning Framework for Predicting Ship Traffic Flow and Invasion Risk of Non-Indigenous Species via Ballast Water Discharge. arXiv preprint arXiv:2401.13098. https://doi.org/10.48550/arXiv:2401.13098