The 1st Workshop on Advanced Platforms for Generative AI for Marine Science and Engineering Applications (GENAI4SEA) will explore the cutting-edge intersection of artificial intelligence, oceanography, and marine ecology. This rapidly evolving field has shown great progress in the last five years. The power of generative artificial intelligence (GAI) has enabled tackling complex challenges in marine science and engineering across various applications, including identification and forecasts of long-term ocean dynamics, super-resolution in data reconstruction, and prediction of extreme events and harmful conditions.

Generative AI techniques, such as large language models (LLMs), generative adversarial networks (GANs), variational autoencoders (VAEs), and deep reinforcement learning, have demonstrated remarkable capabilities in generating synthetic data, simulating natural processes, and optimizing complex system dynamics. When applied to marine science and engineering, these advanced architectures offer an effective framework to advance knowledge with unprecedented possibilities for innovation and discovery.

At the forefront of marine research, generative machine learning is revolutionizing how we model ocean dynamics, predict climate patterns, design autonomous systems, and optimize marine renewable energy solutions. By leveraging GAI, scientists and engineers can augment sparse observational datasets, simulate intricate ocean dynamics with high accuracy, and support the development of sustainable solutions for ocean exploration and exploitation.
The workshop aims to accelerate this interdisciplinary field, providing opportunities to generate the first cross-disciplinary synthesis between the tools provisioned by platform providers, the knowledge in science and technology provided by academia, and the applications making the real world a better place.

The workshop has been designed to promote dialogue and interactions among participants, acting as a potential agorà promoting cross-cutting approaches to ensure the reliability and robustness of AI-generated data, including the ethical considerations surrounding AI-driven decision-making in marine environments.

In our vision, the structure of the GENAI4SEA workshop enables collaborative actions between computer scientists, marine scientists, and engineers to push the boundaries of what is possible in marine science, technology, and engineering. It will identify opportunities to leverage promising approaches in generative AI to deepen our understanding of the oceans as a major Earth system component, driving innovation towards a more sustainable future.

Revision process

The workshop will adopt the same standards and procedures as the main conference. Each submitted paper will undergo a double-blind review, in which the identities of the authors and the reviewers are kept confidential to minimize bias. Upon receiving approximately 20 submissions, our workshop chairs will carefully assign each paper to at least two expert reviewers with relevant expertise in the respective topic areas. These reviewers will evaluate the submissions based on predefined criteria, including originality, technical quality, clarity of presentation, and relevance to the workshop’s themes. The reviewing process will involve a comprehensive examination and constructive feedback. This feedback, designed to guide authors in enhancing the quality of their submissions, will be based on the reviewers’ assessment of each paper’s novelty and significance, considering its potential contribution to marine science and engineering applications of generative AI. After completing their evaluations, reviewers will provide detailed comments and scores for each submission, highlighting strengths, weaknesses, and areas for improvement. The workshop chairs will then aggregate the feedback from the reviewers and convene to make informed decisions on paper acceptance.

Given the competitive nature of the selection process, only the top eight papers representing the most innovative and impactful contributions to the field will be chosen for presentation at the workshop. These selected papers will serve as beacons, illuminating the latest advancements and insights in the intersection of generative AI and marine science and engineering. Authors of accepted papers will receive notification of their paper’s status and, if necessary, feedback from the reviewers to help them revise their work for presentation at the workshop. The final program will feature diverse topics, ensuring a comprehensive exploration of the workshop’s themes throughout the full-day event. By adhering to a robust reviewing process and upholding the highest standards of academic integrity, our workshop aims to foster intellectual exchange, promote collaboration, and advance knowledge at the forefront of generative AI applications in marine science and engineering.

Call for Papers

The 1st Workshop on Advanced Platforms for Generative AI for Marine Science and Engineering Applications (GENAI4SEA) explores the intersection of artificial intelligence and marine disciplines. Generative AI techniques like Large Language Models (LLMs), GANs, VAEs, and deep reinforcement learning have recently been used to solve several complex problems in marine science and engineering.
These AI platforms have the potential to revolutionize ocean modeling, climate prediction, ecosystem assessments, design and operations with autonomous systems, and marine energy solutions. They enhance data availability and resolution, simulate ocean dynamics, and accelerate sustainable ocean exploration and exploitation solutions.
The workshop aims to accelerate interdisciplinary collaboration, leveraging academia, platform providers, and real-world applications across all marine science, technology, and engineering sectors. Further, it fosters discussions on AI data reliability, ethical decision-making, and sustainable innovation in the blu-economy.
GENAI4SEA aims to discuss recent advancements, applications, and challenges in generative AI for marine science and engineering and identify progress toward a sustainable future.

We invite submissions of original research contributions, case studies, and innovative applications in the following areas (but not limited to):

• Generative AI Techniques: This section explores various generative AI methods, such as Large Language Models (LLMs), GANs, VAEs, and deep reinforcement learning, and their applications in marine science and engineering.
• Synthetic Data Generation: Techniques for generating synthetic data to augment sparse observational datasets in marine science research.
• Simulation of Ocean Dynamics: Utilizing generative AI to simulate and forecast complex oceanic processes and phenomena.
• Climate Prediction and Modeling: The application of generative AI in climate modeling and prediction mainly focuses on marine climate patterns and trends.
• Autonomous Systems: Design, optimize, and control autonomous vehicles using generative AI techniques for marine exploration, inspection, and monitoring tasks.
• Marine Renewable Energy: We use generative AI approaches to optimize and design marine renewable energy systems, such as offshore wind turbines, wave energy converters, and tidal turbines.
• Oceanographic Data Analysis: Advanced data analysis methods, including data assimilation, leveraging generative AI to extract meaningful insights from large-scale oceanographic datasets.
• Environmental Monitoring and Management: Generative AI is used to optimize the monitoring and management of marine ecosystems, including biodiversity assessment, pollution detection, and habitat mapping.
• Ethical Considerations and Bias in AI: Discussion on ethical considerations, biases, and fairness issues associated with generative AI in marine science and engineering applications to support decision making.
• Robustness and Reliability of AI Models: Techniques for ensuring generative AI models’ robustness, reliability, and generalizability in real-world marine environments.
• Human-AI Collaboration in Marine Research: Exploration of collaborative frameworks and interfaces for integrating human expertise with generative AI tools in marine science and engineering projects.
• Interdisciplinary Collaboration and Knowledge Integration: Strategies for fostering interdisciplinary collaboration between computer scientists, marine scientists, and engineers to address challenges in marine research using generative AI.
• Case Studies and Applications: Presentation of case studies and real-world applications showcasing the successful implementation of generative AI in solving specific marine science and engineering problems.
• Future Directions and Emerging Technologies: This session will discuss emerging trends, challenges, and future research directions in generative AI for marine science and engineering.

We encourage submissions of full papers describing original research, work-in-progress, or experience reports related to the workshop topics.

Important dates

Paper Due: September 2, 2024
Authors Notification: September 16, 2024
Camera-ready Submission: September 23, 2024

Workshop/SS Proposal Due: June 30, 2024
Regular Paper Due: June 25, 2024 July 26, 2024 (Final Extension)
WiP/Workshop/SS Paper Due: July 15, 2024 August 10, 2024 (Final Extension)
LBI Paper Due: August 10, 2024
Author Notification: September 1, 2024
Paper Registration Due: September 18, 2024
Camera-ready Submission Due: September 27, 2024

Submission guidelines

Authors are invited to submit their original research work that has not been submitted or published in any other venue. Papers (4-6 pages long) must be submitted in IEEE CS Proceedings format. Read IEEE formatting info.
All the accepted papers will be published by IEEE in the Conference Proceedings (IEEE-DL and EI indexed).
At least one of the authors of any accepted paper is requested to register and present the paper at the conference.

Workshop proceedings

Accepted papers presented at the workshop will be published in revised form in the PiCOM 2024 proceedings by Conference Publishing Services. The best papers will be invited to submit an extended version to the Special Issue journal (TBD).

Organizers

Raffaele Montella (raffaele.montella@uniparthenope.it) is an Associate Professor with tenure in Computer Science at the Department of Science and Technologies (DiST), University of Naples “Parthenope” (UNP), Italy. His main research topics and scientific production focus on tools for embedded platforms for data crowdsourcing in marine science and engineering, scientific workflows, high-performance computing, cloud computing, and GPU virtualization with applications in computational environmental science. He is the Director of the High-Performance Scientific Computing Laboratory (HPSC), joining together theoretical and practical knowledge of scientists from computer science, scientific computing, applied mathematics, bioinformatics, and computational environmental science, taking the best from all those research fields to perform science and technology acceleration. He leads the DAGonStar workflow engine project, which is designed to support large-scale environmental data production scientific workflows. He is the Chief of Technical Operations (CTO) of the Center for Marine and Atmosphere Monitoring and Modeling (CMMMA), leading the design and management of the HPC infrastructure.

Sokol Kosta (sok@es.aau.dk) holds a PhD degree in Computer Science from Sapienza University of Rome, Italy, since 2013. His previous and current research topics focus mainly on distributed systems, IoT, Edge/Cloud Computing, and the security aspects of these systems. The results of his research are presented in some of the topmost peer-reviewed international conferences and journals like IEEE Infocom, ACM/USENIX HotCloud, IEEE P2P, IEEE Secon, ACM Sigmetrics, TMC. In 2012 the Computer Science Department of La Sapienza University presented him with the Best PhD Student Paper Award, and in 2013 he won the IEEE Infocom 2013 Best Demo Award, and the IEEE Secon Best Demo Award. In 2024, he was awarded the IEEE Infocom Test of Time Paper Award. He is the recipient of the Young Researchers Starting Grant given by La Sapienza University of Rome, for three years in a row. His PhD studies were partially supported by the Albanian Ministry of Education through the Excellent Albanian Researchers program. Sokol has worked on several European Projects such as Horizon 2020/Europe (IoT-A, RAPID, I3LUNG), KDT-JU (CLEVER), Marie Curie Actions (IoTalentum, QUARC), etc., supervising more than 5 PhD students. Sokol joined Aalborg University in 2016 as Assistant Professor and in May 2020 was promoted to Associate Professor.

Patrizio Mariani (pat@aqua.dtu.dk) is professor and head of Observation Technology at the Technical University of Denmark (DTU). His research focuses on developing models, methods, and technologies for the complex ocean system with a cross-disciplinary approach in marine science and engineering in support of integrated marine ecosystem assessments. His expertise is in ecosystem modeling (physical-biological coupling, ecology of plankton and fish, population dynamics, dispersion models) and ocean technology (underwater observation technology, software development, adaptive sampling, path planning, optical and acoustic sensing, big data analytics). He is the Head of the Observation Technology research area at DTU Aqua and president and scientific coordinator of EUROMARINE. He is an expert advisor to the European Commission on research and innovation programs and coordinator of several National and International research projects.