Abstract
Integrating citizen science with digital twin technology represents a significant development in oceanographic research and marine management. This paper examines how the Iliad project has successfully developed a comprehensive suite of digital twins of the ocean (DTOs) that leverage citizen science contributions to enhance data coverage, improve modelling accuracy, and foster public engagement with marine ecosystems. Through innovative technological solutions, including semantic interoperability frameworks, mobile applications, knowledge graphs, and gamification approaches, the project demonstrates the reciprocal benefits between citizen scientists, scientific research and digital twin ecosystems. The developments presented in this work illustrate how engaging the public in scientific research not only broadens the data foundation for digital twins but also creates pathways for citizens to gain valuable insights from these sophisticated digital representations of ocean environments.

Abstract
Developed within the Iliad Digital Twin of the Ocean (DTO) project, Coastal Crete provides advanced marine forecasting for oil spill detection and response. The system integrates satellite data, in-situ observations, and machine learning to predict oil spill trajectories and minimize environmental impacts. Using a multi-model approach, it combines WRF-DA, NEMO, and WAVEWATCH III models for high-resolution forecasts. Making use of Sentinel-1 SAR imagery, a deep learning approach was developed for near-real-time oil spill detection. The methodology is based on a U-net Neural Network, which is compared with the statistical methodology based on pythons' SNAPpy library. The operational forecasting system employs MEDSLIK-II for oil spill transport modeling and visualization via the GeoMachine platform, ensuring rapid decision-making for marine safety and environmental protection.

Abstract
The application of digital twin technology to the ocean is often referred to as Digital Twins of the Ocean (DTO). One notable initiative funded under Horizon Europe programs - Green Deal is the ILIAD - Digital Twin of the Ocean project. One of the objectives of ILIAD is to establish interoperable, data-intensive, and cost-effective DTO pilots. This paper focuses on one such pilot dedicated to environmental monitoring and water quality assessment associated with the OceanLab infrastructure in the Trondheim Fjord, Norway. This paper outlines the architecture and concept of the pilot while providing detailed insights into its application for various what-if scenarios. The scenario presented in this paper is a case study that analyzes the impact of a hypothetical oil spill at the Trondheim terminal. It focuses on the spread of surface oil over a 30-hour period using various pilot modules. The paper also discusses the potential replication of this study in another geographical location.

Abstract
ILIAD focuses on developing an ecosystem of interoperable Digital Twins for the Ocean by connecting to existing ocean data infrastructures, enhancing ocean data infrastructures with additional observation technologies and citizen science, employing numerical models and executing AI models, and aiding operational decision-making of marine and maritime activities. This work focuses on the diverse ILIAD Pilots and emphasizes sensors, data collection, and data management. Emphasis is given on new, low-cost sensors, their objectives, the novel technical aspects, the generated data, and how they can be used in the ILIAD project framework and the operation of ILIAD DTs.

Abstract

Abstract
This study explores models for synthetic data generation of time series. In order to improve the achieved results, i.e., the data generated, new ways of improvement are explored and different models of synthetic data generation are compared. The model addressed in this work is the Generative Adversarial Networks (GANs), known for generating data similar to the original basis data through the training of a generator. The GANs are applied using the datasets of Quinta de Santa Barbara and the Pinhao region, with the main variables being the Average temperature, Wind direction, Average wind speed, Maximum instantaneous wind speed and Solar radiation. The model allowed to generate missing data in a given period and, in turn, enables to analyze the results and compare them with those of a multiple linear regression method, being able to evaluate the effectiveness of the generated data. In this way, through the study and analysis of the GANs we can see if the model presents effectiveness and accuracy in the synthetic generation of meteorological data. With the proper conclusions of the results, this information can be used in order to improve the search for different models and the ability to generate synthetic time series data, which is representative of the real, original, data.