Dispatcher3 will develop a software prototype for the acquisition and preparation of historical flight data in order to give support to the optimisation of future flights providing predictive capabilities and advice to dispatchers and pilots. This will be done considering airline preferences and the impact of flight missions on overall airline objectives. Dispatcher3 focuses on activities prior to departure: dispatching and pilot advice on how to operate the flight. Dispatcher3 is composed of three layers: data infrastructure, predictive capabilities and advice capabilities. The data infrastructure will be powered by DataBeacon, a multi-sided and open-source data storage and processing platform. DataBeacon provides private environments, secure data frames, a full-stack artificial intelligence environment and a scalable highly available on-demand cluster. DataBeacon has been developed and successfully been used in other initiatives by members of the consortium. The infrastructure will allow further developments, based on data science techniques, to be built on the pre-processed datasets. The predictive capabilities will be provided by the development of two modules: data acquisition and preparation, encompassing data wrangling and descriptive analytics, and a predictive model, which will perform target variable labelling and feature engineering, plus the training, testing and validation of machine learning predictive models for targeted airlines' KPIs. With the same predictions, different advice could be generated considering user policies. The advice capabilities of Dispatcher3 will be provided by a dedicated advice generator module, which will collect all the information from the predictive analytics and build a decision framework, which could be used by dispatchers and pilots. Dispatcher3 fits within the activities of CS2 Systems ITD WP1.3 "FMS and functions" and addresses some of the high-level objectives and challenges for this ITD defined by CS2.

SafeClouds is a research project supported by EASA and powered by a full spectrum of aviation stakeholders (Airlines, Airports, ANSPs, Eurocontrol, Research Entities, Safety Agencies) that develops cutting-edge technologies for aviation safety assurance in a cost-effective manner. SafeClouds proposes a data-driven approach to achieve a deeper understanding of the dynamics of the system, where risks are pro-actively identified and mitigated in a continuous effort to enhance the already excellent European aviation safety records. SafeClouds develops an innovative aviation safety data analysis approach. Currently each stakeholder owns different isolated datasets and data-sharing paradigms are rare. However, the combination of those datasets is critical in discovering unknown safety hazards and in understanding and defining a performance-based system safety concept. The new data-driven paradigm, capable of extracting safety intelligence in a fast, connected and inexpensive way requires the collaboration of aviation and IT entities sharing their raw datasets, tools, techniques and information. SafeClouds high level objectives are: - To define a user-requirement driven approach for data mining in aviation safety, covering several current safety challenges within airlines and runway operations. - To develop novel data structures and safety intelligence representation. Given the complexity of the datasets, SafeClouds aims to solve their current challenges in data handling and knowledge discovery. - To develop the proof of concept and validate in a laboratory the safety data analysis paradigms, at different levels: historical analysis, predictive analytics, automatic safety data monitoring and unknown hazards identification. - To assemble a group of entities that encompasses the entire data-cycle for a unified, achievable vision for the future of safety analytics in Europe, including: users, data providers, data infrastructure researchers, operators and data scientists.