About

Abstract

The aviation sector needs to make substantial short-term changes to meet its global warming reduction goals. According to last European Community vision document, EU supports, as one possible solution, powertrains using alternative energy sources, such as electricity and/or hydrogen, as opposed to kerosene. In such way, CO2 emissions would be reduced, or, virtually eliminated, resulting in a win-win strategy (in terms of cost and environment).

The design of such aircraft is itself a formidable task as the adoption of such innovative powertrains introduces complexities at the propulsion and its integration levels, that need to be properly modelled. Moreover, an optimization able to reproduce the multidisciplinarity and the strong coupling between the different disciplines is necessary to convert the latent advantages of such powertrain solutions into practical benefit.

Despite the promises, focusing only on CO2 emissions might be hide an unpleasant picture: impacts of non-CO₂ emissions might not only be very significant but also under-represented within the current aviation sector. A significant knowledge gap when addressing a holistic climate-oriented aviation system is the lack of performance indicators to properly measure climatic impact (derived from both CO₂ and nonCO₂) and assess mitigation costs.

Needless to say, climate change is one of the most peremptory challenges this generation needs to face, and aviation is a key agent contributing today to nearly 4-6% of the radiative forcing.

In addition to climate change as a challenge, the possibility of using Artificial Intelligence (AI) techniques is emerging with great force in various fields. Recent studies support that AI can enable the accomplishment of 134 targets across all the goals established in 2030 Agenda for Sustainable Development.  This includes Earth sciences and the aviation domain.

In HYDROGENATING we aim at exploiting AI techniques and to show that they can effectively be used to find climate optimal trajectories to H2 powered aircraft, paving the way towards a climate neutral aviation form both CO₂ and nonCO₂ perspectives.

Overall concept

The overall purpose of this project is to contribute to a more sustainable aviation through a climate-oriented aircraft trajectories that consider both CO₂ and non-CO₂ effects on climate change, Hydrogen-propelled aircraft models, and all supported by artificial intelligence (AI).

More specifically, the aim of this interdisciplinary environment is twofold: 1) to develop new models of hybrid/electric and hydrogen-powered aircraft, including the assessment of non-CO₂ emissions and its impact to climate change; and 2) to develop optimization algorithms for environmentally oriented management of hydrogen-powered aircraft trajectories based on reinforcement learning. Thereby providing the ammunition for a revolution in the ATM system, with Madrid, and in particular UC3M, taking the lead on a future, climate friendly concept of aviation.