The conference will be organized around three topical areas:

1. AI for fuel and engine design: This topic explores how AI can enable the design of new fuels and engines to improve the flexibility, efficiency, and cleanliness of combustion devices. Machine Learning algorithms can inform on the optimal composition of multicomponent fuel blends to achieve target performance indicators, such as autoignition time, flame speed, etc. Optimal engine geometries and operating conditions can be identified quicker using AI algorithms informed by data from measurements or CFD simulations.
2. AI for hydrogen and renewables: This topic focuses on the potential of AI in accelerating the integration of hydrogen and renewables in the current energy landscape. AI can play a role in the design of efficient grid balancing strategies, and, for example, help inform if power from solar and/or wind should, at any given time, be used to provide electricity or be instead stored as hydrogen or ammonia for later use.
3. AI for sensing and diagnostics in energy-related applications: This topic deals with how AI can help record, process, and act-on signals recorded in energy-related applications. AI can be used to indirectly infer quantities that are challenging or impossible to measure directly (e.g., heat release rate and species formation rates in flames) by measuring instead easily accessible quantity (e.g., flame chemiluminescence and acoustic pressure). AI can also enable the development of sensors for the early detection of undesirable events (e.g., pollutant formation and flame instabilities) in combustion chambers. In addition, there are already multiple proven applications of AI in signal and image denoising.