As climate change is nowadays one of the greatest global threats and challenges, the recent global initiatives reflect the strong will of societies to synergistically and proactively apply robust strategies to moderate the climate crisis. This overarching set of policies aims at making Europe climate neutral in 2050, i.e. with zero emissions of greenhouse gases by that date. This strategy includes, for instance, the plan for a 25-times increase in Offshore Wind by 2050, a fact that requires paramount cutting-edge innovation in Wind Energy. Within this framework, AI in all its forms including Aeolian potential big data management, Digital Twins, Machine Learning and Artificial Neural Network approaches are destined to play a major role in the coming years in boosting Wind Energy.

The present CISM Course aims to systematically cover all current trends related to the use of AI to advance Wind Energy. During the course, besides the fundamental knowledge regarding wind and wind energy yielding, including offshore installations, new technologies such as LiDAR for the prognosis of the Aeolian potential, will be presented, along with Machine Learning and Digital Twins techniques applied to the design of wind energy systems. Along these lines, current achievements related to the accuracy of the assessment of the wind resources and the respective wind flow characteristics will be presented. The advances in the design and optimized maintenance of wind energy converters by means of Machine Learning techniques will be presented. It seems that nowadays the key and the game-changer is the in-time prognosis of the response and performance of the wind energy systems, based on high performance monitoring and inspection data. To this end, the concept of Digital Twins has begun to be employed, aiming to bridge the gap between the numerical model and the physical asset by integrating the measurement that, however, can hardly be realised via traditional tools. The emerging artificial intelligence offers a feasible solution from a novel perspective: Digital Twin prototypes are applied to optimise and control the performance of the wind energy systems by integrating inspection and measurement data via Bayesian inference and Machine Learning. Indeed Digital Twins have a promising potential to provide innovative insights into Wind Energy infrastructure status with the physical model, monitoring data and inspection results integrated.

The course will also cover the trends of promising new technologies and valuable topics such as the concept of modular sustainable energy islands and the sustainability analysis of selected types of Wind Energy converters. With these lectures we aim to attract doctoral students, post-doctoral researchers, and practicing engineers working with data-driven Wind Energy projects. The objective is to provide the audience with all the tools necessary to better understand the most recent developments on the above described subjects, and thus to facilitate the technology transfer from research to applications.