{"id":7827,"date":"2025-03-27T11:18:15","date_gmt":"2025-03-27T11:18:15","guid":{"rendered":"https:\/\/reuniwatt.com\/es\/?p=7827"},"modified":"2025-03-27T11:18:15","modified_gmt":"2025-03-27T11:18:15","slug":"seminario-web-when-ai-meets-the-sky","status":"publish","type":"post","link":"https:\/\/reuniwatt.com\/es\/eventos\/seminario-web-when-ai-meets-the-sky\/","title":{"rendered":"[Seminario web] When AI meets the sky"},"content":{"rendered":"
We are proud to present a webinar on cutting-edge research in atmospheric sciences and cloud observation techniques: When AI meets the sky All sky imagers – from basic research to energy applications\u00a0<\/b>will showcase the collaborative efforts of researchers in advancing our understanding of cloud dynamics and their impact on solar radiation prediction.<\/p>\n In this webinar, you will learn about innovative methods for cloud observation and classification, as well as their applications in renewable energy forecasting. Our speakers will present recent developments in image processing, machine learning, and data integration techniques that are revolutionizing the field of atmospheric physics.<\/p>\n Mehdi Ben Slama <\/strong>from Reuniwatt will discuss the latest advancements in cloud type classification using various imaging technologies. He will present the capabilities of all-sky imagers for Atmospheric Science, and findings from Reuniwatt’s our study, \u00abLeveraging Wide-Field of View Imagers to Improve the Instantaneous Cloud Amount Estimates<\/em>\u00ab. In his presentation, he’ll propose novel approaches to estimating multi-layer cloud amounts from a single image. The presentation will also cover comparisons between IR sky imagers, ceilometers, and radiometers, highlighting the strengths and complementarities of these observation methods. Learn why ceilometer measurements often miss cloud edges or gaps in the cloud cover due to their narrow spatial constraints, while both the camera and pyrgeometer are sensitive to the entire sky dome, and more details to consider when selecting instruments for cloud observations.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n Emanuele Giovanni Carlo Ogliari <\/strong>from the Department of Energy at Politecnico di Milano will focus on the practical applications of sky imager data in the renewable energy sector, particularly for solar radiation estimation. His presentation will delve into the development of machine learning-based methods for nowcasting global horizontal irradiance 5-15 minutes ahead. He will propose a Machine Learning based method using sequences of infrared images captured by an All-Sky Imager to forecast the Global Horizontal Irradiance on different time horizon. Additionally, exogenous data, as the solar radiation measurement, is encoded in the images through an innovative technique, the Enhanced Convolutional Neural Network (ECNN). Considering the na\u00efve persistence method as a baseline, a clear improvement across the key metrics has been noted with the proposed methodology. A deeper analysis of the results reveals that the proposed models are more accurate than persistence when high fluctuations of solar radiation are experienced.<\/p>\n Prof. Stephanie Fiedler<\/strong> will welcome you and lead you through the event. We will demonstrate how these advanced cloud observation and prediction techniques contribute to more accurate solar radiation forecasts, which are crucial for the stability and efficient management of electric grids.<\/span><\/p>\n Join us for this exciting webinar to explore the latest developments in atmospheric sciences and their real-world implications. Our speakers will be available to answer your questions on cloud observation, modeling, and solar radiation prediction.<\/p>\n<\/div> Innovative methods for cloud observation and classification<\/strong> using all-sky imagers, including techniques for estimating multi-layer cloud amounts from a single image<\/span><\/p>\n<\/div><\/li> Comparisons between different instruments<\/strong>, highlighting their strengths and limitations for comprehensive cloud cover analysis<\/span><\/p>\n<\/div><\/li> Machine learning-based approaches for nowcasting<\/strong> global horizontal irradiance<\/strong> 5-15 minutes ahead<\/span><\/p>\n<\/div><\/li> How advanced cloud observation and prediction techniques contribute to more accurate solar radiation forecasts<\/strong>, crucial for managing electric grids and renewable energy systems<\/span><\/p>\n<\/div><\/li><\/ul><\/div><\/div> Prof. Stephanie Fiedler<\/strong> is Co-Director of the Institute of Environmental Physics, Universit\u00e4t Heidelberg, where she focuses on aerosol-climate interactions and atmospheric physics. She received her Ph.D. in Atmospheric Sciences from the University of Leeds and a Diplom in Meteorology from Universit\u00e4t Hannover. Prof. Fiedler has been working on aerosol forcing and its impacts on climate since 2011, with a particular emphasis on dust storms and their effects on global climate patterns. She has previously worked at other international research institutions, including the Max Planck Institute for Meteorology and GEOMAR Helmholtz-Zentrum f\u00fcr Ozeanforschung Kiel. Her research group at Universit\u00e4t Heidelberg explores interactions between atmospheric composition and dynamics across weather to climate scales.<\/span><\/p>\n Emanuele Giovanni Carlo Ogliari, PhD<\/strong> is Associate Professor at the Department of Energy, Politecnico di Milano, Italy where he teaches Electrical Engineering and Photovoltaic-based Systems Lab. He received a M.Sc., and Ph.D. in electrical engineering from the Politecnico di Milano, Italy. He has been working on photovoltaic power plant design and optimization since 2010 and Renewables expected power by means of computational intelligence techniques since 2012. He has collaborated with international universities and research centres (The University of Danang \u2013 University of Science and Technology, Ben Gurion University of the Negev and Global Energy Interconnection Research Institute Europe), in 2013 he won the joint laboratories between Italy and Israel on Solar Energy ILSE.<\/span><\/p>\n Mehdi<\/span> Ben Slama<\/strong> holds a Master\u2019s degree with honors in Applied Mathematics and Mathematical Physics from Imperial College London and an Advanced Master from ISAE-SUPAERO in Artificial Intelligence. He worked with the Space and Atmospheric Physics group of Imperial College to advance our understanding of Jupiter\u2019s Galilean Moons as a research engineer, before joining Reuniwatt in 2022 as a Research and Development Engineer, working on cloud properties retrieval from Reuniwatt\u2019s fleet of infrared and visible all-sky imagers. He ensures that measures and forecasts maintain the high-quality metrological standards demanded by our clients.<\/span><\/p>\n<\/div><\/div><\/div> Prof. Stefanie Fiedler<\/span><\/p>\n Moderator \u00a0<\/span><\/p>\n \u00a0<\/span><\/p>\n<\/div><\/div><\/div> Emanuele Ogliari, PhD<\/span><\/p>\n Speaker \u00a0<\/span><\/p>\n \u00a0<\/span><\/p>\n<\/div><\/div><\/div>After this webinar, you will have a better understanding of:<\/h3>\n<\/div><\/div><\/div>
About the speakers:<\/h3>\n<\/div>
<\/span><\/div>
\nProfessor, Directorate Institute of Environmental Physics <\/span>@Universit\u00e4t Heidelberg<\/span><\/p>\n
<\/span><\/div>
\nAssociate Professor, Department of Energy <\/span>@Politecnico di Milano<\/span><\/p>\n