Data scientist
Florian Ghionda is a Data Scientist at CalibSun, where he drives the continuous development of the solar forecasting algorithm, NEXT. He holds an engineering degree from ISAE-Supaero and completed environmental impact studies at the University of La Plata, equipping him with a strong background in satellite Earth observation and environmental engineering. Florian applies data science to address the climate targets of the Paris Agreement, focusing on geostationary satellite imagery processing, time-series analysis, and short-term solar irradiance modeling.
Florian manages the operational data pipelines for global satellite constellations, including MSG, MTG, GOES, Himawari, and INSAT, to optimize real-time data ingestion and minimize forecast latency. He also performs statistical quality control on historical sensor and data logger time-series during customer onboarding to maintain high input data standards.
Florian’s research includes feature selection studies presented at ICEM 2025 in Padova, as well as the implementation of Cloud Motion Vector models that cut image-processing delays. Additionally, he engineered a specialized deep learning architecture to accurately predict solar generation during the Indian monsoon, delivering top-tier performance for utility-scale solar operators.
CalibSun was created in 2023 by Nicolas Thévenin and Sébastien Pitaval, the founders of Solaïs, a company that has been an expert in photovoltaics for more than 18 years and a world leader in glare studies.
