Cyril Voyant
Solar forecasting · Frugal AI
Embedded Files
I am a physicist and Research Director at Mines Paris–PSL, within the Centre Observation, Impacts, Énergie (O.I.E.), and Visiting Professor at the University of Kragujevac, Serbia. My work connects solar and photovoltaic forecasting, time series and frugal AI. My background also includes medical physics.
Can we know how predictable the sky is? When does a simple model beat a complex one? Which forecast errors matter in practice? Here I explain the results behind these questions, with the papers and code that support them.
Research news · Academic profile · Methods and code
Research stories
Research stories
How forecastable is the sun?
Separating cloud-driven variability from the daily solar cycle: the sCV and forecastability indices, evaluated at 68 stations.
A better persistence forecast, without training a model
BLEND uses the recurring statistical structure of energy signals to improve a simple reference forecast.
When a displaced forecast is still useful
The γ-index evaluates spatial, temporal and intensity agreement within explicit tolerances.
Also explore multi-output energy forecasting with ELM and NICE: measuring improvement over persistence.
Watch and learn
Watch and learn
Watch: Research Excellence in 2026
My talk on making research discoverable, verifiable and useful. Talk summary, references and preprint.
Solar forecasting: my course at Mines Paris–PSL
The UE14 course connects solar variability, time-series models, evaluation and frugal forecasting.
Full academic CV · Research projects · Google Scholar
Background
Background
I trained in fundamental physics, qualified as a medical physicist in 2003, and completed my PhD on solar radiation time series in 2011. I pursued energy research alongside clinical work before joining Mines Paris–PSL as Research Director in 2024.
My experience in radiotherapy and measurement informs how I approach uncertainty, model evaluation and scientific software. Read my academic CV.
Current Research
Current Research
I study solar variability and forecastability, parsimonious time-series models and the evaluation of forecasts against meaningful baselines. Applications include joint energy-demand and generation forecasting, storage and microgrid operation. My medical-physics research addresses dose equivalence and modelling.
Recent first-author papers introduce the sCV and forecastability indices, develop BLEND forecasting, and examine tolerance-based validation with the γ-index.
Research themes and project portfolio · Implementation guides and code
Research Projects
Research Projects
My current collaborative work includes Fine4Cast (2023–2028), the ELECTRE programme, and the Mines Paris–PSL / University of Corsica / CNRS research agreement (2024–2027). These activities connect forecasting, AI and energy management.
Earlier work includes SAPHIR, HyLES, INTELPOLY and the TILOS island demonstrator. Explore the research themes and project portfolio.
Recognition and Service
Recognition and Service
I serve as Associate Editor of Scientific Reports and on the Sustainability Energy Sustainability editorial board. I also contribute to research evaluation, doctoral supervision and the ETIP PV working group on Digital PV, Grid and Storage.
Selected distinctions include the PVSEC Award (Hamburg, 2009) and the City of Nice Prize (2012). Appointments, service and career.
External profiles
External profiles
I maintain several academic profiles across platforms to enhance research visibility, ensure citation accuracy, and facilitate open-access dissemination
Google Scholar · ORCID · Zenodo · IDRef · LinkedIn
Page updated
Google Sites
Report abuse