Global weather models form the foundation of much of the available solar irradiance and power forecasting, and are typically sourced from publicly funded weather agencies, including the European Centre for Medium-Range Weather Forecasts (ECMWF). In late February, the ECMWF added cloud and radiation outputs to their first operational AI-driven weather model, AIFS V1, offering a new kind of forecast for solar radiation forecasting. The AIFS V1 operational release is a pivotal moment for solar energy forecasting as it is the first operational “AI model” to contain cloud cover and solar radiation parameters.
The ECMWF reports a persistent bias, but very good variance metrics. The Solcast data science team have run an early analysis of ECMWF models, including AIFS, against Solcast’s globally validated historical actuals, finding that despite the model being in the early days of development, it is already delivering excellent accuracy.
Accurate, large-scale solar radiation forecasts are crucial for grid firming, helping to balance supply and demand as solar power increases as a share of energy generation. Historically, numerical weather models have focused on temperature, wind, and precipitation, leaving solar irradiance parameters less well-developed. This model takes a totally new approach to modelling, yet is already matching industry standards for accuracy. As the tuning of this model improves, update frequency is increased, and more resources are applied to running this model, it will be fascinating to see how the industry can take advantage of this model’s faster (and cheaper) run time to deliver more accurate probabilistic and ensemble forecasts.
AIFS currently operates at a six-hour temporal resolution, coarser than IFS’s hourly output. Despite this, its deep learning architecture makes it much faster to run, meaning that as it improves it will likely become a valuable model input for rapid and short-term forecasting. This conclusion is based on the below analysis, completed by the Solcast Data Science team, comparing forecast performance of the AIFS model against two other well regarded global weather models over the several weeks since the model was published.
ECMWF’s own early evaluation highlights a tendency for AIFS to favor intermediate cloud conditions, under-representing in both clear-sky and heavily overcast scenarios. This results in solar radiation forecasts that are less active than those from IFS, leading to a more conservative estimation of irradiance. The Solcast team found the same conclusion, with good Mean Average Error (nMAE), but a negative bias. This level of performance is impressive, especially considering that AIFS is still only running at 25km resolution.
AIFS V1 remains in its early stages, with further refinements needed. Nonetheless, it represents a significant step forward in AI-based weather modelling and could complement existing numerical approaches. ECMWF’s efforts to operationalize AI-driven forecasting is an exciting evolution in meteorology, with potential long-term benefits for solar energy forecasting and grid stability. As AI-driven weather models continue to evolve, their integration into solar forecasting workflows could enhance predictability, reduce curtailment, and support the broader transition to a renewable energy future.
Solcast produces these figures by tracking clouds and aerosols at 1-2km resolution globally, using satellite data and proprietary AI/ML algorithms. This data is used to drive irradiance models, enabling Solcast to calculate irradiance at high resolution, with typical bias of less than 2%, and also cloud-tracking forecasts. This data is used by more than 350 companies managing over 300 GW of solar assets globally.
The views and opinions expressed in this article are the author’s own, and do not necessarily reflect those held by pv magazine.
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com.
By submitting this form you agree to pv magazine using your data for the purposes of publishing your comment.
Your personal data will only be disclosed or otherwise transmitted to third parties for the purposes of spam filtering or if this is necessary for technical maintenance of the website. Any other transfer to third parties will not take place unless this is justified on the basis of applicable data protection regulations or if pv magazine is legally obliged to do so.
You may revoke this consent at any time with effect for the future, in which case your personal data will be deleted immediately. Otherwise, your data will be deleted if pv magazine has processed your request or the purpose of data storage is fulfilled.
Further information on data privacy can be found in our Data Protection Policy.