EUMETNET - E-TREND Joint Workshop on Postprocessing, Forecasting and Nowcasting for Renewable Energy (RenEUCast)

Dec 8, 2025, 8:00 AM → Dec 10, 2025, 5:30 PM Europe/Brussels

U-Residence (Vrije Universiteit Brussels (VUB))

Dear RenEUCast25 attendees,

We thank you again for your participation which has made this workshop a resounding success, gathering more than 50 participants from both the weather forecasting community and the renewable energy sector. 30 high-quality contributions were presented, organized in 6 different sessions, including 5 keynote presentations. In addition, the event was streamed online with more than 20 additional participants.

EUMETNET will gladly welcome you again for the next ENWFC26 workshop in Copenhagen in May 2026. Until then, have a pleasant winter break and a happy new year.

Sincerely,

The organizing committee.

 

 

The joint EUMETNET - E-TREND RenEUCast workshop in December 2025 was a dedicated event for the exchange of experiences across different fields and backgrounds, all focused on effective forecasting for the renewable energy sector.

The ultimate objective of this event was to provide useful forecasts and nowcasts to European renewable energy stakeholders, many of whom were invited, and to foster better understanding of how end users make use of forecasts and nowcasts in their decision making.

 

This event was supported and funded by the SNC European Meteorological Network (EUMETNET) and the Belgian Science Policy office (Belspo). A huge thanks to both organizations.

 

 

program-reneucast25.pdf

Monday, December 8

8:30 AM Welcome & Setup

1 Welcome address

Speakers: Prof. Lesley De Cruz (RMI - VUB), Jonathan Demaeyer (Royal Meteorological Institute of Belgium), Joris Van den Bergh (Royal Meteorological Institute of Belgium), Stéphane Vannitsem (Royal Meteorological Institute of Belgium), Irene Schicker (GeoSphere Austria)

Operational forecasting application

Convener: Jonathan Demaeyer (Royal Meteorological Institute of Belgium)

2 Forecasting at a Transmission System Operator: applications & challenges within TenneT

Running a high-voltage transmission grid is work in the shadows: it rarely goes wrong. Yet, a lot of challenges are faced every day. Reliable forecasting is at the heart of this challenge. A good understanding of weather will lead to better forecasts, yet the landscape is changing fast. Having accurate solar and wind forecasts is not enough; better insights in market dynamics and new technological developments are on the horizon. Within this keynote an overview will be given in the developments we have faced over the last few years, and the challenges we will face for the next few years.

Speaker: Wouter Tromp (TenneT)

3 Renewable energy forecasting at the Royal Meteorological Institute of Belgium

In recent years, the Royal Meteorological Institute of Belgium (RMI) has positioned itself strongly in the field of renewable energy forecasting and its applications. This was made possible by leveraging scientific collaboration within various projects. In this presentation, we give an overview of applications such as the RMI Storm Forecast Tool developed for the Belgian TSO (Elia), and research and development performed in the context of the projects E-TREND (funded by Belspo), BeFORECAST, InStaFlex and STORM (FOD Economy through the Energy Transition Fund), renewable energy impact models within Destination Earth (ECMWF), and the Destination Earth Pilot Service on Dynamic Line Rating (ECMWF). We present the main results, ongoing work, and future plans within these projects.

Speaker: Joris Van den Bergh (Royal Meteorological Institute Belgium)

4 Current Status of Numerical Weather Prediction

Over more than half a century, Numerical Weather Prediction (NWP) has achieved remarkable progress. This advancement results from the use of increasingly dense observational data types, progress in high-performance computing, and steady improvements in numerical modeling. This long-standing progress faces new challenges, with standard technologies approaching their physical limits, and models reaching resolutions where global high-resolution datasets are lacking.

To address these challenges a threefold strategy is being pursued. Limited-area models are being used to further increase resolution toward the hectometric scale. Existing models are being refactored to enhance their flexibility and efficiency on emerging computing architectures. Machine learning techniques are being integrated with traditional numerical approaches to develop Machine-Learning NWP.

This talk will explore these three directions, highlighting their implementation within major international initiatives.

Speaker: Piet Termonia (Royal Meteorological Institute of Belgium)

11:10 AM Coffee break

5 From Extreme Weather Detection to Energy Forecasts: The On-Demand Extremes Digital Twin Renewables Model

The on-demand Extremes Digital Twin Renewables models, developed by the Destination Earth team, provide a configurable workflow linking the detection of adverse weather, hectometric and sub-hourly NWP simulations, and impact models for wind and solar energy. Targeted forecasts of renewable energy production under extreme conditions are generated through dynamic triggering based on meteorological detection algorithms. For wind and solar energy, post-processing combines NWP data (including a wind-farm parametrization) with machine-learning methods to refine the power output predictions, while satellite-driven nowcasting of global radiation complements the forecasts. Together, these components enhance the forecasting precision, uncertainty quantification, and user-tailored information to support grid operators, TSOs, DSOs, and energy traders in operational decision-making during extreme events.

Speaker: Kristian Pagh Nielsen (DMI)

6 Evaluating the Prediction of Wind Power Ramping Events in the Belgian Offshore Zone

We present evaluations for the prediction of wind power ramping events in the Belgian Offshore Zone. We verify two models from Royal Meteorological Institute of Belgium: the operational ALARO-4km and its version with Wind Farm Parameterization (WFP). Power predictions are generated with power curves and machine learning (ML). As standard metrics like MAE are insufficient for evaluating ramps, our proposed framework incorporates time and power buffers for a flexible assessment by tolerating minor errors. Results show that WFP models improve ramping prediction skill, with ML achieving more balanced forecasts between reducing misses and false alarms. We also introduce a Ramp Alignment Score to quantify temporal errors by forecast lead time and confirm the averaged smaller timing errors of WFP models. Finally, the framework helps to understand that severe precipitation is a strong indicator of large, predictable ramps, while lighter precipitation is associated with more forecast errors.

Speaker: Ruoke Meng (Royal Meteorological Institute of Belgium)

12:40 PM Lunch break

Operation & Decision-making

Convener: Joris Van den Bergh (Royal Meteorological Institute of Belgium)

7 Forecasting Belgium’s Solar Future: Climate Change Impact on PV Energy Output

This study investigates how climate change could affect the energy output of solar panels in Belgium, with projections extending to the year 2100. It offers a long-term perspective by starting with weather data from 1950 and building on future climate models developed by the Royal Meteorological Institute (RMI). By analysing multiple climate scenarios, the study examines potential shifts in photovoltaic (PV) system performance over time.

The methodological framework is based on a bottom-up, multi-physics energy yield model developed by imec. This advanced model uses a wide range of weather variables to produce a clear and realistic estimate of how solar panels perform under different climate conditions.

Speaker: Mr Richard de Jong (imec)

8 HireNext: HIgh Resolution forecasts for Next Generation Dynamic Line Rating computation

The HIRENEXT project aims to co-design and implement a Pilot Service tailored to dynamic line rating (DLR) computations for electricity transmission. This service leverages innovative research from the Destination Earth On-Demand Extremes Digital Twin contract (DE_330), which provides access to unprecedented high-resolution weather predictions.

Through a user-centric co-design approach, conducted in close collaboration with a Transmission System Operator (TSO), the project seeks to demonstrate how accurate, high-resolution weather data can be operationalized to enhance overhead line ratings—both in real-time grid operations and long-term planning. By focusing on demonstrable outcomes and clear communication of expected benefits, the contract is positioned to showcase the tangible value of DestinE services, thereby driving significant user engagement and adoption of the Destination Earth (DestinE) platform.

Speaker: Tomas Van Oyen (PropheSea B.V.)

2:30 PM Coffee break

9 Identifying hotspots of adverse weather for Austrian energy infrastructure

EnergyProtect aims to identify present and future risk hotspots, defined as sites of renewable energy infrastructure with elevated exposure to potentially disruptive meteorological conditions. We i) use physics-informed ML to detect patterns of adverse weather, ii) dynamically downscale ensemble time slices to convection permitting resolutions, and iii) estimate uncertainties, return periods and changes in intensity. These datasets are then overlaid with renewable energy infrastructure to identify current and future risk hotspots. We present preliminary results for different severity levels of wind speed ramping and high wind events, that have potential to cause turbine cut-outs, reduced efficiency, or grid balance destabilization. We map the average annual occurrence of such risk events using multiple meteorological datasets (hourly, 1–30 km resolution), thereby identifying key hotspots in Austria and quantifying related uncertainties.

Speaker: Dr Irene Schicker (GeoSphere Austria)

10 Machine-learning informed stochastic control of a hybrid wind-battery plant operating under time-dependent grid constraints

Offshore wind farms play an important role in the transition toward carbon-free energy production, but their variable and uncertain power output, depending on the wind conditions, presents significant operational challenges. To mitigate fluctuations in the grid, transmission system operators and regulatory authorities may impose various constraints on the power injection into the grid. Complying with these requirements may necessitate the integration of a battery energy storage system (BESS) together with advanced supervisory control.

In this talk, a stochastic control strategy is presented for a hybrid wind-battery plant operating under time-dependent grid constraints, motivated by a real-world use case. The proposed approach maximizes the economic value of the plant, while ensuring compliance with both operational limitations and grid constraints. It is demonstrated that combining machine-learning-based wind farm power forecasts with a stochastic model predictive control (SMPC) framework can substantially improve the profitability of the hybrid renewable energy plant.

Speaker: Stijn Ally (VUB)

11 Renewable forecasts as an enabler for Elia's operations

Elia Transmission Belgium operates a grid with a high penetration of PV-production capacity, offshore wind parks, DC cables and a particular geographical position, between the biggest consumers of the European grid – Germany and France. The exploitation happens parallel to one of the most challenging infrastructure portfolios in the whole of Europe, implying many outages happening at any given time.
The first topic is the use of forecasts in the congestion management domain. Elia has designed several processes to balance the need of outages while limiting the impact on the market. In these processes, a particular role is played by the renewable forecasts.
In a second part, Predico will be highlighted, an innovative platform designed by the Elia Group Innovation Department, that aims at improving the forecast Elia uses internally and publishes as well. It lowers the entry barriers for forecasting companies and drives innovation, by rewarding forecasters based on their performance.

Speaker: FREDERIK VANMAELE

5:00 PM Ice Breaker

Tuesday, December 9

Postprocessing

Convener: Sebastian Lerch (University of Marburg, Germany)

12 User-Informed Post-Processing: Designing Around Decision-making Requirements

As the Met Office retires legacy deterministic data feeds and moves towards ensemble forecasting, a challenge arises in maintaining delivery of spot forecast products, including those supporting renewable energy applications. Rather than replicating existing data feeds, a new project is taking a fresh approach to understand requirements. Starting with plain-English questions to understand how each product supports decision-making and what behaviour it aims to capture, key scientific characteristics (such as inter-parameter consistency, temporal consistency, and accuracy metrics) were identified. These characteristics inform the design of modular post-processing components, which will be deployed in cloud-based pipelines to deliver forecasts tailored to user needs. This method enables more flexible, purposeful forecasting and supports the transition to modern, scalable systems. Examples will be presented to illustrate the approach and its benefits.

Speaker: Alice Lake (Met Office (UK))

13 Probabilistic forecasting of spatially aggregated wind power production using Bernstein Quantile Networks.

Accurate forecasts of regional wind power production are crucial for power system operation and planning. Total generation in the coming hours and days depends strongly on both weather forecasts and time-varying production capacity. We propose a probabilistic forecasting approach based on Bernstein Quantile Networks (BQN) to predict aggregated power production from multiple wind farms without access to individual farm data.

The model uses ensemble forecasts of several meteorological variables at each wind farm, combined with time-dependent capacity information. Its architecture exploits the structured input through (i) learnable wind farm embeddings, (ii) mappings to power output, (iii) spatial aggregation across farms, and (iv) permutation-invariant layers capturing distributional features. The BQN framework produces full predictive distributions via quantile functions represented by Bernstein polynomials.

Speaker: John Bjørnar Bremnes (Norwegian Meteorological Institute)

10:20 AM Coffee break

14 The Zero Degree of Freedom Non-Central Chi Squared Distribution for Postprocessing of Precipitation Forecasts

In this work we introduce and investigate the zero degree of freedom non-central Chi Squared distribution for ensemble postprocessing. It has a point mass at zero by definition and is thus particularly suited for postprocessing weather variables naturally exhibiting large numbers of zeros, such as precipitation, solar radiation or lightnings. Due to the properties of the distribution, no additional truncation or censoring is required to obtain a positive probability at zero. The presented study investigates its performance compared to that of the censored generalized extreme value distribution (GEV0) and the censored and shifted gamma distribution (CSG0) for postprocessing 24h accumulated precipitation at 31 stations in Germany using an Ensemble Model Output Statistics (EMOS) approach with a rolling training period. The case study shows that the Chi Squared distribution is highly competitive to state-of-the-art distributions, specifically when predicting extreme precipitation events.

Speaker: Annette Möller

15 ENTSO-E API Python Package: Streamlining Access to European Electricity Market Data

The ENTSO-E Transparency Platform provides comprehensive European electricity market data essential for renewable energy forecasting and operations. We present entsoe-apy, an open-source Python library enabling access to all ENTSO-E RESTful API endpoints with seamless data retrieval.

The package features automatic request splitting for large queries, intelligent retries, and consistent error handling. Its structure mirrors the official API documentation, making it intuitive for users.

Built on Pydantic models, entsoe-apy offers type-safe, validated data structures with runtime checks, improving reliability. The library preserves complete API responses while providing flexible outputs: users can extract data as JSON or pandas DataFrames.

Designed for operational and research use, entsoe-apy enables stakeholders to efficiently integrate ENTSO-E data into forecasting models, validate predictions, and support data-driven decisions for improved renewable energy integration across Europe.

Speaker: Dr Jonathan Berrisch (University of Duisburg-Essen, House of Energy, Climate & Finance)

16 Joint lead time precipitation forecast post-processing using deep generative models

Accurate weather forecasting plays an increasingly important role in today's society, with implications in hydrological modelling, renewable energy production, and civil service operations. To improve the reliability of ensemble weather forecasts, post-processing of said forecasts is frequently employed. However, many variables of interest, such as precipitation or wind speed, exhibit highly skewed distributions, making them challenging to model.

We investigate the application of normalizing flows and flow matching to facilitate skewed distribution modelling, focusing on precipitation forecast post-processing. We show that both methods improve the reliability of the underlying forecast while post-processing the entire lead time at once, jointly.

Speaker: Peter Mlakar (Slovenian Environment Agency)

12:30 PM Lunch break

Nowcasting

Convener: Irene Schicker (GeoSphere Austria)

17 Adaptive Bayesian Nowcasting of Wind Power Based on the Generalised Logit Transformation

Wind power central to the energy transition, yet its variability challenges accurate forecasting. This work introduces an adaptive nowcasting method for probabilistic forecasting method combining the generalised logit transformation with a Bayesian framework. The transformation maps double-bounded wind power data to an unbounded domain, enabling Bayesian inference, while an adaptive mechanism updates the shape parameter using representative samples. Four adaptive methods are compared in a case study of over 100 wind farms in Great Britain over four years, focusing on one-step-ahead 30-minute forecasts. Performance is assessed with the Continuous Ranked Probability Score and functional reliability diagrams. Results show the proposed Bayesian method consistently improves forecast accuracy and reliability, supporting robust grid integration and decision-making.

Speaker: Tao SHEN (University of Glasgow)

18 RUSH: Seamless Shift from Obs Extrapolation to AIFS Guidance

RUSH (Rapid Update Short-term High-resolution) is an AI-native, rapid-update nowcasting framework that turns heterogeneous inputs into probabilistic 0–24 h forecasts at 30-min steps on a 1-km grid over Belgium. Methodologically, RUSH couples two ingredients: (i) observation-led evolution learned from 30-min radar accumulations and 15-min SEVIRI channels, and (ii) large-scale dynamical context from ECMWF’s AIFS. A latent-diffusion sequence-to-sequence model performs conditioning and super-resolution in latent space, avoiding manual blending and enabling seamless transition from nowcasting to short-range guidance. The system is designed for fast cycling as new observations arrive and exposes uncertainty via ensembles. We will present the framework design, training/ingestion pipeline and provide an update on current work which now includes longer forecast times and large-scale predictions downscaling.

Speaker: Simon De Kock (Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, Belgium. Royal Meteorological Institute, Brussels, Belgium)

2:50 PM Coffee break

3:20 PM User requirements for nowcasting, forecasting, and observations

19 Panel discussion

Speaker: Jonathan Demaeyer (Royal Meteorological Institute of Belgium)

6:30 PM Workshop social dinner

https://www.fox.brussels/en/

Wednesday, December 10

Wind energy application

Convener: Hossein Tabari (RMI / UAntwerpen)

20 Modeling the impact of gigawatt-scale offshore wind farm clusters on regional wind and weather conditions

With offshore wind farms increasing in size and number, their interaction with regional wind and weather patterns plays an increasingly important role. Wind turbines extract energy from the boundary layer, resulting in downstream wakes with reduced wind speeds. When clustering many turbines together, wakes coalesce and can persist for tens of kilometers, affecting neighboring farms and regional conditions.

We study the impact of a gigawatt-scale cluster on regional weather using multi-year high-resolution mesoscale simulations. We focus on the Belgian–Dutch cluster, the largest offshore cluster to date with an installed capacity of over 3.7 GW. Modeled wake effects are validated against lidar and satellite data, and potential impacts on precipitation and sea surface waves are explored. This work provides a first long-duration assessment of the accuracy of this setup, paving the way for broader use of mesoscale wind farm parameterizations in different phases of wind farm projects.

Speaker: Wim Munters (von Karman Institute for Fluid Dynamics)

21 Day-ahead wind power forecasting with gradient boosting trees

Accurate day-ahead wind power forecasts are essential for wind farm operation strategies and grid capacity planning. This presentation demonstrates probabilistic day-ahead wind power forecasting using gradient boosting trees. We compare three probabilistic prediction methods - conformalised quantile regression, natural gradient boosting and conditional diffusion models - combined with tree-based machine learning. Validated with four years of data from all wind farms in the Belgian offshore zone, we find that these methods outperform deterministic engineering approaches (power curve or analytical wake model), with an improved point forecast accuracy of around 3.7 % of installed capacity compared to the analytical wake model. Considering the three probabilistic prediction methods, the conditional diffusion model is found to yield the best overall probabilistic and point estimate of wind power generation.

Speaker: Max Bruninx (Vrije Universiteit Brussel)

22 Development of a multi-layer atmospheric perturbation model

Recent research has pointed out that wind farms can interact with the atmosphere at scales much larger than the turbine size. Although these large-scale effects are significant, they cannot be captured by the widely used engineering wake models. To bridge this gap, Allaerts & Meyers [1] developed an Atmospheric Perturbation Model (APM) that accounts for both turbine-scale and mesoscale effects on power predictions. The original model represents the atmospheric boundary layer as two sub-layers topped by the free atmosphere. This work aims to generalize the APM to a user-defined number of sub-layers, and to inform a simple physics-based procedure to define them. Preliminary results have shown that the improved model allows to study a wider range of atmospheric conditions. The current focus is placed on testing the performance of the model for realistic conditions provided by RMI (ECMWF data of the Belgian offshore zone).

[1] Allaerts & Meyers 2019, J. Fluid. Mech vol 862

Speaker: Theo Delvaux (KU Leuven)

10:40 AM Coffee break

23 Advancing Wind Power Forecasting with AI Weather Models

AI-driven Weather Prediction Models (AIWPMs) are revolutionizing weather forecasting and surpassing traditional numerical weather models in both accuracy and computational efficiency. With weather conditions impacting numerous sectors, such as renewable energy generation, this has far-reaching implications. AIWPMs could enable improved forecasts for renewable energy generation, such as wind power, ensuring that appropriate actions are taken to maintain grid stability and cope with volatile generation. Traditionally, such renewable energy forecasts have been generated with separate models in a model-chain approach, considering weather predictions as important inputs. We explore novel strategies for utilizing AIWPMs for wind energy prediction, including parameter-efficient fine-tuning methods, which have been successfully employed to adapt large models to new tasks without excessive computational cost in the machine learning community.

Speaker: Sebastian Lerch (University of Marburg, Germany)

24 Adapting Machine Learning Weather Forecasting Architectures for Wind Power Prediction

This study investigates the application of Encoder–Processor–Decoder architectures, which have been successfully employed in large machine learning–based weather forecasting models, for wind power prediction. Using the Anemoi framework from the European Centre for Medium-Range Weather Forecasts (ECMWF), we evaluate graph-based neural networks over a domain covering Belgium and the Belgian Offshore Zone (BOZ) with a forecast horizon of up to 48 hours. These models are trained to forecast key meteorological variables, including wind speed, wind direction, and temperature, derived from the Copernicus Regional Reanalysis for Europe (CERRA). Wind power is treated as a diagnostic variable, and verification is performed using publicly available production data from the European Network of Transmission System Operators for Electricity (ENTSO-E). We assess how both input feature selection and network architecture affect prediction accuracy.

Speaker: Aaron Van Poecke (University of Antwerp)

25 A fast blockage-correction model for wind-farm power calculation

As offshore wind-farms grow in size, atmospheric gravity waves and blockage can affect their operation and performance [1]. Since conventional wake models cannot capture these effects on their own, they need to be coupled to other models that simulate the mesoscale interaction between wind farms and the atmosphere. However, this raises the computational cost of the wake model by several orders of magnitude.

To address this, we present a new method of speeding up the coupling with an atmospheric perturbation model [2]. The resulting combined model can calculate farm power output in just a few seconds per case, and has been validated using prior LES results [1]. Furthermore, we will show how the combined model can be used for estimating annual losses due to flow blockage, and compare its predictions against operational data from the Belgian-Dutch offshore wind cluster.

[1] Lanzilao & Meyers 2024, J. Fluid Mech., vol 979
[2] Devesse et al. 2024, J. of Physics: Conf. Series, vol 2767

Speaker: Koen Devesse (KU Leuven)

26 Wind Energy Ramp Events: On the meteorological events causing sudden changes in wind energy generation

This study investigates the meteorological drivers responsible for sudden wind power fluctuations (ramps) at the Belgian offshore wind farm cluster. These ramps can cause grid management challenges.
Using power generation and meteorological data, 221 unique ramps are identified across 154 days in 4 years time. Each ramp is manually linked to synoptic conditions via a custom dashboard integrating weather charts and power data. Ramp types are categorised into slow-large ($\geq$1000 Mw in $\leq$60 min), fast-small ($\geq$500 Mw in $\leq$15 min) and fast-large ramps (both criteria).
Most events (171) can be associated to synoptic scale events, which might suggest that the Belgian cluster is somewhat insensitive to mesoscale features (often fast ramps).
To explore this further, ramp extraction (with scaled thresholds) of hypothetical sub-clusters shows that larger clusters ramp less frequently, but when they do, the events are more severe (larger and longer).

Speaker: Vaughan Jones

12:40 PM Lunch break

PV energy application

Convener: Prof. Lesley De Cruz (RMI - VUB)

27 Satellite-based Solar Energy Nowcasting across Europe

Solar energy forms an important pillar of climate change mitigation. Short-term forecasts of surface solar irradiance (SSI) are gaining more importance for power grid operators seeking to balance supply and demand in a secure and economical way. Regional-scale SSI forecasts are essential since most solar power is provided by decentralized PV plants. Solar nowcast models offer SSI predictions at forecast lead times of minutes to hours. I will provide an introduction to spatiotemporal forecasting of solar energy as applicable across Europe and other global regions and will introduce the first two regional-scale solar nowcast models, SolarSTEPS and SHADECast, which provide probabilistic satellite-based solar forecasts for minutes to hours, enabling uncertainty quantification for regions of dozens to thousands of kilometers in size. I will also present a first intercomparison of probabilistic solar forecast models and how they perform for national-scale PV forecasting.

Speaker: Angela Meyer (BFH, TU Delft)

28 Practice on forecasting wind and solar power

Post-processing methods are implemented at wind/solar farm for the power forecast. We propose two forecasting frameworks based on EMOS and neural network (NN). Boosting technique is applied for selection of the variables in the EMOS approach. The NN approach uses a multilayer perceptron model, where the training process is specifically tailored to the limited dataset size of one year by utilizing a similarity-based custom validation set. The power forecasts are customer-oriented evaluated, and compared with the commercialized product. The results will be shown at the workshop.

Speaker: Yong Wang (Nanjing University of Information Science and Technology)

29 Translating Weather Forecasts into Actionable Flexibility: The Meteorological Core of EngagePrivFlex

Increasing shares of distributed PV generation plus increased wind energy being fed into the grid challenge local grids through rising variability and peak loads, requiring accurate, high-resolution forecasts for grid flexibility. EngagePrivFlex addresses this by exploring how private households can provide flexible generation & consumption to support grid stability. The meteorological component develops post-processing and ML tools to improve weather-driven forecasts for PV and wind energy production &flexibility planning. This is done using ensemble calibration, site-specific temporal disaggregation, and conversion to per-substation aggregated power production predictions to represent local variability relevant for demand response. Meteo-forecasts are coupled with grid and consumption data to predict short-term flexibility potential, demonstrating how tailored post-processing and AI methods can translate NWP outputs into insights for smart-grid operation and renewable integration.

Speaker: Irene Schicker (GeoSphere Austria)

30 Concluding remarks

Speakers: Prof. Lesley De Cruz (RMI - VUB), Jonathan Demaeyer (Royal Meteorological Institute of Belgium), Joris Van den Bergh (Royal Meteorological Institute of Belgium), Stéphane Vannitsem (Royal Meteorological Institute of Belgium), Irene Schicker (GeoSphere Austria)