With the ever-increasing share of Variable Renewable Energy (VRE) sources in the European energy mix, mitigating larger production forecast errors becomes increasingly challenging. In the long term, adequate reserves need to be planned and allocated accordingly to ensure grid stability. Therefore, accurately modeling weather-driven forecast uncertainties for renewable generation over long periods provides valuable insights for power system planning, market price projection, and adequacy assessment in Europe. Traditional long-term studies often rely on stochastic approaches to simulate forecast errors, which may not fully capture the underlying weather-driven spatiotemporal dependencies. Yet, simulating weather forecasts over long periods has become more accessible with the recent rise of AI-driven weather models in comparison to traditional approaches. This paper develops a methodology based on the Artificial Intelligence Forecasting System (AIFS) to simulate VRE day-ahead generation forecasts. Coupled with a methodology to convert weather variables into power generation (CorRES), wind forecast errors are simulated over multiple years from AIFS and aggregated at regional and country levels for Belgium and the Netherlands. Results are validated against observed forecast errors and compared to a previously established stochastic simulation approach for Belgium.