Model Card
Transparency surface for the current LightGBM model, training metrics, and top features.
Live Forecast
Compares actual German renewable generation (wind + solar) against ENTSO-E day-ahead forecast and our model forecast.
Scenario Forecast
What-if analysis: adjust wind and solar capacity multipliers to see how total generation changes vs the baseline forecast.
Backtest Metrics
Evaluates forecast accuracy over the selected date range using standard error metrics (MAE, RMSE, MAPE) and compares against a naive baseline.
AI Insights
Natural-language explanations of forecast drivers and model behavior.
How it works
An honest, end-to-end view of the forecast pipeline and the planned AI explanation layer.
ENTSO-E & Open-Meteo
Ingests German wind onshore, wind offshore, solar PV, and total load from the ENTSO-E Transparency Platform, enriched with weather features from Open-Meteo.
LightGBM quantile regressors
Trains point and quantile regressors to output both a central forecast and 80% prediction intervals for every 15-minute step.
Scenario & backtest APIs
Exposes FastAPI endpoints for live forecasts, what-if capacity scenarios, and rolling backtests with MAE, RMSE, MAPE, and skill score.
AI Insights (coming soon)
A planned RAG/agentic layer will explain forecast drivers—wind ramps, solar clear-sky index, temperature effects—in plain language.
Export Data
Download raw generation data at 15-minute resolution from ENTSO-E for the selected date range.