Example Dataset for ML training code

AI4Wind Machine Learning Training Data and Example Turbine Data Set: This dataset is published as part of the AI4Wind research project, which develops open-source tools for wind energy analysis and power production estimation under current and future climate scenarios in Austria. It provides the machine learning training data and example turbine data needed to run two AI4Wind software packages. https://github.com/4wardEnergyResearch/AI4Wind_ML_PP_Model_data_cleaning - ml_training_data.parquet — Training data for the ML-based turbine selector, which predicts the best-performing turbine for a site from its wind distribution parameters. https://github.com/4wardEnergyResearch/AI4Wind_Toolkit_public - datenbank.db — SQLite database with example turbine metadata (coordinates, hub height, rated power), the manufacturer power curve, and tuned data-cleaning parameters. - 20250401_20250407_10_min_data_V90_105m: Example raw SCADA measurement data (CSV), 10-minute turbine measurements (timestamp, power, wind speed, and optionally temperature, wind direction, nacelle position) for the example turbine. Funding Developed within the AI4Wind research project, funded under the "AI for Green" Call 2021 by the Austrian Federal Ministry for Innovation, Mobility and Infrastructure (BMIMI), administered by the Austrian Research Promotion Agency (FFG). License Recommended: CC-BY-4.0 (a data license — note the software repositories themselves are GPL-3.0). Contact 4wardEnergy Research GmbH