Machine- and Deep-Learning Models for Wind Turbine Icing Prediction Across Multiple Horizons: The Influence of Ice Sensors and Weather Forecasts

Icing affects nearly one-fifth of the global wind energy capacity (≈220 GW) in cold climates, where individual turbines can lose up to 20% of their annual energy output. Despite growing interest in machine learning for turbine-icing prediction, previous studies have been mostly limited to SCADA data and short-term forecasts, offering little value for operational decision-making. We are the first to examine how newly available icing-sensor measurements and liquid water content (LWC) forecasts, together with AI model design, expand what is now possible in turbine-icing prediction. Using one winter (December 2023 to April 2024) of high-resolution data from a single cold-climate wind farm, including SCADA, on-site meteorological data, icing measurements and weather forecast variables, five models were benchmarked: three ensemble learners (Random Forest, XGBoost, LightGBM) and two deep-learning architectures (CNN-LSTM, GRU) across three prediction horizons (1 h, 6 h, 24 h) and four input-richness configurations. For the studied site and winter season, the results reveal a clear pattern: physically meaningful inputs, rather than network depth, dominate predictive performance. At the 1 h horizon, adding icing indicators and liquid water content improved mean F1-score from 0.78 to 0.85, reflecting the benefit of direct microphysical information. At 6 h and 24 h, incorporating forecast-based inputs produced the largest gains, increasing mean F1 from 0.70 to 0.83 and from 0.46 to 0.75, respectively. Once supplied with rich physical inputs, lightweight ensemble models matched the accuracy of deep networks—opening the door to efficient edge-AI deployment directly at turbine level. This work presents a systematic benchmarking of machine-learning and deep-learning models using combined icing-sensor and forecast-derived inputs across multiple horizons. These findings show how emerging ice sensor and forecast data now redefine the limits of AI-based icing prediction, opening new options for turbine and icing protection system control in cold climates.