AI summaryⓘ
The authors developed WindCastNet, a new way to predict short-term offshore wind speeds using satellite radar data from multiple countries. Unlike traditional weather models that work best over longer times, WindCastNet focuses on the next few hours, making use of irregular and sparse satellite observations. It uses a special type of neural network that can handle missing data and forecast wind speed and direction more accurately than some existing models. Their tests over the North Sea show improved accuracy, especially in calm conditions, suggesting satellites can be a useful tool for quickly forecasting offshore wind and marine weather. However, its performance drops somewhat in strong or uneven wind situations.
offshore wind forecastingsatellite scatterometernowcastingnumerical weather predictionpartial convolutional LSTMroot-mean-square errorwind speed predictionspatiotemporal datamarine weatherHARMONIE MEPS
Authors
Francesco Pinto, Luca Lanzilao, Paco Lopez Dekker, Angela Meyer
Abstract
Accurate intraday forecasts of offshore wind are becoming increasingly important for power system operation and the integration of growing shares of offshore wind energy. Operational forecasts rely predominantly on numerical weather prediction (NWP), which is not optimized for lead times of minutes to hours, where initial-condition accuracy dominates forecast skill. Although satellite scatterometer observations are routinely assimilated into NWP, they have not previously been used directly for forecasting. Here we present WindCastNet, the first satellite-based nowcasting framework for offshore wind speed and direction, introducing a new paradigm for intraday forecasting that learns from spatiotemporally irregular satellite observations. WindCastNet predicts offshore wind fields from observations acquired by satellite scatterometer constellations. WindCastNet employs a partial convolutional long short-term memory network that exploits microwave radar observations from the European, Chinese, and Indian scatterometers despite their irregular spatial coverage, asynchronous sampling, and variable revisit times. Spatial observation masks and inter-observation intervals are encoded, while a continuous temporal representation enables forecasts at arbitrary lead times. Evaluated over the North Sea, WindCastNet reduces the root-mean-square error by 23% and 7% relative to the HARMONIE MEPS model at lead times of 1 and 2 h, respectively, and outperforms persistence by 9-15% during the first three forecast hours. Forecast skill decreases under strong-wind conditions and spatially non-uniform flow. These results demonstrate that satellite scatterometer constellations can provide an independent and competitive source of short-term offshore wind forecasts, opening new opportunities for renewable energy forecasting but also broader marine weather applications, including tropical cyclone nowcasting.