The objective of this study is to provide reliable nowcasting (up to six hours) to short-range wind speed forecasts of up to 40 hours ahead in 10 meters height for meteorological observation sites (i.e., point forecasting). The proposed method is a data-driven approach combining artificial neural networks, ensemble learning, and feature selection techniques. Particularly, we improve a pre-defined baseline setup using meteorological features, pre-classification by forecasting intervals, as well as spatial and temporal related data. This combination of methods is the so-called ZiANN (ZAMG interval artificial neural network) and it is optimized for both nowcasting and short-range forecasts. The developed method is one of the first machine learning based wind speed forecasts for the Austrian domain and Austrian observation sites. Heterogenous data sources are combined to derive training data for ZiANN. In particular, we consider (1) observations from weather stations and (2) output of one or several numerical weather prediction models. For (1), we use data from the TAWES network in Austria, while for (2), we use the AROME, ALARO, and/or ECMWF-IFS model interpolated for the observation site location. The model is validated by two test episodes and selected sites in Austria. Forecasts are compared to alternative methods: a random forest approach, the persistence, the currently operational nowcasting system INCA, the model output statistic META, and the NWP model AROME. Our results show that ZiANN outperforms alternative models, especially in the nowcasting-range. We conclude that machine learning techniques are suitable post-processing tools, which outperform classical methodologies.

中文翻译：

---

特征选择，集成学习和人工神经网络，用于短时风速预测

这项研究的目的是为气象观测站点提供可靠的临近预报（长达六个小时），以对10米高处提前40小时的短时风速预报（即，点预报）。提出的方法是一种数据驱动的方法，结合了人工神经网络，集成学习和特征选择技术。特别是，我们使用气象功能，通过预测间隔进行预分类以及时空相关数据来改进预定义的基线设置。这种方法的组合就是所谓的ZiANN（ZAMG间隔人工神经网络），并且已针对临近预报和短期预报进行了优化。所开发的方法是针对奥地利领域和奥地利观测站点的首批基于机器学习的风速预测之一。异构数据源被组合以导出ZiANN的训练数据。特别是，我们考虑（1）来自气象站的观测结果和（2）一个或几个数值天气预报模型的输出。对于（1），我们使用来自奥地利TAWES网络的数据，而对于（2），我们使用为观测站点位置插值的AROME，ALARO和/或ECMWF-IFS模型。该模型通过两次测试和在奥地利的选定地点进行了验证。将预测与其他方法进行比较：随机森林方法，持久性，当前运行的临近预报系统INCA，模型输出统计值META和NWP模型AROME。我们的结果表明ZiANN的性能优于其他模型，尤其是在临近预报范围内。我们得出结论，机器学习技术是合适的后处理工具，