Accurate wind speed forecasting is a fundamental requirement for advanced and economically viable large-scale wind power integration. The hybridization of the quaternion-valued neural networks and stationary wavelet transform has not been proposed before. In this paper, we propose a novel wind-speed forecasting model that combines the stationary wavelet transform with quaternion-valued neural networks. The proposed forecasting model represents wavelet subbands in quaternion vectors, which avoid separating the naturally correlated subbands. The forecasting model consists of three main steps. In the first step, the wind speed signal is decomposed using the stationary wavelet transform into sublevels. In the second step, a quaternion-valued neural network is used to forecast wind speed components in the stationary wavelet domain. Finally, the inverse stationary wavelet transform is applied to estimate the predicted wind speed. In addition, a softplus quaternion variant of the RMSProp learning algorithm is developed and used to improve the performance and convergence speed of the proposed model. The proposed model is tested on wind speed data collected from different sites in China and the United States, and the results demonstrate that it consistently outperforms similar models based on real-valued neural networks, complex-valued neural networks, or LSTM units. In the meteorological terminal aviation routine (METAR) dataset experiment, the proposed wind speed forecasting model reduces the mean absolute error, and root mean squared error of predicted wind speed values by 26.5% and 33%, respectively, in comparison to a number of existing approaches INDEX TERMS Wind Speed Forecasting, Stationary Wavelet Transform, Quaternion Valued Neural Network, RMSProp learning algorithm.