A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data

Abstract

With the development of computer technology and expanding environmental issues, machine learning has received more and more attention in the field of weather forecasting. Global Navigation Satellite System-Radio Occultation(GNSS-RO) technology is a kind of remote sensing technology. This investigation proposes an alternative to numerical weather forecasting model. The new method is based on machine learning utilizing GNSS-RO data to forecast the wind field in the Beijing-Tianjin-Hebei region of China. The dataset including temperature, humidity， pressure， wind speed and direction was obtained by numerical calculation in terms of historical monitoring data in Beijing-Tianjin-Hebei region. Then the models of wind fields forecasting based on machine learning were established with different neural network including Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Deep Neural Networks (DNN). The prediction performance of different models was analyzed. The results demonstrate that LSTM and CNN have better performance on predicting the wind field than Deep Neural Networks. The wind speed error is about 1.4m/s, and the wind direction error is about 30°. Moreover, the time required for neural network to predict a new sample is about 1 second, which is only 0.2% of the prediction time compared with numerical model. Finally, the machine learning model can be used to predict the wind field effectively, with GNSS-RO data as the input in application. This paper pro-vides a new method in sight to use machine learning to forecast the regional wind field utilizing GNSS-RO data. INDEX TERMSWind fields forecasting; machine learning; GNSS-RO; Long Short-Term Memory (LSTM); Convolutional Neural Networks (CNN)

Prediction of Wind Power with Machine Learning Models

“…Unlike other algorithms, this method is not influenced by temperature variations, showcasing its remarkable flexibility. Lahouar et al [13] studied hour-ahead wind power forecasting. They observed that neural networks are sensitive to irrelevant data, with model performance decreasing as the number of features increases.…”

“…Several scientists endeavour to employ DL models in wind power prediction using past data to enhance the precision of wind power forecasting [20][21][22]. Recently, there has been an extensive exploration into the realm of DL, focusing on its implementation in short-term wind power prediction [13]. LSTM and CNN are recognised as the two primary DL models [23].…”