Advancing High-Resolution Weather Prediction through Machine Learning and GNSS Techniques

Accurate high-resolution weather prediction is essential for numerous applications, including agriculture and disaster management. However, traditional forecasting methods face challenges in achieving precise predictions. This study addresses the challenge of weather prediction by harnessing the fusion of machine learning and Global Navigation Satellite System (GNSS) techniques. Specifically, novel machine-learning models are developed to predict precipitable water vapour and temperature, critical variables affecting weather patterns. The models seamlessly combine GNSS and meteorological datasets from the Continuously Operating Reference Station (CORS) in Mzuzu City, Malawi, to estimate weather attributes with exceptional accuracy. Experimental results demonstrate that the proposed models achieve prediction accuracies, enabling the capture of subtle variations in precipitation and temperature contents. Among the developed models, a suitable candidate for weather forecasting is identified based on its superior performance. The development of this model represents a significant step towards the realization of a real-time weather prediction system capable of providing accurate and localized forecasts. Furthermore, by leveraging the power of machine learning and integrating GNSS data, this research addresses the challenge of achieving high-resolution weather prediction and contributes to overcoming the limitations of traditional forecasting methods.