Short-term Weather Forecast Based on Wavelet Denoising and Catboost

Changes in meteorological elements have profoundly affected all aspects of human's life. Therefore, accurate forecasting of future meteorological elements is critical and can be widely used in many fields. Based on the datasets provided by Beijing Meteorological Administration, a short-term weather forecasting model based on wavelet denoising and Catboost is proposed. The correlation-heatmap, recursive feature elimination and tree models are combined for feature selections. Then the wavelet denoising of data is proposed and conducted to process part of the "learning" tasks in advance. The test results demonstrate that the proposed model can achieve shorter convergence time and higher accuracy comparing with many deep learning or machine learning methods such as LSTM, Seq2Seq and Random Forest.