Visibility Prediction Based on Machine Learning Algorithms

In this study, ground observation data were selected from January 2016 to 2020. First, six machine learning methods used predict visibility. We verified the accuracy of method with and without principal components analysis (PCA) by combining actual examples European Centre for Medium-Range Weather Forecast (ECMWF) National Centers Environmental Prediction (NECP) data. The results show that PCA can improve visibility prediction. Neural networks have high in algorithms. initial plays an important role forecast effectively accuracy.