Automated weather event analysis with machine learning

Weather forecasting has numerous impacts in our daily life from cultivation to event planning. Previous weather forecasting models used the complicated blend of mathematical instruments which was insufficient in order to get higher classification rate. In contrast, simple analytical models are well-suited for weather forecasting tasks. In this work, we focus on the weather forecasting by means of classifying different weather events such as normal, rain, and fog by applying comprehensible C4.5 learning algorithm on weather and climate features. The C4.5 classifier classifies weather events by building the decision tree using information entropy from the set of training samples. We conducted experiments on LA weather history dataset; from evaluation results, it is revealed that C4.5 classifier classifies weather events with f-score of around 96.1%. This model also indicates that climate features such as rainfall, visibility, temperature, humidity, and wind speed are highly discriminative toward events classification.