Prediction of Air Quality Index Based on Support Vector Machine and Improved Butterfly Optimization Algorithm

Air pollution is an increasingly serious problem. Air pollution has been become a main cause of environmental degradation and health effects. Accurate prediction of air quality can help improve environmental quality and human living conditions. The traditional methods for predicting the air quality index have the problem of low accuracy and efficiency. To solve this problem, this paper proposes a novel support vector machine prediction model based on improved butterfly optimization algorithm, which is called IBOA-SVM model. In the improved butterfly optimization algorithm, the sigmoid function is used to optimize the update of the parameter c, which increases the search diversity and improves the convergence speed. The performance of the improved butterfly optimization algorithm is verified using eight benchmark functions. Compared with performances of the traditional butterfly optimization algorithm and the particle swarm optimization algorithm, the improved butterfly optimization algorithm has strong competitiveness in accuracy and stability. We establish the IBOA-SVM prediction model for forecasting air quality based on the improved butterfly optimization algorithm. The performance of our proposed model is compared with other predicting models. The experimental results show that our proposed model has higher accuracy and efficiency in predicting the air quality index of four cities in southern China.