PM2.5 Prediction Combined ANFIS with Meta-Heuristic Optimization Algorithms: A Case Study in Wuhan

Meta-heuristic algorithms and ANFIS have extraordinarily impressive performance for predicting time-series PM2.5 air quality data. This paper explores the possibility of mainstream meta-heuristic algorithms combined with the adaptive neuro-fuzzy inference system (ANFIS) applied to PM2.5 prediction in Wuhan. It is a major difficulty to choose appropriate methods to connect the strengths of both MHA and ANFIS for data prediction. Therefore, three sorts of meta-heuristic algorithms, including ant colony optimization, particle swarm optimization, and genetic algorithm, have been constructed to update the parameters of the neural network of ANFIS. In the case study in Wuhan, modified fuzzy inference systems possess the studying capacity of neural networks and integrate the human ability for reasoning and interpretation, thereby handling the uncertainty of data prediction better.