Hybrid Vector Autoregression Feedforward Neural Network with Genetic Algorithm Model for Forecasting Space-Time Pollution Data

The exposure rate to air pollution in most urban cities is really a major concern because it results life-threatening consequence for human health and wellbeing. Furthermore, the accurate estimation continuous forecasting of levels very complicated task. In this paper, one space-temporal models, vector autoregressive (VAR) with neural network (NN) genetic algorithm (GA) was proposed enhanced. VAR could tackle issue multivariate time series, NN nonlinearity, GA parameter determination. Therefore, model be used make predictions, such as information series location data. applied methods were on data, including NOX, PM2.5, PM10, SO2 Taipei, Hsinchu, Taichung, Kaohsiung. metaheuristics enhance during experiments. conclusion, VAR-NN-GA gives good accuracy when metric evaluation used. can determine phenomena 10 years Taiwan.