Study on O3 Prediction Based on Deep Learning and Spatiotemporal Information Integration
High concentrations of ozone can cause many hazards,and accurate prediction of ozone concentration can pro-vide effective early warning for relevant departments.Based on the method of deep learning and spatiotemporal information integration,this study developed a new integrated model,including a deep learning module,a meteorological and spatio-temporal information coupling prediction module and an integration module,to predict the ozone concentration at the Bin-jiang station in Hangzhou.The results show that the mean absolute error(MAE)of this model in 24 h prediction is 19.35μg·m-3,which is significantly better than other models.The model exhibits proficient capabilities in predicting ozone trends under various levels of ozone pollution,particularly excelling in capturing peak concentrations during high ozone epi-sodes.Moreover,the model showcases consistent performance across different seasons,with its optimal performance ob-served in autumn.Regarding the model's accuracy in predicting the ozone individual air quality index(IAQI),it performs notably well within 24 h,reaching an accuracy of 0.81.Specifically,its accuracy exceeds 0.9 within the initial 3 h,there-by offering substantial scientific support for ozone pollution management.
NETL
NSTL
万方数据
