The spatio-temporal prediction of ozone in Zhuhai based on graph convolutional memory network
Ozone(O₃)has become the primary factor affecting air quality over the Pearl River Delta and even the entire Guangdong Province.Although data-driven statistical models have shown improved forecast capabilities compared to numerical models,most of them operate grid-by-grid and cannot re-solve the spatial dependence between site data of non-Euclidean structures.Based on in-situ measure-ments from national environmental stations and surrounding weather stations in Zhuhai,this study per-forms hourly O₃ concentration forecasts for up to three days over multiple sites by constructing a graph convolution memory network(GCN-LSTM).The results show that GCN_LSTM forecasts at different lead times could accurately reproduce the annual,seasonal,and diurnal variations of O3,but the capa-bility of capturing daily variations decreases significantly with the increase in lead time.Further comparisons with the operational numerical model(GRACEs)and Long Short-Term Memory(LSTM)reveal that GCN-LSTM performs the best,with mean RMSE=27.13 μg/m3 and R=0.64,LSTM is the second(RMSE=28.44 μg/m3;R=0.61),and GRACEs presents distinct results(RMSE=40.93 μg/m3;R=0.33)in 72h forecasting.Compared with LSTM,GCN-LSTM considers all sites and their intercon-nections,it not only increases the calculation speed by 71%but also performs better and more stably over different sites.Moreover,it is also optimal for capturing O₃ pollution events in cold seasons.Additional sensitivity experiments reveal that considering more correlated variables improves forecasting capabilities.
国家科技期刊平台
NSTL
万方数据
