科研之友
微信
新浪微博
Facebook
分享链接
摘要
In this study, built upon the WRF-CMAQ air quality model simulations, a novel machine learning method based on simulations and observations (SOML) that integrating feedforward neural network (FNN) and long short-term Memory network (LSTM) through the Lasso method was developed for forecasting NO2 concentrations, where LSTM was derived based on real-time pollutant and meteorological data. This innovative method was then applied to forecast the NO2 concentrations for three consecutive days for ten air quality monitoring stations in Shunde, Foshan to evaluate the model performance. Our results show that: Compared to WRF-CMAQ and other individual models, SOML gave higher accuracy in the three-day forecast of NO2 concentrations, with the mean absolute error (MAE) of first day at 4.99μg/m3, decreasing up to 66.18%; The accuracy of SOML predictions has significantly improved compared with that of WRF-CMAQ, indicating SOML’s suitable applicability to all seasons (MAE decreased by 42.18%, 42.89%, 61.04% and 50.91%, respectively), particularly in autumn and winter; and Compared with WRF-CMAQ, SOML appears to provide better forecasting accuracy of the spatial distribution as well as the NO2 concentration levels at each station in Shunde. ? 2023 Chinese Society for Environmental Sciences.
- 单位
