Abstract
This study presents two dynamic models, namely recurrent neural network and long short-term memory (LSTM) models, for predicting PM2.5 concentrations in Taiwan by using PM2.5 time series obtained at air quality monitoring stations and weather information obtained at neighboring weather stations. The proposed models can efficiently predict PM2.5 by incorporating a learned memory structure with a forgetting gate. To evaluate the predictive performance of the proposed models, large-scale databases established by Taiwan's Environmental Protection Administration, and Central Weather Bureau were used; these databases include hourly data from 77 air quality monitoring stations and 580 weather stations over a 1-year period. The results demonstrated that the proposed models outperformed three traditional machine learning methods (gradient boosting, support vector machine, and classification and regression tree models) by 27.12% and 33.69% on average in terms of the coefficient of determination and root mean square error, respectively. A geographical divergence analysis was conducted to compare predictive performance in different regions. The results revealed that the most significant improvement in predictive performance was achieved in central Taiwan. The seasonal and pollution effect on predictive performance were reduced by the LSTM and the source distribution of PM2.5 emission in Taiwan was also analyzed.
Highlights
A IR pollution is a major environmental concern and continues to pose a serious threat to health worldwide [1]
PREDICTIVE PERFORMANCE Experiments were conducted to determine the predictive performance of the proposed models, and R2, root mean square error (RMSE), normalized RMSE (NRMSE), and mean absolute percentage error (MAPE) served as performance metrics
Despite the complex mechanisms underlying this ominous pollution problem, we discovered that the long-short term memory (LSTM) model could adequately predict PM2.5 concentrations in this region
Summary
A IR pollution is a major environmental concern and continues to pose a serious threat to health worldwide [1]. PM2.5 predictions are challenging because the formation and transportation of PM2.5 is strongly influenced by spatial and temporal variations at both micro- and macro-scales [18], [19] These limitations of time and space results in variations of predictive performance when applying different models in different countries [20]–[24]. Recurrent neural network (RNN) and long-short term memory (LSTM) model are the two major models which have been widely used in time series data prediction including PM2.5 [27]–[29]. To improve predictive performance [25], the present study presents two dynamic models, namely recurrent neural network (RNN) and long-short term memory (LSTM) models that can provide long-term memory of the correlations among time series items. The LSTM model clearly improved predictive performance in this region
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
