An LSTM-based neural network method of particulate pollution forecast in China
Open Access
- 1 February 2021
- journal article
- research article
- Published by IOP Publishing in Environmental Research Letters
- Vol. 16 (4), 044006
- https://doi.org/10.1088/1748-9326/abe1f5
Abstract
Particulate pollution has become more than an environmental problem in rapidly developing economies. Large-scale, long-term and high concentration of particulate pollution occurs much more frequently, which not only affects human health but also economic production. As PM10 is one of the main pollutants, the prediction of its concentration is of great significance. In this study, we present a PM10 forecast model based on the long short-term memory (LSTM) neural network method and evaluate its performance of predicting PM10 daily concentrations at five representative cities (Beijing, Taiyuan, Shanghai, Nanjing and Guangzhou) in China. Our model shows excellent adaptability for various regions in China. The predicted PM10 concentrations have good correlations with observations (R = 0.81–0.91). We also achieve great predication accuracy (70%–80%) on predicting the next-day changing trend and the model has the best performance for heavy pollution situation (PM10 > 100 μg m−3). In addition, the comparison of LSTM-based method and other statistical/machine learning methods indicates that our model is not only robust to different pollution intensities and geographic locations, but also with great potential on pollution forecast with temporal-correlated feature.Funding Information
- National Natural Science Foundation of China (41975139)
- Natural Science Foundation of Guangdong Province (2020A1515011133)
This publication has 24 references indexed in Scilit:
- LSTM: A Search Space OdysseyIEEE Transactions on Neural Networks and Learning Systems, 2016
- The effect of future reduction in aerosol emissions on climate extremes in ChinaClimate Dynamics, 2016
- Radiative forcing and climate response to projected 21st century aerosol decreasesAtmospheric Chemistry and Physics, 2015
- Development of a model for forecasting of PM 10 concentrations in Salamanca, MexicoAtmospheric Pollution Research, 2015
- An adaptive support vector regressor controller for nonlinear systemsSoft Computing, 2015
- Effects of declining aerosols on projections of zonally averaged tropical precipitationEnvironmental Research Letters, 2015
- Neurocomputing techniques to dynamically forecast spatiotemporal air pollution dataEvolving Systems, 2013
- Ordinary Least-Squares RegressionPublished by SAGE Publications ,2011
- Ozone ensemble forecast with machine learning algorithmsJournal of Geophysical Research: Atmospheres, 2009
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006