A novel ensemble reinforcement learning gated unit model for daily PM2.5 forecasting
- PDF / 1,729,920 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 31 Downloads / 189 Views
A novel ensemble reinforcement learning gated unit model for daily PM2.5 forecasting Yanfei Li 1,2 & Zheyu Liu 1 & Hui Liu 1 Received: 30 July 2020 / Accepted: 28 September 2020 # Springer Nature B.V. 2020
Abstract PM2.5 forecasting is an important scientific way to control environmental pollution and keep people healthy. To achieve highperformance PM2.5 forecasting, a new ensemble reinforcement learning gated unit model is presented in this study. The complete framework of this model mainly includes the following steps: In step I, the WPD method is applied to decompose PM2.5 data into 8 sub-series with different frequency types. In step II, the SAE-GRU method is presented to finish the establishment of sub-series forecasting model. Among them, SAE is used to obtain low-latitude features of PM2.5 data, and GRU is applied to finish PM2.5 sub-series forecasting. In step III, Q-learning is used to combine the every PM2.5 sub-series to get the final model prediction results. By comparing and analyzing the final results of all case study, it can be summarized that (1) Q-learning-based ensemble model integrates the subseries with different frequency types perfectly, and results prove that it is better than heuristic algorithm, and (2) the proposed ensemble reinforcement learning gated unit model can get prediction results beyond seventeen alternative models which include three most state-of-the-art models in all cases. Keywords PM2.5 forecasting . Ensemble reinforcement learning gated unit . Wavelet packet decomposition
Introduction With development of industrial technology, the emission of pollutants is gradually deteriorating. The increase of atmospheric pollutants will not only seriously affect people’s health but also greatly increase the cost of environmental governance (Peduzzi et al. 2018). At present, many scholars put forward various new technologies in air pollutant control. Air quality detection technology can report the current situation of urban pollution in real-time and provide help for urban environmental governance (Błaszczyk et al. 2017). However, air pollutant monitoring does not provide people with sufficient time to prepare for environmental governance in advance Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11869-020-00948-x) contains supplementary material, which is available to authorized users. * Hui Liu [email protected] 1
Institute of Artificial Intelligence and Robotics (IAIR), Key Laboratory of Traffic Safety on Track of Ministry of Education, School of Traffic and Transportation Engineering, Central South University, Changsha 410075, Hunan, China
2
School of Mechatronic Engineering, Hunan Agricultural University, Changsha 410128, Hunan, China
(Hähnel et al. 2020). If the prediction of air pollutants can be realized, people can make environmental planning in advance to ensure the effective treatment of air quality (Sharma et al. 2018). As a key part of air pollution, PM2.5 can cause various respiratory diseases. Urban PM2.5 data are mo
Data Loading...
