PM2.5 Prediction Model Based on Combinational Hammerstein Recurrent Neural Networks

• Published in: Mathematics (Basel) Vol. 8; no. 12; p. 2178
• Main Authors: Chen, Yi-Chung, Lei, Tsu-Chiang, Yao, Shun, Wang, Hsin-Ping
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2020
• Subjects: Accuracy; Air pollution; Air quality; Artificial intelligence; Costs; Data transfer (computers); Deep learning; feature selection; Food science; Mathematical models; Model accuracy; Neural networks; Numerical prediction; Particulate emissions; PM2.5 predictions; Pollutants; Prediction models; Recurrent neural networks; Statistical analysis; Support vector machines; Time series; time series prediction; Wavelet transforms
• ISSN: 2227-7390; 2227-7390
• DOI: 10.3390/math8122178

Airborne particulate matter 2.5 (PM2.5) can have a profound effect on the health of the population. Many researchers have been reporting highly accurate numerical predictions based on raw PM2.5 data imported directly into deep learning models; however, there is still considerable room for improvement in terms of implementation costs due to heavy computational overhead. From the perspective of environmental science, PM2.5 values in a given location can be attributed to local sources as well as external sources. Local sources tend to have a dramatic short-term impact on PM2.5 values, whereas external sources tend to have more subtle but longer-lasting effects. In the presence of PM2.5 from both sources at the same time, this combination of effects can undermine the predictive accuracy of the model. This paper presents a novel combinational Hammerstein recurrent neural network (CHRNN) to enhance predictive accuracy and overcome the heavy computational and monetary burden imposed by deep learning models. The CHRNN comprises a based-neural network tasked with learning gradual (long-term) fluctuations in conjunction with add-on neural networks to deal with dramatic (short-term) fluctuations. The CHRNN can be coupled with a random forest model to determine the degree to which short-term effects influence long-term outcomes. We also developed novel feature selection and normalization methods to enhance prediction accuracy. Using real-world measurement data of air quality and PM2.5 datasets from Taiwan, the precision of the proposed system in the numerical prediction of PM2.5 levels was comparable to that of state-of-the-art deep learning models, such as deep recurrent neural networks and long short-term memory, despite far lower implementation costs and computational overhead.