PM2.5 Prediction Model Based on Combinational Hammerstein Recurrent Neural Networks
Open Access
- 6 December 2020
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 8 (12), 2178
- https://doi.org/10.3390/math8122178
Abstract
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.Keywords
This publication has 44 references indexed in Scilit:
- Assessment of the Possible Association of Air Pollutants PM10, O3, NO2 With an Increase in Cardiovascular, Respiratory, and Diabetes Mortality in Panama CityMedicine, 2016
- Comparing the Performance of Statistical Models for Predicting PM10 ConcentrationsAerosol and Air Quality Research, 2014
- Forecasting urban PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF–Chem CO tracer modelAtmospheric Environment, 2011
- An MDL-based Hammerstein recurrent neural network for control applicationsNeurocomputing, 2010
- Combining deterministic and statistical approaches for PM10 forecasting in EuropeAtmospheric Environment, 2009
- Minimal model dimension/order determination algorithms for recurrent neural networksPattern Recognition Letters, 2009
- Modelling the effects of meteorological variables on ozone concentration—a quantile regression approachAtmospheric Environment, 2004
- Identification of Hammerstein Models With Cubic Spline NonlinearitiesIEEE Transactions on Biomedical Engineering, 2004
- The false nearest neighbors algorithm: An overviewComputers & Chemical Engineering, 1997
- Bagging predictorsMachine Learning, 1996