Using wavelet-feedforward neural networks to improve air pollution forecasting in urban environments

作者：Dunea Daniel^*; Pohoata Alin; Iordache Stefania

来源：Environmental Monitoring and Assessment, 2015, 187(7): 477.

DOI：10.1007/s10661-015-4697-x

• Air pollution
• Wavelet transformation
• Batch-learning algorithm
• Time series analysis

The paper presents the screening of various feedforward neural networks (FANN) and waveletfeedforward neural networks (WFANN) applied to time series of ground-level ozone (O-3), nitrogen dioxide (NO2), and particulate matter (PM10 and PM2.5 fractions) recorded at four monitoring stations located in various urban areas of Romania, to identify common configurations with optimal generalization performance. Two distinct model runs were performed as follows: data processing using hourly-recorded time series of airborne pollutants during cold months (O-3, NO2, and PM10), when residential heating increases the local emissions, and data processing using 24-h daily averaged concentrations (PM2.5) recorded between 2009 and 2012. Dataset variability was assessed using statistical analysis. Time series were passed through various FANNs. Each time series was decomposed in four time-scale components using three-level wavelets, which have been passed also through FANN, and recomposed into a single time series. The agreement between observed and modelled output was evaluated based on the statistical significance (r coefficient and correlation between errors and data). Daubechies db(3) wavelet-Rprop FANN (6-4-1) utilization gave positive results for O-3 time series optimizing the exclusive use of the FANN for hourly-recorded time series. NO2 was difficult to model due to time series specificity, but wavelet integration improved FANN performances. Daubechies db(3) wavelet did not improve the FANN outputs for PM10 time series. Both models (FANN/WFANN) overestimated PM2.5 forecasted values in the last quarter of time series. A potential improvement of the forecasted values could be the integration of a smoothing algorithm to adjust the PM2.5 model outputs.

• 出版日期2015-7