Dunea Daniel, Pohoata Alin, Iordache Stefania
Faculty of Environmental Engineering and Food Sciences, Valahia University of Targoviste, Aleea Sinaia no. 13, Targoviste, 130004, Dambovita County, Romania,
Environ Monit Assess. 2015 Jul;187(7):477. doi: 10.1007/s10661-015-4697-x. Epub 2015 Jul 1.
The paper presents the screening of various feedforward neural networks (FANN) and wavelet-feedforward neural networks (WFANN) applied to time series of ground-level ozone (O3), 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 (O3, 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 db3 wavelet-Rprop FANN (6-4-1) utilization gave positive results for O3 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 db3 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.
本文介绍了对各种前馈神经网络（FANN）和小波前馈神经网络（WFANN）的筛选，这些网络应用于罗马尼亚不同市区四个监测站记录的地面臭氧（O3）、二氧化氮（NO2）和颗粒物（PM10和PM2.5组分）的时间序列，以确定具有最佳泛化性能的常见配置。进行了两种不同的模型运行，如下所示：使用寒冷月份（O3、NO2和PM10）每小时记录的空气污染物时间序列进行数据处理，此时住宅供暖会增加本地排放；以及使用2009年至2012年期间记录的24小时日平均浓度（PM2.5）进行数据处理。使用统计分析评估数据集的变异性。时间序列通过各种FANN。每个时间序列使用三级小波分解为四个时间尺度分量，这些分量也通过FANN，然后重新组合成单个时间序列。基于统计显著性（r系数以及误差与数据之间的相关性）评估观测输出与模型输出之间的一致性。对于O3时间序列，使用Daubechies db3小波-Rprop FANN（6-4-1）取得了积极成果，优化了对每小时记录时间序列单独使用FANN的情况。由于时间序列的特殊性，NO2难以建模，但小波集成提高了FANN的性能。Daubechies db3小波并未改善PM10时间序列的FANN输出。在时间序列的最后一个季度，两种模型（FANN/WFANN）都高估了PM2.5的预测值。预测值的一个潜在改进可能是集成一种平滑算法来调整PM2.5模型输出。
