Department of Automation, College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, Shanxi, China.
College of Information and Computer, Taiyuan University of Technology, Taiyuan, 030024, Shanxi, China.
Environ Sci Pollut Res Int. 2021 Jan;28(1):56-72. doi: 10.1007/s11356-020-11065-8. Epub 2020 Oct 12.
PM (particulate matter with a size/diameter ≤ 2.5 μm) is an important air pollutant that affects human health, especially in urban environments. However, as time-series data of PM are non-linear and non-stationary, it is difficult to predict future PM distribution and behavior. Therefore, in this paper, we propose a hybrid short-term urban PM prediction model based on variational mode decomposition modified by the correntropy criterion, the state transition simulated annealing (STASA) algorithm, and a support vector regression model to overcome the disadvantages of traditional forecasting techniques which consider different environmental factors. Two experiments were performed with the model to assess its effectiveness and predictive ability: in experiment I, we verified the performance of STASA on benchmark functions, while in experiment II, we used PM data from different epochs and regions of Beijing to verify its forecasting performance. The experimental results showed that the proposed model is robust and can achieve satisfactory prediction results under different conditions compared with current forecasting techniques.
PM（粒径/直径≤2.5μm 的颗粒物）是一种重要的空气污染物，会影响人类健康，尤其是在城市环境中。然而，由于 PM 的时间序列数据是非线性和非平稳的，因此很难预测未来 PM 的分布和行为。因此，在本文中，我们提出了一种基于变分模态分解的混合短期城市 PM 预测模型，该模型修改了相关熵准则、状态转移模拟退火（STASA）算法和支持向量回归模型，以克服传统预测技术的缺点，这些技术仅考虑了不同的环境因素。通过两个实验对模型的有效性和预测能力进行了评估：在实验 I 中，我们验证了 STASA 在基准函数上的性能，而在实验 II 中，我们使用了来自北京不同时期和不同区域的 PM 数据来验证其预测性能。实验结果表明，与当前的预测技术相比，所提出的模型在不同条件下具有稳健性，并能取得令人满意的预测结果。
