Forecasting air pollution PM 2.5 in Beijing using weather data and multiple kernel learning
Forecasting air pollution PM 2.5 in Beijing using weather data and multiple kernel learning
复制标题
DOI：
10.1002/for.2599
复制
发表时间：
2020-03
影响因子：
3.4
通讯作者：
Xiang Xu
中科院分区：
文献类型：
--
作者：
Xiang Xu
随着大气污染对城市环境影响的日益严重，PM2.5质量浓度预测成为一个重要的研究课题。在本文中，PM2.5的预测框架，结合气象因素的基础上，提出了多核学习（MKL）预测近期PM2.5。此外，我们开发了一种新的两步算法来解决原始MKL问题。与大多数已有的MKL两步算法相比，该算法不需要线性搜索更新核组合系数的最优步长。为了证明所提出的预测框架的性能，将其性能与基于单核的支持向量回归（SVR）进行比较。利用UCI提供的北京内陆城市数据集对两种方法进行了训练和验证。实验表明，我们提出的方法优于SVR。
PM2.5 mass concentration prediction is an important research issue because of the increasing impact of air pollution on the urban environment. In this paper, a PM2.5 forecasting framework incorporating meteorological factors based on multiple kernel learning (MKL) is proposed to forecast the near future PM2.5. In addition, we develop a novel two‐step algorithm for solving the primal MKL problem. Compared with most existing MKL 2‐step algorithms, the proposed algorithm does not require the optimal step size for updating kernel combination coefficients by linear search. To demonstrate the performance of the proposed forecasting framework, its performance is compared to single kernel‐based support vector regression (SVR). Data sets of an inland city Beijing acquired from UCI are used to train and validate both of two methods. Experiments show that our proposed method outperforms the SVR.