基于多分辨率弹性门控注意力和高斯混合模型的地铁站PM2.5浓度区间预测
Probabilistic concentration prediction of PM2.5 in subway stations based on multi-resolution elastic-gated attention mechanism and Gaussian mixture model
方亚民 1刘辉1
作者信息
- 1. Institute of Artificial Intelligence and Robotics(IAIR),Key Laboratory of Traffic Safety on Track of Ministry of Education,School of Traffic&Transportation Engineering,Central South University,Changsha 410075,China
- 折叠
摘要
地铁是城市中短途通勤的主流交通工具.然而,由于地铁站内空气流动性差,所以监测地铁空气质量并提供高污染预警具有重大意义.为解决地铁站内空气质量预警问题,本文提出了一个概率预测框架.首先,采用基于概率损失的自动编码器对PM2.5数据进行检测并纠正异常值.其次,采用多分辨率弹性门控注意力机制改进序列到序列(Seq2Seq)中编码器的结构,以减弱预测过程中的误差累积和历史信息丢失.此外,将多输出策略和弹性门控注意力机制相结合,来改进Seq2Seq中解码器的结构,以减少预测时的误差累积.最后,在Seq2Seq的输出端嵌入高斯混合模型(Gaussian mixture model,GMM),使其能够适应浓度分布的变化并生成浓度的概率分布.所提出的模型在第1步、3步和5步预测中的平均MAPE分别为0.94%、1.16%和1.26%.模型对地铁站PM2.5数据的测试结果表明,与其他模型相比,所提出的模型的Pinball loss和Winkler score更小.
Abstract
The subway has increasingly taken over as the primary method of short-distance travel in the development of modern urban transportation.Due to the poor air mobility in subway stations,it is crucial to monitor and provide alerts on air quality.This work provides a probabilistic prediction framework of PM2.5 concentration to solve the air quality early warning problem in subway stations.Firstly,outliers are discovered and corrected utilizing a probabilistic-based auto-encoder(PAE).Secondly,the multi-resolution elastic-gated attention mechanism is used to address error accumulation and historical information lost during the prediction process.Moreover,the decoder structure of sequence to sequence(Seq2Seq)is improved through multiple output strategy and flexible gate attention mechanism to reduce error accumulation.Finally,the Seq2Seq is equipped with Gaussian mixture models(GMM),allowing it to adapt to more complicated changes and produce a probability distribution of PM2.5 concentrations.According to tests on data from subway stations,the Pinball loss and Winkler score of the proposed model are smaller compared to other models.
关键词
PM2.5/地铁站/混合高斯分布/区间预测/注意力机制Key words
PM2.5/subway station/mixed Gaussian distribution/probabilistic prediction/attention mechanism引用本文复制引用
基金项目
National Key Research;Development Program;China(2020YFC2008605)
National Natural Science Foundation of China(52072412)
Project(2021JJ30359)
Natural Science Foundation of Hunan Province of China()
Hunan Province Science and Technology Talent Support Project,China(2020TJ-Q06)
出版年
2023
NETL
NSTL
万方数据