期刊文献+

面向空气质量预测的多粒度突变拟合网络

Multi-granularity abrupt change fitting network for air quality prediction
下载PDF
导出
摘要 空气质量数据作为一种典型的时空数据,具有复杂的多尺度内在特性并存在突变的问题。针对现有空气质量预测方法在处理包含大量突变数据的空气质量预测任务时表现不佳的问题,提出一种面向空气质量预测的多粒度突变拟合网络(MACFN)。首先,针对空气质量数据在时间上的周期性,对输入数据进行了多粒度的特征提取。然后,采用图卷积网络与时间卷积网络分别提取空气质量数据的空间关联性与时间依赖性。最后,设计一个突变拟合网络自适应地学习数据中的突变部分,从而减小预测误差。所提网络在3个真实的空气质量数据集上进行了实验评估,与多尺度时空网络(MSSTN)相比,均方根误差(RMSE)分别下降约11.6%、6.3%和2.2%。实验结果表明,MACFN能有效捕捉复杂的时空关系,并在变化幅度较大、易发生突变的空气质量预测任务中有更好表现。 Air quality data,as a typical spatio-temporal data,exhibits complex multi-scale intrinsic characteristics and has abrupt change problem.Concerning the problem that existing air quality prediction methods perform poorly when dealing with air quality prediction tasks containing large amount of abrupt change,a Multi-Granularity abrupt Change Fitting Network(MACFN)for air quality prediction was proposed.Firstly,multi-granularity feature extraction was first performed on the input data according to the periodicity of air quality data in time.Then,a graph convolution network and a temporal convolution network were used to extract the spatial correlation and temporal dependence of the air quality data,respectively.Finally,to reduce the prediction error,an abrupt change fitting network was designed to adaptively learn the abrupt change part of the data.The proposed network was experimentally evaluated on three real air quality datasets,and the Root Mean Square Error(RMSE)decreased by about 11.6%,6.3%,and 2.2%respectively,when compared to the Multi-Scale Spatial Temporal Network(MSSTN).The experimental results show that MACFN can efficiently capture complex spatio-temporal relationships and performs better in the task of predicting air quality that is prone to abrupt change with a large magnitude of variability.
作者 石乾宏 杨燕 江永全 欧阳小草 范武波 陈强 姜涛 李媛 SHI Qianhong;YANG Yan;JIANG Yongquan;OUYANG Xiaocao;FAN Wubo;CHEN Qiang;JIANG Tao;LI Yuan(School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu Sichuan 611756,China;Air Environmental Research Institute,Sichuan Academy of Eco-Environmental Sciences,Chengdu Sichuan 610046,China)
出处 《计算机应用》 CSCD 北大核心 2024年第8期2643-2650,共8页 journal of Computer Applications
基金 国家自然科学基金资助项目(61976247)。
关键词 空气质量预测 深度学习 时空特征 多粒度 突变 air quality prediction deep learning spatio-temporal feature multi-granularity abrupt change
  • 相关文献

参考文献3

二级参考文献38

  • 1罗艾民,魏利军.有毒重气泄漏安全距离数值方法[J].中国安全科学学报,2005,15(8):98-100. 被引量:30
  • 2郭琳,肖美,何宗健.关于大气颗粒物源解析技术综述[J].江西化工,2006,22(4):73-75. 被引量:12
  • 3韩力群.人工神经网络理论、设计及应用[M].北京:化学工业出版社,2004.
  • 4Sower S, Nucci N V,Silver M R. Family of gonadotropin- releasing hormone[M]//Encyclopedia of endocrine diseases. Amsterdam, Boston: Elsevier Inc, 2004: 306-316.
  • 5POPE C, BURNETT R, THUN M, et al. Lung cancer, cardiopulmonary mortality, and long term exposure to fine particulate air pollution[J]. Journal of the American Medical Association, 2002, 287: 1132-1141.
  • 6TOON O B. How pollution suppresses rain[J]. Science, 2000, 28(710): 1763-1765.
  • 7DOCKERY D W, POPE C A. Acute respiratory effects of particulate air pollution[J]. Annual Revision Public Health, 1994, 35: 107-132.
  • 8KOCH M. Airborne fine particulates in the environment: a review of health effect studies, monitoring data and emission inventories, IR-00 004. Laxengurg, Austria: IIASA, 2000.
  • 9CHAN Y C, SIMPSON R W, MCTAINSH G H, et al. Characterization of chemical species in PM2.5 and PM10 aerosols in Brisbane Australia[J]. Atmospheric Environment, 1997, 31: 3773-3785.
  • 10WU Dui(吴兑), DENG Xuejiao(邓雪娇), BI Xueyan(毕雪岩), et al. Distinguishing of fog or haze and operational criteria for observation, forecasting and early warning of haze in urban areas of Guangdong, Hong Kong and Macao[J]. 广州气象, 2007, 29(2): 5-10.

共引文献322

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部