Wedad Alahamade, I. Lake, C. Reeves, B. de la Iglesia
{"title":"Evaluation of multivariate time series clustering for imputation of air pollution data","authors":"Wedad Alahamade, I. Lake, C. Reeves, B. de la Iglesia","doi":"10.5194/gi-10-265-2021","DOIUrl":null,"url":null,"abstract":"Abstract. Air pollution is one of the world's leading risk factors for death, with 6.5 million deaths per year worldwide attributed to air-pollution-related diseases. Understanding the behaviour of certain pollutants through air quality assessment can produce improvements in air quality management that will translate to health and economic benefits. However, problems with missing data and uncertainty hinder that assessment. We are motivated by the need to enhance the air pollution data available. We focus on the problem of missing air pollutant concentration data either because a limited set of pollutants is measured at a monitoring site or because an instrument is not operating, so a particular pollutant is not measured for a period of time. In our previous work, we have proposed models which can impute a whole missing time series to enhance air quality monitoring. Some of these models are based on a multivariate time series (MVTS) clustering method. Here, we apply our method to real data and show how different graphical and statistical model evaluation functions enable us to select the imputation model that produces the most plausible imputations. We then compare the Daily Air Quality Index (DAQI) values obtained after imputation with observed values incorporating missing data. Our results show that using an ensemble model that aggregates the spatial similarity obtained by the geographical correlation between monitoring stations and the fused temporal similarity between pollutant concentrations produces very good imputation results. Furthermore, the analysis enhances understanding of the different pollutant behaviours and of the characteristics of different stations according to their environmental type.\n","PeriodicalId":48742,"journal":{"name":"Geoscientific Instrumentation Methods and Data Systems","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geoscientific Instrumentation Methods and Data Systems","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.5194/gi-10-265-2021","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract. Air pollution is one of the world's leading risk factors for death, with 6.5 million deaths per year worldwide attributed to air-pollution-related diseases. Understanding the behaviour of certain pollutants through air quality assessment can produce improvements in air quality management that will translate to health and economic benefits. However, problems with missing data and uncertainty hinder that assessment. We are motivated by the need to enhance the air pollution data available. We focus on the problem of missing air pollutant concentration data either because a limited set of pollutants is measured at a monitoring site or because an instrument is not operating, so a particular pollutant is not measured for a period of time. In our previous work, we have proposed models which can impute a whole missing time series to enhance air quality monitoring. Some of these models are based on a multivariate time series (MVTS) clustering method. Here, we apply our method to real data and show how different graphical and statistical model evaluation functions enable us to select the imputation model that produces the most plausible imputations. We then compare the Daily Air Quality Index (DAQI) values obtained after imputation with observed values incorporating missing data. Our results show that using an ensemble model that aggregates the spatial similarity obtained by the geographical correlation between monitoring stations and the fused temporal similarity between pollutant concentrations produces very good imputation results. Furthermore, the analysis enhances understanding of the different pollutant behaviours and of the characteristics of different stations according to their environmental type.
期刊介绍:
Geoscientific Instrumentation, Methods and Data Systems (GI) is an open-access interdisciplinary electronic journal for swift publication of original articles and short communications in the area of geoscientific instruments. It covers three main areas: (i) atmospheric and geospace sciences, (ii) earth science, and (iii) ocean science. A unique feature of the journal is the emphasis on synergy between science and technology that facilitates advances in GI. These advances include but are not limited to the following:
concepts, design, and description of instrumentation and data systems;
retrieval techniques of scientific products from measurements;
calibration and data quality assessment;
uncertainty in measurements;
newly developed and planned research platforms and community instrumentation capabilities;
major national and international field campaigns and observational research programs;
new observational strategies to address societal needs in areas such as monitoring climate change and preventing natural disasters;
networking of instruments for enhancing high temporal and spatial resolution of observations.
GI has an innovative two-stage publication process involving the scientific discussion forum Geoscientific Instrumentation, Methods and Data Systems Discussions (GID), which has been designed to do the following:
foster scientific discussion;
maximize the effectiveness and transparency of scientific quality assurance;
enable rapid publication;
make scientific publications freely accessible.