Spatial imputation for air pollutants data sets via low rank matrix completion algorithm

Liu, Xiaofeng; Wang, Xue; Zou, Lang; Xia, Jing; Pang, Wei

doi:10.1016/j.envint.2020.105713

Cited by 29 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To realize the coordination between economic growth and ecological governance, in the Fourteenth Five-Year Plan , China clearly defined air pollution prevention and control actions that must be carried out to eliminate heavy pollution weather. Air pollution is a typical public problem with characteristics such as cross-regional, strong fluidity, wide influence, noncompetitive and nonexclusive, and it usually formed a correlation within a certain region [ 3 ]. These make the effect of the fragmented governance that depends on administrative divisions very limited.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the spatio-temporal network of air pollution in the Yangtze River Delta urban agglomeration, China

et al. 2022

View full text Add to dashboard Cite

The complex correlation between regions caused by the externality of air pollution increases the difficulty of its governance. Therefore, analysis of the spatio-temporal network of air pollution (STN-AP) holds great significance for the cross-regional coordinated governance of air pollution. Although the spatio-temporal distribution of air pollution has been analyzed, the structural characteristics of the STN-AP still need to be clarified. The STN-AP in the Yangtze River Delta urban agglomeration (YRDUA) is constructed based on the improved gravity model and is visualized by UCINET with data from 2012 to 2019. Then, its overall-individual-clustering characteristics are analyzed through social network analysis (SNA) method. The results show that the STN-AP in the YRDUA was overall stable, and the correlation level gradually improved. The centrality of every individual city is different in the STN-AP, which reveals the different state of their interactive mechanism. The STN-AP could be subdivided into the receptive block, overflow block, bidirectional block and intermediary block. Shanghai, Suzhou, Hangzhou and Wuxi could be key cities with an all above degree centrality, betweenness centrality and closeness centrality and located in the overflow block of the STN-AP. This showed that these cities had a greater impact on the STN-AP and caused a more pronounced air pollution spillovers. The influencing factors of the spatial correlation of air pollution are further determined through the quadratic assignment procedure (QAP) method. Among all factors, geographical proximity has the strongest impact and deserves to be paid attention in order to prevent the cross-regional overflow of air pollution. Furthermore, several suggestions are proposed to promote coordinated governance of air pollution in the YRDUA.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of the spatio-temporal network of air pollution in the Yangtze River Delta urban agglomeration, China

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It occurs most frequently in air pollutant research studies because the data are measured by air quality monitoring stations at regular time intervals and there may be reading or recording failures. These failures may be due to maintenance shutdowns, filter clogging, periodic calibrations, power failures, etc., resulting in the absence of measurements at certain time intervals [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

A Method of Pruning and Random Replacing of Known Values for Comparing Missing Data Imputation Models for Incomplete Air Quality Time Series

et al. 2022

View full text Add to dashboard Cite

The data obtained from air quality monitoring stations, which are used to carry out studies using data mining techniques, present the problem of missing values. This paper describes a research work on missing data imputation. Among the most common methods, the method that best imputes values to the available data set is analysed. It uses an algorithm that randomly replaces all known values in a dataset once with imputed values and compares them with the actual known values, forming several subsets. Data from seven stations in the Silesian region (Poland) were analyzed for hourly concentrations of four pollutants: nitrogen dioxide (NO2), nitrogen oxides (NOx), particles of 10 μm or less (PM10) and sulphur dioxide (SO2) for five years. Imputations were performed using linear imputation (LI), predictive mean matching (PMM), random forest (RF), k-nearest neighbours (k-NN) and imputation by Kalman smoothing on structural time series (Kalman) methods and performance evaluations were performed. Once the comparison method was validated, it was determine that, in general, Kalman structural smoothing and the linear imputation methods best fitted the imputed values to the data pattern. It was observed that each imputation method behaves in an analogous way for the different stations The variables with the best results are NO2 and SO2. The UMI method is the worst imputer for missing values in the data sets.

show abstract

“…Mean imputation and Median imputation are two common missing value imputation methods when data are MCAR. They are used as benchmark methods for imputing missing values in air quality datasets in many studies, such as [15][16][17][18][19]. They substitute the mean or median of the corresponding observed attribute's values for the missing values of that attribute in a dataset, respectively [20].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, to achieve more efficient imputation of discrete missing values in time series air quality data, we raise a new single imputation method [18,27] called "First five last three logistic regression imputation (FTLRI)". This method combines the traditional logistic regression with a presented "first Five & last Three" model, which can explain relationships between/among disparate attributes and extract the data points that are extremely relevant, both in terms of time and attributes, to the data point with missing values, respectively.…”

Section: Introductionmentioning

confidence: 99%

A Novel Missing Data Imputation Approach for Time Series Air Quality Data Based on Logistic Regression

et al. 2022

View full text Add to dashboard Cite

Missing values in air quality datasets bring trouble to exploration and decision making about the environment. Few imputation methods aim at time series air quality data so that they fail to handle the timeliness of the data. Moreover, most imputation methods prefer low-missing-rate datasets to relatively high-missing-rate datasets. This paper proposes a novel missing data imputation method, called FTLRI, for time series air quality data based on the traditional logistic regression and a presented “first Five & last Three” model, which can explain relationships between disparate attributes and extract data that are extremely relevant, both in terms of time and attributes, to the missing data, respectively. To investigate the performance of FTLRI, it is benchmarked with five classical baselines and a new dynamic imputation method using a neural network with average hourly concentration data of pollutants from three disparate stations in Lanzhou in 2019 under different missing rates. The results show that FTLRI has a significant advantage over the compared imputation approaches, both in the particular short-term and long-term time series air quality data. Furthermore, FTLRI has good performance on datasets with a relatively high missing rate, since it only selects the data extremely related to the missing values instead of relying on all the other data like other methods.

show abstract

Spatial imputation for air pollutants data sets via low rank matrix completion algorithm

Cited by 29 publications

References 21 publications

Analysis of the spatio-temporal network of air pollution in the Yangtze River Delta urban agglomeration, China

Analysis of the spatio-temporal network of air pollution in the Yangtze River Delta urban agglomeration, China

A Method of Pruning and Random Replacing of Known Values for Comparing Missing Data Imputation Models for Incomplete Air Quality Time Series

A Novel Missing Data Imputation Approach for Time Series Air Quality Data Based on Logistic Regression

Contact Info

Product

Resources

About