A statistical learning framework for spatial-temporal feature selection and application to air quality index forecasting

Zhao, Zixi; Wu, Jinran; Cai, Fengjing; Zhang, Shaotong; Wang, You‐Gan

doi:10.1016/j.ecolind.2022.109416

Cited by 24 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In visual analysis, maps are the most commonly used spatial visualization tools because the presentation of maps enables both professional and nonprofessional analysts to achieve preliminary assessment of the evolution of events in geospatial areas 30 . Accurate AQI forecasting benefits the local economy, environment, and public health 31 . Therefore, we created a spatiotemporal map to reveal the monthly changes and developments in the air quality across the 31 Chinese provinces between 2014 and 2021, thereby employing www.nature.com/scientificreports/ color channels to display the AQI and a time drop-down list to visualize the time sequence.…”

Section: Methods Visual Analysis Is Based On the Classical Visualizat...mentioning

confidence: 99%

High-dimensional spatiotemporal visual analysis of the air quality in China

Liu

Wan

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Air quality is a significant environmental issue among the Chinese people and even the global population, and it affects both human health and the Earth’s long-term sustainability. In this study, we proposed a multiperspective, high-dimensional spatiotemporal data visualization and interactive analysis method, and we studied and analyzed the relationship between the air quality and several influencing factors, including meteorology, population, and economics. Six visualization methods were integrated in this study, each specifically designed and improved for visualization analysis purposes. To reveal the spatiotemporal distribution and potential impact of the air quality, we designed a comprehensive coupled visual interactive analysis approach visually express both high-dimensional and spatiotemporal attributes, reveal the overall situation and explain the relationship between attributes. We clarified the current spatiotemporal distribution, development trends, and influencing factors of the air quality in China through interactive visual analysis of a 25-dimensional dataset involving 31 Chinese provinces. We also verified the correctness and effectiveness of relevant policies and demonstrated the advantages of our method.

show abstract

Section: Methods Visual Analysis Is Based On the Classical Visualizat...mentioning

confidence: 99%

High-dimensional spatiotemporal visual analysis of the air quality in China

Liu

Wan

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The statistical method does not involve meteorological theories; instead, it mainly explores patterns from the data to construct prediction models [15][16][17] . Considering that air quality data is a typical time series, auto regressive moving average model (ARMA) is widely used.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Later on, a reinforcement learning based bee swarm optimization (QBSO) is proposed for feature selection to obtain a more intelligent optimizer 38 . The QBSO algorithm in feature selection takes the advantage of reinforcement learning with very adaptive and efficient each process, and the QBSO has been popularly used in practice 17 , 39 .…”

Section: Introductionmentioning

confidence: 99%

“…Although deep learning combined with feature selection has an expectation of improving the prediction accuracy of air quality, it is not yet possible to analyse the spatial characteristics of air quality data. Currently, many scholars are beginning to notice this important characteristic of air quality data, and the spatial correlations have been shown to improve prediction accuracy in many research 17 , 28 , 40 , 41 . In particular, the statistical-based method for spatial correlation modelling is popularly used due to its solid foundation.…”

Section: Introductionmentioning

confidence: 99%

“…Besides, numerical simulation methods often produce complex calculations, which are not user-friendly. In view of these inadequacies, statistical methods to predict air quality have become increasingly popular among researchers.The statistical method does not involve meteorological theories; instead, it mainly explores patterns from the data to construct prediction models [15][16][17] . Considering that air quality data is a typical time series, auto regressive moving average model (ARMA) is widely used.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A hybrid deep learning framework for air quality prediction with spatial autocorrelation during the COVID-19 pandemic

Zhao

Cai

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

China implemented a strict lockdown policy to prevent the spread of COVID-19 in the worst-affected regions, including Wuhan and Shanghai. This study aims to investigate impact of these lockdowns on air quality index (AQI) using a deep learning framework. In addition to historical pollutant concentrations and meteorological factors, we incorporate social and spatio-temporal influences in the framework. In particular, spatial autocorrelation (SAC), which combines temporal autocorrelation with spatial correlation, is adopted to reflect the influence of neighbouring cities and historical data. Our deep learning analysis obtained the estimates of the lockdown effects as − 25.88 in Wuhan and − 20.47 in Shanghai. The corresponding prediction errors are reduced by about 47% for Wuhan and by 67% for Shanghai, which enables much more reliable AQI forecasts for both cities.

show abstract