High-resolution daily AOD estimated to full coverage using the random forest model approach in the Beijing-Tianjin-Hebei region

Zhao, Chen; Liu, Zhaorong; Wang, Qing; Ban, Jie; Chen, Nancy Xi; Li, Tiantian

doi:10.1016/j.atmosenv.2019.01.045

Cited by 57 publications

(30 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The newly released MODIS MAIAC AOD [60][61][62] with 1 km spatial resolution will be used to further investigate the performance of our framework. The fourth is that we only compared our proposed framework with the IDW and OK. More state-of-the-art full-coverage PM 2.5 concentrations like machine learning models [49][50][51] will be used to make comparisons with our method on much larger study areas, e.g., the whole of China or the whole continent.…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies show that some outliers negatively affect the accuracy and robustness of PM 2.5 retrieval modelling [49][50][51]58]. Therefore, in our study, we excluded PM 2.5 and AOD data in three conditions: (1) the AOD < 2.5; (2) the AOD > 0.5 and PM 2.5 < 10 µg/m 3 ; and (3) the PM 2.5 < 3 µg/m 3 .…”

Section: Data Pre-processing and Integrationmentioning

confidence: 99%

“…Hu et al [48] adopted the fixed rank smoothing to fill the data gaps in 3 km AOD data, and proposed a spatiotemporal regression kriging (STRK) model to obtain accurate daily PM 2.5 estimations with full-coverage. Zhao [49] and Vu [50] used the random forest model to estimate the corresponding full-coverage AOD data. Xue et al [51] developed a machine learning model with high dimensional expansion of numerous predictors and incorporated a generalized additive model into the model to obtain a full-coverage PM 2.5 estimation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Full-Coverage Daily Average PM2.5 Retrieval Method with Two-Stage IVW Fused MODIS C6 AOD and Two-Stage GAM Model

et al. 2019

View full text Add to dashboard Cite

Current PM2.5 retrieval maps have many missing values, which seriously hinders their performance in real applications. This paper presents a framework to map full-coverage daily average PM2.5 concentrations from MODIS C6 aerosol optical depth (AOD) products and fill missing pixels in both the AOD and PM2.5 maps. First, a two-stage inversed variance weights (IVW) algorithm was adopted to fuse the MODIS C6 Terra and Aqua AOD products, which fills missing data in MODIS standard AOD data and obtains a high coverage daily average. After that, using the fused MODIS daily average AOD and ground-level PM2.5 in all grid cells, a two-stage generalized additive model (GAM) was implemented to obtain the full-coverage PM2.5 concentrations. Experiments on the Yangtze River Delta (YRD) in 2013–2016 were carefully designed to validate the performance of our proposed framework. The results show that the two-stage IVW could not only improve the spatial coverage of MODIS AOD against the original standard product by 230%, but could also keep its data accuracy. When compared with the ground-level measurements, the two-stage GAM can obtain accurate PM2.5 concentration estimates (R2 = 0.78, RMSE = 19.177 μg/m3, and RPE = 28.9%). Moreover, our method performs better than the inverse distance weighted method and kriging methods in mapping full-coverage daily PM2.5 concentrations. Therefore, the proposed framework provides a good methodology for retrieving full-coverage daily average PM2.5 concentrations from MODIS standard AOD products.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Pre-processing and Integrationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Full-Coverage Daily Average PM2.5 Retrieval Method with Two-Stage IVW Fused MODIS C6 AOD and Two-Stage GAM Model

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Compared with space acquisition, the AOD obtained by the ground observation network has higher accuracy. Nevertheless, it is difficult to provide a wide range of viewing angles for the AOD of ground measurements due to limitations in equipment deployment and observation ranges [9,10]. Therefore, it is more efficient to use remote sensing for AOD measurement and inversion on a large scale.…”

Section: Introductionmentioning

confidence: 99%

“…AOD information is filled in by using a machine learning methods such as random forest (RF) [20] or gradient boosting machine (GBM) [24] to process the multisource data. The strong data mining ability of the machine learning methods is good for fitting multisource data, and it can achieve higher precision at the same time [9,37].…”

Section: Introductionmentioning

confidence: 99%

Handling Missing Data in Large-Scale MODIS AOD Products Using a Two-Step Model

Yufeng

Liao

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Aerosol optical depth (AOD) is a key parameter that reflects the characteristics of aerosols, and is of great help in predicting the concentration of pollutants in the atmosphere. At present, remote sensing inversion has become an important method for obtaining the AOD on a large scale. However, AOD data acquired by satellites are often missing, and this has gradually become a popular topic. In recent years, a large number of AOD recovery algorithms have been proposed. Many AOD recovery methods are not application-oriented. These methods focus mainly on to the accuracy of AOD recovery and neglect the AOD recovery ratio. As a result, the AOD recovery accuracy and recovery ratio cannot be balanced. To solve these problems, a two-step model (TWS) that combines multisource AOD data and AOD spatiotemporal relationships is proposed. We used the light gradient boosting (LightGBM) model under the framework of the gradient boosting machine (GBM) to fit the multisource AOD data to fill in the missing AOD between data sources. Spatial interpolation and spatiotemporal interpolation methods are limited by buffer factors. We recovered the missing AOD in a moving window. We used TWS to recover AOD from Terra Satellite’s 2018 AOD product (MOD AOD). The results show that the MOD AOD, after a 3 × 3 moving window TWS recovery, was closely related to the AOD of the Aerosol Robotic Network (AERONET) (R = 0.87, RMSE = 0.23). In addition, the MOD AOD missing rate after a 3 × 3 window TWS recovery was greatly reduced (from 0.88 to 0.1). In addition, the spatial distribution characteristics of the monthly and annual averages of the recovered MOD AOD were consistent with the original MOD AOD. The results show that TWS is reliable. This study provides a new method for the restoration of MOD AOD, and is of great significance for studying the spatial distribution of atmospheric pollutants.

show abstract

Long short-term memory network model to estimate PM2.5 concentrations with missing-filled satellite data in Beijing

Jia

Han

Zhang

2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

High-resolution daily AOD estimated to full coverage using the random forest model approach in the Beijing-Tianjin-Hebei region

Cited by 57 publications

References 39 publications

A Full-Coverage Daily Average PM2.5 Retrieval Method with Two-Stage IVW Fused MODIS C6 AOD and Two-Stage GAM Model

A Full-Coverage Daily Average PM2.5 Retrieval Method with Two-Stage IVW Fused MODIS C6 AOD and Two-Stage GAM Model

Handling Missing Data in Large-Scale MODIS AOD Products Using a Two-Step Model

Long short-term memory network model to estimate PM2.5 concentrations with missing-filled satellite data in Beijing

Contact Info

Product

Resources

About