High spatiotemporal resolution estimation of AOD from Himawari-8 using an ensemble machine learning gap-filling method

Chen, Aoxuan; Yang, Jin Shan; He, Yan; Yuan, Qiangqiang; Li, Zhengqiang; Zhu, Liye

doi:10.1016/j.scitotenv.2022.159673

Cited by 16 publications

(4 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study utilizes the MAIAC AOD products at 550 nm for Hubei Province, spanning a period of six years from 1 January 2015 through 31 December 2020, sourced from the Google Earth Engine (https://code.earthengine.google.com, accessed on 25 July 2023). However, the accuracy of satellite AOD can be compromised due to atmospheric conditions, such as cloud cover or precipitation [13], resulting in spatiotemporal gaps in the MAIAC AOD data. As illustrated in Figure 2, the year 2017 had the highest annual effective observation rate of the MAIAC AOD, being approximately 4% higher than the other years.…”

Section: Aod Datamentioning

confidence: 99%

“…Moreover, the application of machine-learning techniques to estimate PM 2.5 concentrations from satellite AOD measurements has gained traction [12], leveraging the correlation between AOD and ground-based PM 2.5 observations to facilitate estimations in regions lacking groundbased monitoring stations. However, the utility of satellite AOD is curtailed by weather conditions such as cloud cover and rain, resulting in spatial gaps in AOD and PM 2.5 datasets [13]. In response, researchers have proposed an AOD reconstruction method to create a comprehensive AOD dataset, which has proven beneficial for PM 2.5 estimation [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Daily Seamless PM2.5 Concentrations with Climate Feature in Hubei Province, China

Ding

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The urgent necessity for precise and uninterrupted PM2.5 datasets of high spatial–temporal resolution is underscored by the significant influence of PM2.5 on weather, climate, and human health. This study leverages the AOD reconstruction method to compensate for missing values in the MAIAC AOD throughout Hubei Province. The reconstructed AOD dataset, exhibiting an R2/RMSE of 0.76/0.18, compared to AERONET AOD, was subsequently used for PM2.5 estimation. Our research breaks from traditional methodologies that solely depend on latitude and longitude information. Instead, it emphasizes the use of climate feature as an input for estimating PM2.5 concentrations. This strategic approach prevents potential spatial discontinuities triggered by geolocation information (latitude and longitude), thus ensuring the precision of the PM2.5 estimation (sample/spatial CV R2 = 0.91/0.88). Moreover, we proposed a method for identifying the absolute feature importance of machine-learning models. Contrasted with the relative feature-importance property typical of machine-learning models (a minor difference in the order of top three between geolocation-based and climate-feature-based models, and the slight difference in the top three: 0.08%/0.17%), our method provides a more comprehensive explanation of the absolute significance of features to the model (maintaining the same order and a larger difference in the top three: 0.99%/0.72%). Crucially, our findings demonstrated that AOD reconstruction can mitigate the overestimation of annual mean PM2.5 concentrations (ranging from 0.52 to 9.28 µg/m3). In addition, the seamless PM2.5 dataset contributes to reducing the bias in exposure risk assessment (ranging from −0.11 to 9.81 µg/m3).

show abstract

Section: Aod Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of Daily Seamless PM2.5 Concentrations with Climate Feature in Hubei Province, China

Ding

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, the traditional methods used to identify water bodies have limitations, including low accuracy in single-band threshold methods, complex calculations involved in multi-spectral band methods, and difficulties in determining water body boundaries when they appear fuzzy using water index methods [18]. The rise of machine learning algorithms offers innovative approaches for water body recognition and river morphology analysis [19][20][21][22]. With modern computers' powerful processing capabilities, high-precision automatic interpretations of remote sensing images are achievable, and the introduction of residual connection mechanisms further propels image recognition into deep learning territory.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Approach for Analyzing the Morphological Evolution of the Lower Reaches of the Minjiang River Based on Long-Term Remote Sensing Data

Zhou

Sheng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Understanding the evolution of river morphology is crucial for comprehending changes in water resources and implementing development projects along rivers. This study proposes an integrated approach utilizing remote sensing image data combined with deep learning and visual interpretation algorithms to analyze continuous-type changes in river morphology. This research focuses on the lower reaches of the Minjiang River in China and comprehensively analyzes the river’s morphological evolution from 1986 to 2021. The results show that the proposed method of river water identification in this study demonstrates high accuracy and effectiveness, with an F1 score and Kappa coefficient greater than 0.96 and 0.91, respectively. The morphology of the river channel remains stable in the upstream and estuarine sections of the study region while undergoing substantial alterations in the middle section. Additionally, this study also identifies several factors that significantly impact the evolution of river morphology, including reservoir construction, river sediment mining, river training measures, geological conditions, and large flood events. The findings of this study can provide some insights into the management and conservation of water resources.

show abstract

“…The above studies show that fully exploiting appropriate models and meteorological data to explore spatiotemporal changes in aerosols has gradually become a research hotspot in recent years [23][24][25][26]. However, problems remain in the current research: (1) research mainly focuses on coastal, desert, and other areas with a single topography, while few studies have focused on areas with complex underlying surfaces, which is problematic because spatiotemporal variations of aerosols vary under the influence of different topographic factors [27,28].…”

Section: Introductionmentioning

confidence: 99%

Aerosol Evolution and Influencing Factor Analysis during Haze Periods in the Guanzhong Area of China Based on Multi-Source Data

et al. 2022

View full text Add to dashboard Cite

Aerosols suspended in the atmosphere negatively affect air quality and public health and promote global climate change. The Guanzhong area in China was selected as the study area. Air quality data from July 2018 to June 2021 were recorded daily, and 19 haze periods were selected for this study. The Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model was used to simulate the air mass transport trajectory during this haze period to classify the formation process. The spatial distribution of the aerosol optical depth (AOD) was obtained by processing Moderate-resolution Imaging Spectroradiometer (MODIS) data using the dark target (DT) method. Three factors were used to analyze the AOD spatial distribution characteristics based on the perceptual hashing algorithm (PHA): GDP, population density, and topography. Correlations between aerosols and the wind direction, wind speed, and precipitation were analyzed using weather station data. The research results showed that the haze period in Guanzhong was mainly due to locally generated haze (94.7%). The spatial distribution factors are GDP, population density, and topography. The statistical results showed that wind direction mainly affected aerosol diffusion in Guanzhong, while wind speed (r = −0.63) and precipitation (r = −0.66) had a significant influence on aerosol accumulation and diffusion.

show abstract

High spatiotemporal resolution estimation of AOD from Himawari-8 using an ensemble machine learning gap-filling method

Cited by 16 publications

References 68 publications

Estimation of Daily Seamless PM2.5 Concentrations with Climate Feature in Hubei Province, China

Estimation of Daily Seamless PM2.5 Concentrations with Climate Feature in Hubei Province, China

An Integrated Approach for Analyzing the Morphological Evolution of the Lower Reaches of the Minjiang River Based on Long-Term Remote Sensing Data

Aerosol Evolution and Influencing Factor Analysis during Haze Periods in the Guanzhong Area of China Based on Multi-Source Data

Contact Info

Product

Resources

About