4.7 Article

A novel algorithm for full-coverage daily aerosol optical depth retrievals using machine learning-based reconstruction technique

Related references

Note: Only part of the references are listed.
Article Meteorology & Atmospheric Sciences

Spatiotemporal high-resolution imputation modeling of aerosol optical depth for investigating its full-coverage variation in China from 2003 to 2020

Qingqing He et al.

Summary: Investigating the spatiotemporal variations of atmospheric aerosols is important for climate change and environmental research. This study developed an adaptive spatiotemporal imputation model for aerosol optical depth (AOD) using the MAIAC algorithm and multisource data, aiming to support full-coverage aerosol studies in China. The proposed approach effectively captured the massive spatiotemporal variability and delivered high-accuracy full-coverage AODs. The imputed AODs showed better representativeness and revealed underestimation in the original satellite-retrieved AODs, especially during summer and over the North China Plain.

ATMOSPHERIC RESEARCH (2023)

Article Environmental Sciences

Evaluation of four meteorological reanalysis datasets for satellite-based PM2.5 retrieval over China

Chen Zuo et al.

Summary: This study evaluates four meteorological reanalysis datasets in China and finds that ERA5 is the most accurate in terms of temperature, relative humidity, wind speed, and boundary layer height, while FNL has the highest uncertainty. The spatial accuracy of all datasets is higher in the eastern region compared to the western region due to complex terrain and limited ground-based observations. ERA5 performs the best in retrieving PM2.5 in China, providing a useful guideline for subsequent satellite-based PM2.5 retrieval studies in the country.

ATMOSPHERIC ENVIRONMENT (2023)

Article Geography, Physical

Improved retrievals of aerosol optical depth and fine mode fraction from GOCI geostationary satellite data using machine learning over East Asia

Yoojin Kang et al.

Summary: Aerosol Optical Depth (AOD) and Fine Mode Fraction (FMF) are important parameters for air quality research. In this study, machine learning models were used to directly estimate AOD and FMF from Geostationary Ocean Color Imager (GOCI) reflectances. The results showed that the machine learning models performed well and had smaller errors compared to existing algorithms. Additionally, considering meteorological conditions and surface reflectance improved the estimation of AOD and FMF.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2022)

Article Environmental Sciences

Geographical and temporal encoding for improving the estimation of PM2.5 concentrations in China using end-to-end gradient boosting

Naisen Yang et al.

Summary: This paper proposes a geospatial-temporal joint encoding method to characterize the influence of spatial-temporal information on PM2.5 concentration hidden in satellite-based aerosol products. Experimental results in China in 2019 show promising performance of the proposed method.

REMOTE SENSING OF ENVIRONMENT (2022)

Article Meteorology & Atmospheric Sciences

The relationship between atmospheric boundary layer and temperature inversion layer and their aerosol capture capabilities

Boming Liu et al.

Summary: The study investigated the relationship between the atmospheric boundary layer and the temperature inversion layer, and examined their correlation with aerosol capture capabilities. The results indicated that temperature inversion intensity is a key factor in determining the aerosol capture ability.

ATMOSPHERIC RESEARCH (2022)

Article Geography, Physical

Gap-filling MODIS daily aerosol optical depth products by developing a spatiotemporal fitting algorithm

Tao Zhang et al.

Summary: Aerosol loadings and their spatial distribution play a crucial role in air quality monitoring, climate research, and public health. Researchers have proposed a novel algorithm to fill the gaps in MODIS AOD product, which has been tested and cross-validated in China. The algorithm outperforms other methods in accuracy and meets the requirements of typical applications.

GISCIENCE & REMOTE SENSING (2022)

Article Environmental Sciences

Synergistic data fusion of satellite observations and in-situ measurements for hourly PM2.5 estimation based on hierarchical geospatial long short-term memory

Xinyu Yu et al.

Summary: This study proposes a hierarchical geospatial long short-term memory method (HG-LSTM) for PM2.5 estimation with 2-km spatial resolution in the Yangtze River Delta urban agglomeration. The results show that the HG-LSTM model accurately estimates hourly PM2.5 concentrations and reveals the spatiotemporal characteristics of PM2.5 in the study area.

ATMOSPHERIC ENVIRONMENT (2022)

Article Environmental Sciences

Analysis of Long-Term Aerosol Optical Properties Combining AERONET Sunphotometer and Satellite-Based Observations in Hong Kong

Xinyu Yu et al.

Summary: This study examines the seasonal characteristics and long-term variations of aerosol optical parameters in Hong Kong using AERONET data and satellite-based observations. The results show that the dominant aerosol types in Hong Kong are mixed aerosols and urban/industrial aerosols with fine-mode sizes and slightly absorbing or non-absorbing properties. Seasonally, the aerosol optical depth (AOD), Angstrom exponent (AE), and single scattering albedo (SSA) exhibit different patterns, with lower AOD but higher AE and SSA in summer, and elevated AOD but lower AE and SSA in spring and winter. The long-term variations indicate a turning point in 2012, with an upward trend in AOD and AE before 2012 and a downward trend afterwards. However, SSA shows a rising trend in both periods, with a steeper gradient in the first period.

REMOTE SENSING (2022)

Article Geosciences, Multidisciplinary

LGHAP: the Long-term Gap-free High-resolution Air Pollutant concentration dataset, derived via tensor-flow-based multimodal data fusion

Kaixu Bai et al.

Summary: Developing a big data analytics framework to generate a long-term continuous high-resolution air pollutant concentration dataset is crucial for environmental management and Earth system science analysis. The framework integrates multimodal aerosol data from various sources and uses a tensor-flow-based data fusion method to generate a gap-free aerosol optical depth (AOD) dataset for China from 2000 to 2020 at a daily 1 km resolution.

EARTH SYSTEM SCIENCE DATA (2022)

Article Meteorology & Atmospheric Sciences

Estimation of hourly full-coverage PM2.5 concentrations at 1-km resolution in China using a two-stage random forest model

Tingting Jiang et al.

Summary: The study estimated hourly PM2.5 concentrations in China from March 2018 to February 2019 at a 1-km spatial resolution using a two-stage random forest model. The model achieved accurate and robust estimations of PM2.5 concentrations, but the performance varied across different seasons.

ATMOSPHERIC RESEARCH (2021)

Article Engineering, Environmental

High-Resolution Spatiotemporal Modeling for Ambient PM2.5 Exposure Assessment in China from 2013 to 2019

Conghong Huang et al.

Summary: The study established a hybrid spatiotemporal modeling framework for PM2.5 in China, incorporating various predictor variables and advanced machine learning methods, to accurately assess long-term and short-term PM2.5 concentrations nationally and at city scales. The model performed well with high spatial and temporal cross-validation R-squared values, and the downscaled predictions significantly improved the spatial variation of PM2.5 concentrations at the city scale. The framework and dataset generated in this study could be valuable for PM2.5 exposure assessment and epidemiological studies.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2021)

Article Environmental Sciences

Reconstructing 1-km-resolution high-quality PM2.5 data records from 2000 to 2018 in China: spatiotemporal variations and policy implications

Jing Wei et al.

Summary: This study utilized satellite remote sensing and modeling to construct a 1 km resolution PM2.5 dataset for China from 2000 to 2018, revealing a decrease in PM2.5 concentrations over the past two decades, especially accelerating in the last six years. The North China Plain remains the most polluted region in China, while significant improvements are observed in the Pearl and Yangtze River Deltas.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Meteorology & Atmospheric Sciences

Incorrect Asian aerosols affecting the attribution and projection of regional climate change in CMIP6 models

Zhili Wang et al.

Summary: The study reveals that CMIP6 models fail to accurately capture the observed trends of aerosol optical depth over Asia, mainly due to problematic anthropogenic aerosol emissions adopted by the models. Differences in simulated regional aerosol radiative forcing and temperature responses over Asia are evident when using different emissions inventories. Additionally, some widely adopted CMIP6 pathways underestimate the recent decline in anthropogenic aerosol emissions over China.

NPJ CLIMATE AND ATMOSPHERIC SCIENCE (2021)

Article Environmental Sciences

Estimate hourly PM2.5 concentrations from Himawari-8 TOA reflectance directly using geo-intelligent long short-term memory network

Bin Wang et al.

Summary: Researchers developed a model to estimate PM2.5 concentrations and explored the optimal modeling strategy. The results showed that PM2.5 concentrations exhibited different stable changes within a day, with the highest concentrations occurring in winter and the lowest concentrations occurring in summer.

ENVIRONMENTAL POLLUTION (2021)

Article Environmental Sciences

A High-Precision Aerosol Retrieval Algorithm (HiPARA) for Advanced Himawari Imager (AHI) data: Development and verification

Xin Su et al.

Summary: The study proposed a land general aerosol algorithm for East Asia, achieving high-precision aerosol property detection through a spectral ratio library and statistical methods. HiPARA algorithm dynamically determined surface reflectance and aerosol types, with detected AOD showing high consistency with AERONET measurements.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Meteorology & Atmospheric Sciences

An overview of and issues with sky radiometer technology and SKYNET

Teruyuki Nakajima et al.

ATMOSPHERIC MEASUREMENT TECHNIQUES (2020)

Article Multidisciplinary Sciences

Deep learning and process understanding for data-driven Earth system science

Markus Reichstein et al.

NATURE (2019)

Article Environmental Sciences

Impacts of snow and cloud covers on satellite-derived PM2.5 levels

Jianzhao Bi et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Article Environmental Sciences

Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach

Jing Wei et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Article Environmental Sciences

Filling the missing data gaps of daily MODIS AOD using spatiotemporal interpolation

Jing Yang et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2018)

Article Environmental Sciences

Reconstructing spatial-temporal continuous MODIS land surface temperature using the DINEOF method

Wang Zhou et al.

JOURNAL OF APPLIED REMOTE SENSING (2017)

Article Meteorology & Atmospheric Sciences

The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2)

Ronald Gelaro et al.

JOURNAL OF CLIMATE (2017)

Article Marine & Freshwater Biology

Data Interpolating Empirical Orthogonal Functions (DINEOF): a tool for geophysical data analyses

A. ALVERA-AZCÁRATE et al.

MEDITERRANEAN MARINE SCIENCE (2017)

Article Meteorology & Atmospheric Sciences

The Collection 6 MODIS aerosol products over land and ocean

R. C. Levy et al.

ATMOSPHERIC MEASUREMENT TECHNIQUES (2013)

Article Meteorology & Atmospheric Sciences

Aerosol optical properties and their radiative effects in northern China

Zhanqing Li et al.

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES (2007)

Review Environmental Sciences

A review of measurement-based assessments of the aerosol direct radiative effect and forcing

H Yu et al.

ATMOSPHERIC CHEMISTRY AND PHYSICS (2006)

Article Meteorology & Atmospheric Sciences

Monthly averages of aerosol properties: A global comparison among models, satellite data, and AERONET ground data

S Kinne et al.

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES (2003)

Review Multidisciplinary Sciences

A satellite view of aerosols in the climate system

YJ Kaufman et al.

NATURE (2002)

Review Multidisciplinary Sciences

Atmosphere - Aerosols, climate, and the hydrological cycle

V Ramanathan et al.

SCIENCE (2001)

Article Meteorology & Atmospheric Sciences

Accuracy assessments of aerosol optical properties retrieved from Aerosol Robotic Network (AERONET) Sun and sky radiance measurements

O Dubovik et al.

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES (2000)