Research

20 pages, 4557 KiB

Open AccessArticle

MFCD-Net: Cross Attention Based Multimodal Fusion Network for DPC Imagery Cloud Detection

by Jingjing Zhang, Kai Ge, Lina Xun, Xiaobing Sun, Wei Xiong, Mingmin Zou, Jinqin Zhong and Teng Li

Remote Sens. 2022, 14(16), 3905; https://doi.org/10.3390/rs14163905 - 11 Aug 2022

Viewed by 1523

Abstract

As one kind of remote sensing image (RSI), Directional Polarimetric Camera (DPC) data are of great significance in atmospheric radiation transfer and climate feedback. The availability of DPC images is often hindered by clouds, and effective cloud detection is the premise of many [...] Read more.

As one kind of remote sensing image (RSI), Directional Polarimetric Camera (DPC) data are of great significance in atmospheric radiation transfer and climate feedback. The availability of DPC images is often hindered by clouds, and effective cloud detection is the premise of many applications. Conventional threshold-based cloud detection methods are limited in performance and generalization capability. In this paper, we propose an effective learning-based 3D multimodal fusion cloud detection network (MFCD-Net) model. The network is a three-input stream architecture with a 3D-Unet-like encoder-decoder structure to fuse the multiple modalities of reflectance image, polarization image Q, and polarization image U in DPC imagery, with consideration of the angle and spectral information. Furthermore, cross attention is utilized in fusing the polarization features into the spatial-angle-spectral features in the reflectance image to enhance the expression of the fused features. The dataset used in this paper is obtained from the DPC cloud product and the cloud mask product. The proposed MFCD-Net achieved excellent cloud detection performance, with a recognition accuracy of 95.74%, according to the results of the experiments. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

14 pages, 2370 KiB

Open AccessCommunication

Cloud Detection of Remote Sensing Image Based on Multi-Scale Data and Dual-Channel Attention Mechanism

by Qing Yan, Hu Liu, Jingjing Zhang, Xiaobing Sun, Wei Xiong, Mingmin Zou, Yi Xia and Lina Xun

Remote Sens. 2022, 14(15), 3710; https://doi.org/10.3390/rs14153710 - 03 Aug 2022

Cited by 8 | Viewed by 1575

Abstract

Cloud detection is one of the critical tasks in remote sensing image preprocessing. Remote sensing images usually contain multi-dimensional information, which is not utilized entirely in existing deep learning methods. This paper proposes a novel cloud detection algorithm based on multi-scale input and [...] Read more.

Cloud detection is one of the critical tasks in remote sensing image preprocessing. Remote sensing images usually contain multi-dimensional information, which is not utilized entirely in existing deep learning methods. This paper proposes a novel cloud detection algorithm based on multi-scale input and dual-channel attention mechanisms. Firstly, we remodeled the original data to a multi-scale layout in terms of channels and bands. Then, we introduced the dual-channel attention mechanism into the existing semantic segmentation network, to focus on both band information and angle information based on the reconstructed multi-scale data. Finally, a multi-scale fusion strategy was introduced to combine band information and angle information simultaneously. Overall, in the experiments undertaken in this paper, the proposed method achieved a pixel accuracy of 92.66% and a category pixel accuracy of 92.51%. For cloud detection, the proposed method achieved a recall of 97.76% and an F1 of 95.06%. The intersection over union (IoU) of the proposed method was 89.63%. Both in terms of quantitative results and visual effects, the deep learning model we propose is superior to the existing semantic segmentation methods. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

18 pages, 5308 KiB

Open AccessArticle

Constructing High-Resolution (10 km) Daily Diffuse Solar Radiation Dataset across China during 1982–2020 through Ensemble Model

by Jinyang Wu, Hejin Fang, Wenmin Qin, Lunche Wang, Yan Song, Xin Su and Yujie Zhang

Remote Sens. 2022, 14(15), 3695; https://doi.org/10.3390/rs14153695 - 02 Aug 2022

Cited by 9 | Viewed by 2301

Abstract

Diffuse solar radiation is an essential component of surface solar radiation that contributes to carbon sequestration, photovoltaic power generation, and renewable energy production in terrestrial ecosystems. We constructed a 39-year (1982–2020) daily diffuse solar radiation dataset (CHSSDR), using ERA5 and MERRA_2 reanalysis data, [...] Read more.

Diffuse solar radiation is an essential component of surface solar radiation that contributes to carbon sequestration, photovoltaic power generation, and renewable energy production in terrestrial ecosystems. We constructed a 39-year (1982–2020) daily diffuse solar radiation dataset (CHSSDR), using ERA5 and MERRA_2 reanalysis data, with a spatial resolution of 10 km through a developed ensemble model (generalized additive models, GAM). The validation results, with ground-based measurements, showed that GAM had a high and stable performance with the correlation coefficient (R), root-mean-square error (RMSE), and mean absolute error (MAE) for the sample-based cross-validations of 0.88, 19.54 Wm⁻², and 14.87 Wm⁻², respectively. CHSSDR had the highest consistency with ground-based measurements among the four diffuse solar radiation products (CERES, ERA5, JiEA, and CHSSDR), with the least deviation (MAE = 15.06 Wm⁻² and RMSE = 20.22 Wm⁻²) and highest R value (0.87). The diffuse solar radiation values in China range from 59.13 to 104.65 Wm⁻², with a multi-year average value of 79.39 Wm⁻² from 1982 to 2020. Generally, low latitude and low altitude regions have larger diffuse solar radiation than high latitude and high altitude regions, and eastern China has less diffuse solar radiation than western China. This dataset would be valuable for analyzing regional climate change, photovoltaic applications, and solar energy resources. The dataset is freely available from figshare. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

18 pages, 14803 KiB

Open AccessArticle

An Ensemble Model-Based Estimation of Nitrogen Dioxide in a Southeastern Coastal Region of China

by Sicong He, Heng Dong, Zili Zhang and Yanbin Yuan

Remote Sens. 2022, 14(12), 2807; https://doi.org/10.3390/rs14122807 - 11 Jun 2022

Cited by 6 | Viewed by 1450

Abstract

NO₂ (nitrogen dioxide) is a common pollutant in the atmosphere that can have serious adverse effects on the health of residents. However, the existing satellite and ground observation methods are not enough to effectively monitor the spatiotemporal heterogeneity of near-surface NO₂ [...] Read more.

NO₂ (nitrogen dioxide) is a common pollutant in the atmosphere that can have serious adverse effects on the health of residents. However, the existing satellite and ground observation methods are not enough to effectively monitor the spatiotemporal heterogeneity of near-surface NO₂ concentrations, which limits the development of pollutant remediation work and medical health research. Based on TROPOMI-NO₂ tropospheric column concentration data, supplemented by meteorological data, atmospheric condition reanalysis data and other geographic parameters, combined with classic machine learning models and deep learning networks, we constructed an ensemble model that achieved a daily average near-surface NO₂ of 0.03° exposure. In this article, a meteorological hysteretic effects term and a spatiotemporal term were designed, which considerably improved the performance of the model. Overall, our ensemble model performed better, with a 10-fold CV R² of 0.89, an RMSE of 5.62 µg/m³, and an MAE of 4.04 µg/m³. The model also had good temporal and spatial generalization capability, with a temporal prediction R² and a spatial prediction R² of 0.71 and 0.81, respectively, which can be applied to a wider range of time and space. Finally, we used an ensemble model to estimate the spatiotemporal distribution of NO₂ in a coastal region of southeastern China from May 2018 to December 2020. Compared with satellite observations, the model output results showed richer details of the spatiotemporal heterogeneity of NO₂ concentrations. Due to the advantages of using multi-source data, this model framework has the potential to output products with a higher spatial resolution and can provide a reference for downscaling work on other pollutants. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

22 pages, 14372 KiB

Open AccessArticle

Estimation of Daily and Instantaneous Near-Surface Air Temperature from MODIS Data Using Machine Learning Methods in the Jingjinji Area of China

by Chunling Wang, Xu Bi, Qingzu Luan and Zhanqing Li

Remote Sens. 2022, 14(8), 1916; https://doi.org/10.3390/rs14081916 - 15 Apr 2022

Cited by 6 | Viewed by 2132

Abstract

Meteorologically observed air temperature (T_a) is limited due to low density and uneven distribution that leads to uncertain accuracy. Therefore, remote sensing data have been widely used to estimate near-surface T_a on various temporal scales due to their spatially [...] Read more.

Meteorologically observed air temperature (T_a) is limited due to low density and uneven distribution that leads to uncertain accuracy. Therefore, remote sensing data have been widely used to estimate near-surface T_a on various temporal scales due to their spatially continuous characteristics. However, few studies have focused on instantaneous T_a when satellites overpass. This study aims to produce both daily and instantaneous T_a datasets at 1 km resolution for the Jingjinji area, China during 2018–2019, using machine learning methods based on remote sensing data, dense meteorological observation station data, and auxiliary data (such as elevation and normalized difference vegetation index). Newly released Moderate Resolution Imaging Spectroradiometer (MODIS) Collection 6 surface Downward Shortwave Radiation (DSR) was introduced to improve the accuracy of T_a estimation. Five machine learning algorithms were implemented and compared so that the optimal one could be selected. The random forest (RF) algorithm outperformed the others (such as decision tree, feedforward neural network, generalized linear model) and RF obtained the highest accuracy in model validation with a daily root mean square error (RMSE) of 1.29 °C, mean absolute error (MAE) of 0.94 °C, daytime instantaneous RMSE of 1.88 °C, MAE of 1.35 °C, nighttime instantaneous RMSE of 2.47 °C, and MAE of 1.83 °C. The corresponding R² was 0.99 for daily average, 0.98 for daytime instantaneous, and 0.95 for nighttime instantaneous. Analysis showed that land surface temperature (LST) was the most important factor contributing to model accuracy, followed by solar declination and DSR, which implied that DSR should be prioritized when estimating T_a. Particularly, these results outperformed most models presented in previous studies. These findings suggested that RF could be used to estimate daily instantaneous T_a at unprecedented accuracy and temporal scale with proper training and very dense station data. The estimated dataset could be very useful for local climate and ecology studies, as well as for nature resources exploration. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

16 pages, 3023 KiB

Open AccessArticle

A Deep-Neural-Network-Based Aerosol Optical Depth (AOD) Retrieval from Landsat-8 Top of Atmosphere Data

by Lu She, Hankui K. Zhang, Ziqiang Bu, Yun Shi, Lu Yang and Jintao Zhao

Remote Sens. 2022, 14(6), 1411; https://doi.org/10.3390/rs14061411 - 15 Mar 2022

Cited by 8 | Viewed by 2870

Abstract

The 30 m resolution Landsat data have been used for high resolution aerosol optical depth (AOD) retrieval based on radiative transfer models. In this paper, a Landsat-8 AOD retrieval algorithm is proposed based on the deep neural network (DNN). A total of 6390 [...] Read more.

The 30 m resolution Landsat data have been used for high resolution aerosol optical depth (AOD) retrieval based on radiative transfer models. In this paper, a Landsat-8 AOD retrieval algorithm is proposed based on the deep neural network (DNN). A total of 6390 samples were obtained for model training and validation by collocating 8 years of Landsat-8 top of atmosphere (TOA) data and aerosol robotic network (AERONET) AOD data acquired from 329 AERONET stations over 30°W–160°E and 60°N–60°S. The Google Earth Engine (GEE) cloud-computing platform is used for the collocation to avoid a large download volume of Landsat data. Seventeen predictor variables were used to estimate AOD at 500 nm, including the seven bands TOA reflectance, two bands TOA brightness (BT), solar and viewing zenith and azimuth angles, scattering angle, digital elevation model (DEM), and the meteorological reanalysis total columnar water vapor and ozone concentration. The leave-one-station-out cross-validation showed that the estimated AOD agreed well with AERONET AOD with a correlation coefficient of 0.83, root-mean-square error of 0.15, and approximately 61% AOD retrievals within 0.05 + 20% of the AERONET AOD. Theoretical comparisons with the physical-based methods and the adaptation of the developed DNN method to Sentinel-2 TOA data with a different spectral band configuration are discussed. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

27 pages, 12781 KiB

Open AccessArticle

Estimation of the All-Wave All-Sky Land Surface Daily Net Radiation at Mid-Low Latitudes from MODIS Data Based on ERA5 Constraints

by Shaopeng Li, Bo Jiang, Jianghai Peng, Hui Liang, Jiakun Han, Yunjun Yao, Xiaotong Zhang, Jie Cheng, Xiang Zhao, Qiang Liu and Kun Jia

Remote Sens. 2022, 14(1), 33; https://doi.org/10.3390/rs14010033 - 22 Dec 2021

Cited by 7 | Viewed by 3077

Abstract

The surface all-wave net radiation (

R_{n}

) plays an important role in the energy and water cycles, and most studies of

R_{n}

estimations have been conducted using satellite data. As one of the most commonly used satellite data sets, Moderate [...] Read more.

The surface all-wave net radiation (

R_{n}

) plays an important role in the energy and water cycles, and most studies of

R_{n}

estimations have been conducted using satellite data. As one of the most commonly used satellite data sets, Moderate Resolution Imaging Spectroradiometer (MODIS) data have not been widely used for radiation calculations at mid-low latitudes because of its very low revisit frequency. To improve the daily

R_{n}

estimation at mid-low latitudes with MODIS data, four models, including three models built with random forest (RF) and different temporal expansion models and one model built with the look-up-table (LUT) method, are used based on comprehensive in situ radiation measurements collected from 340 globally distributed sites, MODIS top-of-atmosphere (TOA) data, and the fifth generation of European Centre for Medium-Range Weather Forecasts Reanalysis 5 (ERA5) data from 2000 to 2017. After validation against the in situ measurements, it was found that the RF model based on the constraint of the daily

R_{n}

from ERA5 (an RF-based model with ERA5) performed the best among the four proposed models, with an overall validated root-mean-square error (RMSE) of 21.83 Wm⁻², R² of 0.89, and a bias of 0.2 Wm⁻². It also had the best accuracy compared to four existing products (Global LAnd Surface Satellite Data (GLASS), Clouds and the Earth’s Radiant Energy System Edition 4A (CERES4A), ERA5, and FLUXCOM_RS) across various land cover types and different elevation zones. Further analyses illustrated the effectiveness of the model by introducing the daily

R_{n}

from ERA5 into a “black box” RF-based model for

R_{n}

estimation at the daily scale, which is used as a physical constraint when the available satellite observations are too limited to provide sufficient information (i.e., when the overpass time is less than twice per day) or the sky is overcast. Overall, the newly-proposed RF-based model with ERA5 in this study shows satisfactory performance and has strong potential to be used for long-term accurate daily

R_{n}

global mapping at finer spatial resolutions (e.g., 1 km) at mid-low latitudes. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

19 pages, 8663 KiB

Open AccessArticle

Characterization of Urban Heat Islands Using City Lights: Insights from MODIS and VIIRS DNB Observations

by Jingjing Song, Jun Wang, Xiangao Xia, Runsheng Lin, Yi Wang, Meng Zhou and Disong Fu

Remote Sens. 2021, 13(16), 3180; https://doi.org/10.3390/rs13163180 - 11 Aug 2021

Cited by 5 | Viewed by 2371

Abstract

An urban heat island (UHI) is a phenomenon whereby the temperature in an urban area is significantly warmer than it a rural area. To further advance the characterization and understanding of UHIs within urban areas, nighttime light measured by the Day/Night Band (DNB) [...] Read more.

An urban heat island (UHI) is a phenomenon whereby the temperature in an urban area is significantly warmer than it a rural area. To further advance the characterization and understanding of UHIs within urban areas, nighttime light measured by the Day/Night Band (DNB) onboard the Visible Infrared Imaging Radiometer Suite (VIIRS) and the land surface temperature (LST) data derived from the Moderate Resolution Imaging Spectroradiometer (MODIS) combined with principal component analysis (PCA) are used here. Beijing (highly developed) and Pyongyang (less developed) are selected as the two case studies. Linear correlation analysis is first used, with higher correlations being found between DNB and LST data at nighttime than between population and LST data for both cities, although none of the correlation coefficients are particularly high because of noise. Principal component analysis (PCA), a method that can remove random noise, is used to extract more useful information. Two types of PCA are conducted, focusing on spatial (S) and temporal (T) patterns. The results of the S-mode PCA reveal that the typical temporal variation is a seasonal cycle for both LST and DNB data in Beijing and Pyongyang. Furthermore, there are monthly cycles for DNB data related to the moon phase in two cities. The T-mode PCA results show important spatial information, while the spatial pattern of the first mode explains over 50% of the variation. This study is among the first to demonstrate the advantages of using urban light to study the spatial variation of urban heat, especially for nighttime urban temperatures measured from space, at the street and neighborhood scales. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

17 pages, 2609 KiB

Open AccessArticle

Application of Machine-Learning-Based Fusion Model in Visibility Forecast: A Case Study of Shanghai, China

by Zhongqi Yu, Yuanhao Qu, Yunxin Wang, Jinghui Ma and Yu Cao

Remote Sens. 2021, 13(11), 2096; https://doi.org/10.3390/rs13112096 - 27 May 2021

Cited by 9 | Viewed by 2600

Abstract

A visibility forecast model called a boosting-based fusion model (BFM) was established in this study. The model uses a fusion machine learning model based on multisource data, including air pollutants, meteorological observations, moderate resolution imaging spectroradiometer (MODIS) aerosol optical depth (AOD) data, and [...] Read more.

A visibility forecast model called a boosting-based fusion model (BFM) was established in this study. The model uses a fusion machine learning model based on multisource data, including air pollutants, meteorological observations, moderate resolution imaging spectroradiometer (MODIS) aerosol optical depth (AOD) data, and an operational regional atmospheric environmental modeling System for eastern China (RAEMS) outputs. Extreme gradient boosting (XGBoost), a light gradient boosting machine (LightGBM), and a numerical prediction method, i.e., RAEMS were fused to establish this prediction model. Three sets of prediction models, that is, BFM, LightGBM based on multisource data (LGBM), and RAEMS, were used to conduct visibility prediction tasks. The training set was from 1 January 2015 to 31 December 2018 and used several data pre-processing methods, including a synthetic minority over-sampling technique (SMOTE) data resampling, a loss function adjustment, and a 10-fold cross verification. Moreover, apart from the basic features (variables), more spatial and temporal gradient features were considered. The testing set was from 1 January to 31 December 2019 and was adopted to validate the feasibility of the BFM, LGBM, and RAEMS. Statistical indicators confirmed that the machine learning methods improved the RAEMS forecast significantly and consistently. The root mean square error and correlation coefficient of BFM for the next 24/48 h were 5.01/5.47 km and 0.80/0.77, respectively, which were much higher than those of RAEMS. The statistics and binary score analysis for different areas in Shanghai also proved the reliability and accuracy of using BFM, particularly in low-visibility forecasting. Overall, BFM is a suitable tool for predicting the visibility. It provides a more accurate visibility forecast for the next 24 and 48 h in Shanghai than LGBM and RAEMS. The results of this study provide support for real-time operational visibility forecasts. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

13 pages, 4228 KiB

Open AccessArticle

Non-Linear Response of PM_2.5 Pollution to Land Use Change in China

by Debin Lu, Wanliu Mao, Wu Xiao and Liang Zhang

Remote Sens. 2021, 13(9), 1612; https://doi.org/10.3390/rs13091612 - 21 Apr 2021

Cited by 19 | Viewed by 2434

Abstract

Land use change has an important influence on the spatial and temporal distribution of PM_2.5 concentration. Therefore, based on the particulate matter (PM_2.5) data from remote sensing instruments and land use change data in long time series, the Getis-Ord Gi* [...] Read more.

Land use change has an important influence on the spatial and temporal distribution of PM_2.5 concentration. Therefore, based on the particulate matter (PM_2.5) data from remote sensing instruments and land use change data in long time series, the Getis-Ord Gi* statistic and SP-SDM are employed to analyze the spatial distribution pattern of PM_2.5 and its response to land use change in China. It is found that the average PM_2.5 increased from 25.49 μg/m³ to 31.23 μg/m³ during 2000-2016, showing an annual average growth rate of 0.97%. It is still greater than 35 μg/m³ in nearly half of all cities. The spatial distribution pattern of PM_2.5 presents the characteristics of concentrated regional convergence. PM_2.5 is positively correlated with urban land and farmland, negatively correlated with forest land, grassland, and unused land. Furthermore, the average PM_2.5 concentrations show the highest values for urban land and decrease in the order of farmland > unused land > water body > forest > grassland. The impact of land use change on PM_2.5 is a non-linear process, and there are obvious differences and spillover effects for different land types. Thus, reasonably controlling the scale of urban land and farmland, optimizing the spatial distribution pattern and development intensity, and expanding forest land and grassland are conducive to curbing PM_2.5 pollution. The research conclusions provide a theoretical basis for the management of PM_2.5 pollution from the perspective of optimizing land use. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

24 pages, 72733 KiB

Open AccessArticle

Estimation of Lower-Stratosphere-to-Troposphere Ozone Profile Using Long Short-Term Memory (LSTM)

by Xinxin Zhang, Ying Zhang, Xiaoyan Lu, Lu Bai, Liangfu Chen, Jinhua Tao, Zhibao Wang and Lili Zhu

Remote Sens. 2021, 13(7), 1374; https://doi.org/10.3390/rs13071374 - 02 Apr 2021

Cited by 13 | Viewed by 2332

Abstract

Climate change and air pollution are emerging topics due to their possible enormous implications for health and social perspectives. In recent years, tropospheric ozone has been recognized as an important greenhouse gas and pollutant that is detrimental to human health, agriculture, and natural [...] Read more.

Climate change and air pollution are emerging topics due to their possible enormous implications for health and social perspectives. In recent years, tropospheric ozone has been recognized as an important greenhouse gas and pollutant that is detrimental to human health, agriculture, and natural ecosystems, and has shown a trend of increasing interest. Machine-learning-based approaches have been widely applied to the estimation of tropospheric ozone concentrations, but few studies have included tropospheric ozone profiles. This study aimed to predict the Northern Hemisphere distribution of Lower-Stratosphere-to-Troposphere (LST) ozone at a pressure of 100 hPa to the near surface by employing a deep learning Long Short-Term Memory (LSTM) model. We referred to a history of all the observed parameters (meteorological data of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5), satellite data, and the ozone profiles of the World Ozone and Ultraviolet Data Center (WOUDC)) between 2014 and 2018 for training the predictive models. Model–measurement comparisons for the monitoring sites of WOUDC for the period 2019–2020 show that the mean correlation coefficients (R²) in the Northern Hemisphere at high latitude (NH), Northern Hemisphere at middle latitude (NM), and Northern Hemisphere at low latitude (NL) are 0.928, 0.885, and 0.590, respectively, indicating reasonable performance for the LSTM forecasting model. To improve the performance of the model, we applied the LSTM migration models to the Civil Aircraft for the Regular Investigation of the Atmosphere Based on an Instrument Container (CARIBIC) flights in the Northern Hemisphere from 2018 to 2019 and three urban agglomerations (the Sichuan Basin (SCB), North China Plain (NCP), and Yangtze River Delta region (YRD)) between 2018 and 2019. The results show that our models performed well on the CARIBIC data set, with a high R² equal to 0.754. The daily and monthly surface ozone concentrations for 2018–2019 in the three urban agglomerations were estimated from meteorological and ancillary variables. Our results suggest that the LSTM models can accurately estimate the monthly surface ozone concentrations in the three clusters, with relatively high coefficients of 0.815–0.889, root mean square errors (RMSEs) of 7.769–8.729 ppb, and mean absolute errors (MAEs) of 6.111–6.930 ppb. The daily scale performance was not as high as the monthly scale performance, with the accuracy of R² = 0.636~0.737, RMSE = 14.543–16.916 ppb, MAE = 11.130–12.687 ppb. In general, the trained module based on LSTM is robust and can capture the variation of the atmospheric ozone distribution. Moreover, it also contributes to our understanding of the mechanism of air pollution, especially increasing our comprehension of pollutant areas. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

23 pages, 11017 KiB

Open AccessArticle

Global Aerosol Classification Based on Aerosol Robotic Network (AERONET) and Satellite Observation

by Jianyu Lin, Yu Zheng, Xinyong Shen, Lizhu Xing and Huizheng Che

Remote Sens. 2021, 13(6), 1114; https://doi.org/10.3390/rs13061114 - 15 Mar 2021

Cited by 13 | Viewed by 4147

Abstract

The particle linear depolarization ratio (PLDR) and single scatter albedo (SSA) in 1020 nm from the Aerosol Robotic Network (AERONET) level 2.0 dataset was utilized among 52 stations to identify dust and dust dominated aerosols (DD), pollution dominated mixture (PDM), strongly absorbing aerosols [...] Read more.

The particle linear depolarization ratio (PLDR) and single scatter albedo (SSA) in 1020 nm from the Aerosol Robotic Network (AERONET) level 2.0 dataset was utilized among 52 stations to identify dust and dust dominated aerosols (DD), pollution dominated mixture (PDM), strongly absorbing aerosols (SA) and weakly absorbing aerosols (WA), investigate their spatial and temporal distribution, net radiative forcing and radiative forcing efficiency in global range, and further compare with VIIRS Deep Blue Production. The conclusion about net radiative forcing suggests that the high values of radiative forcing from dust and dust dominated aerosols, pollution dominated mixture both mainly come from western Africa. Strongly absorbing aerosols in South Africa and India contribute greatly to the net radiative forcing and the regions with relative high values of weakly absorbing aerosols are mainly located at East Asia and India. Lastly, the observation of VIIRS Deep Blue satellite monthly averaged products depicts the characteristics about spatial distribution of four kinds of aerosol well, the result from ground-based observation presents great significant to validate the measurements from remote sensing technology. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

25 pages, 23534 KiB

Open AccessArticle

Performance Comparison of Machine Learning Models for Annual Precipitation Prediction Using Different Decomposition Methods

by Chao Song and Xiaohong Chen

Remote Sens. 2021, 13(5), 1018; https://doi.org/10.3390/rs13051018 - 08 Mar 2021

Cited by 13 | Viewed by 2804

Abstract

It has become increasingly difficult in recent years to predict precipitation scientifically and accurately due to the dual effects of human activities and climatic conditions. This paper focuses on four aspects to improve precipitation prediction accuracy. Five decomposition methods (time-varying filter-based empirical mode [...] Read more.

It has become increasingly difficult in recent years to predict precipitation scientifically and accurately due to the dual effects of human activities and climatic conditions. This paper focuses on four aspects to improve precipitation prediction accuracy. Five decomposition methods (time-varying filter-based empirical mode decomposition (TVF-EMD), robust empirical mode decomposition (REMD), complementary ensemble empirical mode decomposition (CEEMD), wavelet transform (WT), and extreme-point symmetric mode decomposition (ESMD) combined with the Elman neural network (ENN)) are used to construct five prediction models, i.e., TVF-EMD-ENN, REMD-ENN, CEEMD-ENN, WT-ENN, and ESMD-ENN. The variance contribution rate (VCR) and Pearson correlation coefficient (PCC) are utilized to compare the performances of the five decomposition methods. The wavelet transform coherence (WTC) is used to determine the reason for the poor prediction performance of machine learning algorithms in individual years and the relationship with climate indicators. A secondary decomposition of the TVF-EMD is used to improve the prediction accuracy of the models. The proposed methods are used to predict the annual precipitation in Guangzhou. The subcomponents obtained from the TVF-EMD are the most stable among the four decomposition methods, and the North Atlantic Oscillation (NAO) index, the Nino 3.4 index, and sunspots have a smaller influence on the first subcomponent (Sc-1) than the other subcomponents. The TVF-EMD-ENN model has the best prediction performance and outperforms traditional machine learning models. The secondary decomposition of the Sc-1 of the TVF-EMD model significantly improves the prediction accuracy. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

Review

Jump to: Research, Other

21 pages, 3501 KiB

Open AccessReview

The Development and Application of Machine Learning in Atmospheric Environment Studies

by Lianming Zheng, Rui Lin, Xuemei Wang and Weihua Chen

Remote Sens. 2021, 13(23), 4839; https://doi.org/10.3390/rs13234839 - 29 Nov 2021

Cited by 13 | Viewed by 3333

Abstract

Machine learning (ML) plays an important role in atmospheric environment prediction, having been widely applied in atmospheric science with significant progress in algorithms and hardware. In this paper, we present a brief overview of the development of ML models as well as their [...] Read more.

Machine learning (ML) plays an important role in atmospheric environment prediction, having been widely applied in atmospheric science with significant progress in algorithms and hardware. In this paper, we present a brief overview of the development of ML models as well as their application to atmospheric environment studies. ML model performance is then compared based on the main air pollutants (i.e., PM_2.5, O₃, and NO₂) and model type. Moreover, we identify the key driving variables for ML models in predicting particulate matter (PM) pollutants by quantitative statistics. Additionally, a case study for wet nitrogen deposition estimation is carried out based on ML models. Finally, the prospects of ML for atmospheric prediction are discussed. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Figure 1

Other

Jump to: Research, Review

14 pages, 3050 KiB

Open AccessTechnical Note

Development and Validation of Machine-Learning Clear-Sky Detection Method Using 1-Min Irradiance Data and Sky Imagers at a Polluted Suburban Site, Xianghe

by Mengqi Liu, Xiangao Xia, Disong Fu and Jinqiang Zhang

Remote Sens. 2021, 13(18), 3763; https://doi.org/10.3390/rs13183763 - 20 Sep 2021

Cited by 5 | Viewed by 2153

Abstract

Clear-sky detection (CSD) is of critical importance in solar energy applications and surface radiative budget studies. Existing CSD methods are not sufficiently validated due to the lack of high-temporal resolution and long-term CSD ground observations, especially at polluted sites. Using five-year high resolution [...] Read more.

Clear-sky detection (CSD) is of critical importance in solar energy applications and surface radiative budget studies. Existing CSD methods are not sufficiently validated due to the lack of high-temporal resolution and long-term CSD ground observations, especially at polluted sites. Using five-year high resolution ground-based solar radiation data and visual inspected Total Sky Imager (TSI) measurements at polluted Xianghe, a suburban site, this study validated 17 existing CSD methods and developed a new CSD model based on a machine-learning algorithm (Random Forest: RF). The propagation of systematic errors from input data to the calculated global horizontal irradiance (GHI) is confirmed with Mean Absolute Error (MAE) increased by 99.7% (from 20.00 to 39.93 W·m⁻²). Through qualitative evaluation, the novel Bright-Sun method outperforms the other traditional CSD methods at Xianghe site, with high accuracy score 0.73 and 0.92 under clear and cloudy conditions, respectively. The RF CSD model developed by one-year irradiance and TSI data shows more robust performance, with clear/cloudy-sky accuracy score of 0.78/0.88. Overall, the Bright-Sun and RF CSD models perform satisfactorily at heavy polluted sites. Further analysis shows the RF CSD model built with only GHI-related parameters can still achieve a mean accuracy score of 0.81, which indicates RF CSD models have the potential in dealing with sites only providing GHI observations. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

14 pages, 2155 KiB

Open AccessTechnical Note

Retrieving High-Resolution Aerosol Optical Depth from GF-4 PMS Imagery in Eastern China

by Zhendong Sun, Jing Wei, Ning Zhang, Yulong He, Yu Sun, Xirong Liu, Huiyong Yu and Lin Sun

Remote Sens. 2021, 13(18), 3752; https://doi.org/10.3390/rs13183752 - 18 Sep 2021

Cited by 4 | Viewed by 2109

Abstract

Gaofen 4 (GF-4) is a geostationary satellite, with a panchromatic and multispectral sensor (PMS) onboard, and has great potential in observing atmospheric aerosols. In this study, we developed an aerosol optical depth (AOD) retrieval algorithm for the GF-4 satellite. AOD retrieval was realized [...] Read more.

Gaofen 4 (GF-4) is a geostationary satellite, with a panchromatic and multispectral sensor (PMS) onboard, and has great potential in observing atmospheric aerosols. In this study, we developed an aerosol optical depth (AOD) retrieval algorithm for the GF-4 satellite. AOD retrieval was realized based on the pre-calculated surface reflectance database and 6S radiative transfer model. We customized the unique aerosol type according to the long time series aerosol parameters provided by the Aerosol Robotic Network (AERONET) site. The solar zenith angle, relative azimuth angle, and satellite zenith angle of the GF-4 panchromatic multispectral sensor image were calculated pixel-by-pixel. Our 1 km AOD retrievals were validated against AERONET Version 3 measurements and compared with MOD04 C6 AOD products at different resolutions. The results showed that our GF-4 AOD algorithm had a good robustness in both bright urban areas and dark rural areas. A total of 71.33% of the AOD retrievals fell within the expected errors of ±(0.05% + 20%); root-mean-square error (RMSE) and mean absolute error (MAE) were 0.922 and 0.122, respectively. The accuracy of GF-4 AOD in rural areas was slightly higher than that in urban areas. In comparison with MOD04 products, the accuracy of GF-4 AOD was much higher than that of MOD04 3 km and 10 km dark target AOD, but slightly worse than that of MOD04 10 km deep blue AOD. For different values of land surface reflectance (LSR), the accuracy of GF-4 AOD gradually deteriorated with an increase in the LSR. These results have theoretical and practical significance for aerosol research and can improve retrieval algorithms using the GF-4 satellite. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

15 pages, 5283 KiB

Open AccessTechnical Note

Ambient PM_2.5 Estimates and Variations during COVID-19 Pandemic in the Yangtze River Delta Using Machine Learning and Big Data

by Debin Lu, Wanliu Mao, Lilin Zheng, Wu Xiao, Liang Zhang and Jing Wei

Remote Sens. 2021, 13(8), 1423; https://doi.org/10.3390/rs13081423 - 07 Apr 2021

Cited by 11 | Viewed by 3234

Abstract

The lockdown of cities in the Yangtze River Delta (YRD) during COVID-19 has provided many natural and typical test sites for estimating the potential of air pollution control and reduction. To evaluate the reduction of PM_2.5 concentration in the YRD region by [...] Read more.

The lockdown of cities in the Yangtze River Delta (YRD) during COVID-19 has provided many natural and typical test sites for estimating the potential of air pollution control and reduction. To evaluate the reduction of PM_2.5 concentration in the YRD region by the epidemic lockdown policy, this study employs big data, including PM_2.5 observations and 29 independent variables regarding Aerosol Optical Depth (AOD), climate, terrain, population, road density, and Gaode map Point of interesting (POI) data, to build regression models and retrieve spatially continuous distributions of PM_2.5 during COVID-19. Simulation accuracy of multiple machine learning regression models, i.e., random forest (RF), support vector regression (SVR), and artificial neural network (ANN) were compared. The results showed that the RF model outperformed the SVR and ANN models in the inversion of PM_2.5 in the YRD region, with the model-fitting and cross-validation coefficients of determination R² reached 0.917 and 0.691, mean absolute error (MAE) values were 1.026 μg m⁻³ and 2.353 μg m⁻³, and root mean square error (RMSE) values were 1.413 μg m⁻³, and 3.144 μg m⁻³, respectively. PM_2.5 concentrations during COVID-19 in 2020 have decreased by 3.61 μg m⁻³ compared to that during the same period of 2019 in the YRD region. The results of this study provide a cost-effective method of air pollution exposure assessment and help provide insight into the atmospheric changes under strong government controlling strategies. Full article

(This article belongs to the Special Issue Artificial Intelligence in Remote Sensing of Atmospheric Environment)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Artificial Intelligence in Remote Sensing of Atmospheric Environment

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (17 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI