Search

Abstract Negative Air Ions (NAIs), essential for environmental and human health, facilitate air purification and offer antimicrobial benefits. Our study achieves hourly estimations of NAIs using a machine learning framework, developed from a multi‐layer selection pipeline of over 200 variables, to identify the key determinants critical for adapting to high‐resolution NAIs dynamics. Addressing site sparsity and NAIs volatility, we introduced a hybrid stacking incorporating pseudo sites generated from Kriging Spatiotemporal Augmentation (KSTA) to mitigate spatial overfitting. Our approach, validated in Zhejiang, China, demonstrates exceptional accuracy, achieving R2 values of 0.90 (sample‐based), 0.85 (temporal‐based), and 0.79 (site‐based). This work not only sheds light on NAIs behavior in relation to diurnal shifts, land use, and environmental events, but also integrates a health grading system, enhancing public health strategies through precise air quality assessment.

Abstract Surface visibility (SV), a key indicator of atmospheric transparency, is used widely in the fields of environmental monitoring, transportation, and aviation. However, the sparse distribution and limited number of SV monitoring sites make it difficult to fulfill the urgent need for spatiotemporally seamless fine-scale monitoring. Here, we developed the operational real-time SV retrieval (RT-SVR) framework for China that incorporates information from multiple data sources, including Chinese Land Data Assimilation System meteorological data, in situ observations, and other ancillary data. Seamless hourly SV data with 6.25-km spatial resolution are available in real time via the operational RT-SVR model, which was built using a two-layer stacked ensemble approach that combines multiple machine learning algorithms and a deep learning module. Sample-based cross-validation of the RT-SVR model on approximately 41.3 million data pairs revealed strong robustness and high accuracy, with a Pearson correlation coefficient (R) value of 0.95 and a root mean square error (RMSE) of 3.17 km. An additional hindcast-validation experiment, performed with continuous observations obtained over one year (approximately 20.8 million data pairs), demonstrated the powerful generalization capabilities of the RT-SVR model, albeit with slight degradation in performance (R = 0.85, RMSE = 5.28 km). The seamless hourly SV data with real-time update capability enable tracking of the generation, development, and dissipation of various low-SV events (e.g., fog, haze, and dust storms) in China. The developed framework might also prove useful for quantitative retrieval of aerosol-related parameters (e.g., PM2.5, PM10, and aerosol optical depth).

The basal channel is a morphological feature that widely exists at the bottom of ice shelves, which is mainly formed by the incision of warm water at the base of ice shelves. The study of the basal channel can contribute to further understanding the impact of global warming on polar ice shelves. In this article, the depression caused by the basal channel on the surface of an ice shelf is used to confirm and extract the channel's position. The automatic acquisition of the channel is realized by machine learning. To extract the basal channel more efficiently and minimize the subjectivity caused by visual interpretation, a neural network was applied for the first time, which effectively improved the accuracy of basal channel extraction. We took the manual extraction results of basal channels as the training set input from the model. The improved U-NET network model was used to classify the 79NG ice shelf area, and the extraction accuracy was 73.58%. Then, the trained model was extended to the Peterman ice shelf and Ryder ice shelf located in Greenland. The extraction accuracies were 75.54% and 72.70%, respectively.

Solar radiation drives many geophysical and biological processes in Antarctica, such as sea ice melting, ice sheet mass balance, and photosynthetic processes of phytoplankton in the polar marine environment. Although reanalysis and satellite products can provide important insight into the global scale of solar radiation in a seamless way, the ground-based radiation in the polar region remains poorly understood due to the harsh Antarctic environment. The present study attempted to evaluate the estimation performance of empirical models and machine learning models, and use the optimal model to establish a 35-year daily global solar radiation (DGSR) dataset at the Great Wall Station, Antarctica using meteorological observation data during 1986–2020. In addition, it then compared against the DGSR derived from ERA5, CRA40 reanalysis, and ICDR (AVHRR) satellite products. For the DGSR historical estimation performance, the machine learning method outperforms the empirical formula method overall. Among them, the Mutli2 model (hindcast test R2, RMSE, and MAE are 0.911, 1.917 MJ/m2, and 1.237 MJ/m2, respectively) for the empirical formula model and XGBoost model (hindcast test R2, RMSE, and MAE are 0.938, 1.617 MJ/m2, and 1.030 MJ/m2, respectively) for the machine learning model were found with the highest accuracy. For the austral summer half-year, the estimated DGSR agrees very well with the observed DGSR, with a mean bias of only −0.47 MJ/m2. However, other monthly DGSR products differ significantly from observations, with mean bias of 1.05 MJ/m2, 3.27 MJ/m2, and 6.90 MJ/m2 for ICDR (AVHRR) satellite, ERA5, and CRA40 reanalysis products, respectively. In addition, the DGSR of the Great Wall Station, Antarctica followed a statistically significant increasing trend at a rate of 0.14 MJ/m2/decade over the past 35 years. To our best knowledge, this study presents the first reconstruction of the Antarctica Great Wall Station DGSR spanning 1986–2020, which will contribute to the research of surface radiation balance in Antarctic Peninsula.

Abstract Precipitable water vapor (PWV), despite being the key factor for assessing climate change over the Tibetan Plateau (TP), is undersampled in this region due to the complex terrain and climate conditions therein. The fifth‐generation European Center for Medium‐Range Weather Forecasts Reanalysis (ERA5) and Second Modern‐Era Retrospective Analysis for Research and Applications (MERRA‐2) data sets are the two newly released global reanalyzes that provide hourly PWV products with a high spatiotemporal resolution for water vapor research. The accuracies of these two PWV products on the TP require a comprehensive and cautious assessment. In this study, the hourly PWV values derived from ERA5 and MERRA‐2 are systematically assessed by a comparison with 33 Global Navigation Satellite System (GNSS) stations from 2017 to 2018 over the TP. To improve the reliability of this evaluation, an enhanced Tm model and a PWV vertical correction model, namely, TP‐Tm and TP‐PWVC, respectively, are developed, and both models show better performance when compared against other widely used models. The accuracies of the ERA5‐ and MERRA‐2‐derived PWV at the 33 GNSS stations are very high; ERA5 has the smallest mean bias and root mean square (RMS) error of −0.08 and 1.77 mm, respectively, compared to those of 0.53 and 2.12 mm for MERRA‐2. In addition, the biases and RMS errors show significant regional and seasonal differences. The performance of ERA5 is slightly better than MERRA‐2, mainly due to its higher spatial resolution. The spatial distributions of the PWV derived from the two reanalyzes are consistent with the GNSS‐derived PWV distribution. The diurnal PWV variations derived from ERA5 are in good agreement with the diurnal variation of the GNSS‐derived PWV, whereas significant differences are observed for MERRA‐2 at several stations. These results indicate that ERA5 can provide more reliable hourly PWV estimates over the TP, which can help users further understand the strengths and weaknesses of these two PWV products and promote climate change research.

Solar radiation is the Earth’s primary source of energy and has an important role in the surface radiation balance, hydrological cycles, vegetation photosynthesis, and weather and climate extremes. The accurate prediction of solar radiation is therefore very important in both the solar industry and climate research. We constructed 12 machine learning models to predict and compare daily and monthly values of solar radiation and a stacking model using the best of these algorithms were developed to predict solar radiation. The results show that meteorological factors (such as sunshine duration, land surface temperature, and visibility) are crucial in the machine learning models. Trend analysis between extreme land surface temperatures and the amount of solar radiation showed the importance of solar radiation in compound extreme climate events. The gradient boosting regression tree (GBRT), extreme gradient lifting (XGBoost), Gaussian process regression (GPR), and random forest models performed better (poor) prediction capabilities of daily and monthly solar radiation. The stacking model, which included the GBRT, XGBoost, GPR, and random forest models, performed better than the single models in the prediction of daily solar radiation but showed no advantage over the XGBoost model in the prediction of the monthly solar radiation. We conclude that the stacking model and the XGBoost model are the best models to predict solar radiation.

With increasing public concerns on air pollution in China, there is a demand for long-term continuous PM2.5 datasets. However, it was not until the end of 2012 that China established a national PM2.5 observation network. Before that, satellite-retrieved aerosol optical depth (AOD) was frequently used as a primary predictor to estimate surface PM2.5. Nevertheless, satellite-retrieved AOD often encounter incomplete daily coverage due to its sampling frequency and interferences from cloud, which greatly affect the representation of these AOD-based PM2.5. Here, we constructed a virtual ground-based PM2.5 observation network at 1180 meteorological sites across China using the Extreme Gradient Boosting (XGBoost) model with high-density meteorological observations as major predictors. Cross-validation of the XGBoost model showed strong robustness and high accuracy in its estimation of the daily (monthly) PM2.5 across China in 2018, with R2, root-mean-square error (RMSE) and mean absolute error values of 0.79 (0.92), 15.75 μg/m3 (6.75 μg/m3) and 9.89 μg/m3 (4.53 μg/m3), respectively. Meanwhile, we find that surface visibility plays the dominant role in terms of the relative importance of variables in the XGBoost model, accounting for 39.3% of the overall importance.We then use meteorological and PM2.5 data in the year 2017 to assess the predictive capability of the model. Results showed that the XGBoost model is capable to accurately hindcast historical PM2.5 at monthly (R2 = 0.80, RMSE = 14.75 μg/m3), seasonal (R2 = 0.86, RMSE = 12.28 μg/m3), and annual (R2 = 0.81, RMSE = 10.10 μg/m3) mean levels. In general, the newly constructed virtual PM2.5 observation network based on high-density surface meteorological observations using the Extreme Gradient Boosting model shows great potential in reconstructing historical PM2.5 at ~1000 meteorological sites across China. It will be of benefit to filling gaps in AOD-based PM2.5 data, as well as to other environmental studies including epidemiology.

Abstract Accurate estimation of the spatiotemporal variations of solar radiation is crucial for assessing and utilizing solar energy, one of the fastest‐growing and most important clean and renewable resources. Based on observations from 2,379 meteorological stations along with scare solar radiation observations, the random forest (RF) model is employed to construct a high‐density network of daily global solar radiation (DGSR) and its spatiotemporal variations in China. The RF‐estimated DGSR is in good agreement with site observations across China, with an overall correlation coefficient (R) of 0.95, root‐mean‐square error of 2.34 MJ/m2, and mean bias of −0.04 MJ/m2. The geographical distributions of R values, root‐mean‐square error, and mean bias values indicate that the RF model has high predictive performance in estimating DGSR under different climatic and geographic conditions across China. The RF model further reveals that daily sunshine duration, daily maximum land surface temperature, and day of year play dominant roles in determining DGSR across China. In addition, compared with other models, the RF model exhibits a more accurate estimation performance for DGSR. Using the RF model framework at the national scale allows the establishment of a high‐resolution DGSR network, which can not only be used to effectively evaluate the long‐term change in solar radiation but also serve as a potential resource to rationally and continually utilize solar energy.

Precipitable water vapor (PWV) plays a vital role in climate research, especially for Antarctica in which meteorological observations are insufficient due to the adverse climate and topography therein. Reanalysis data sets provide a great opportunity for Antarctic water vapor research. This study investigates the climatological PWV means, variability and trends over Antarctica from four reanalyses, including the fifth generation of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis (ERA5), the Second Modern-Era Retrospective analysis for Research and Applications (MERRA-2), Japanese 55-year Reanalysis (JRA-55) and National Centers for Environmental Prediction/Department of Energy (NCEP/DOE), in the period of 2001–2018 based on radiosonde and GNSS observations. PWV data from the ERA5, MERRA-2, JRA-55 and NCEP/DOE have been evaluated by radiosonde and GNSS observations, showing that ERA5 and MERRA-2 perform better than JRA-55 and NCEP/DOE with mean root mean square (RMS) errors below 1.2 mm. The climatological PWV mean distribution over Antarctica roughly shows a decreasing trend from west to east, with the highest content in summer and the lowest content in winter. The PWV variability is generally small over Antarctica, showing a seasonal dependence that is larger in the cold season and smaller in the warm season. PWV trends for all reanalyses at most Antarctic regions are insignificant and most reanalyses present overall drying trends from 2001 to 2018, except for ERA5 exhibiting a moistening trend. PWV trends also show seasonal and regional dependence. All reanalyses are generally consistent with radiosonde and GNSS observations in reproducing the PWV means (mean differences within 1.1 mm), variability (mean differences within 3%) and trends (mean differences within 6.4% decade−1) over Antarctica, except for NCEP/DOE showing spurious variability and trends in East Antarctica. Results can help us further understand these four reanalysis PWV products and promote climate research in Antarctica.

The verification and correction of CALIPSO aerosol products is key to understanding the atmospheric environment and climate change. However, CALIPSO often cannot detect the full profile of aerosol for the low instrument sensitivity near the surface. Thus, a correction scheme for the aerosol extinction coefficient (AECs) in the planetary boundary layer (PBL) is proposed to improve the quality of the CALIPSO-based aerosol optical depth (AOD) at 532 nm. This scheme assumed that the aerosol is vertically and uniformly distributed below the PBL, and that the AECs in the whole PBL are equal to those at the top of the PBL; then, the CALIPSO AOD was obtained by vertically integrating AECs throughout the whole atmosphere. Additionally, the CALIPSO AOD and corrected CALIPSO AOD were validated against seven ground-based sites across eastern China during 2007–2015. Our results show that the initial CALIPSO AOD obtained by cloud filtering was generally lower than that of the ground-based observations. After accounting for the AECs in the PBL, the adjustment method tended to improve the CALIPSO AOD data quality. The average R (slope) value from all sites was improved by 7% (46%). Further, the relative distance between the ground track of CALIPSO and the ground station exhibited an influence on the validation result of CALIPSO AOD. The retrieval precision of CALIPSO AOD worsened with the increase in water vapor in the atmosphere. Our findings indicate that our scheme significantly improves the accuracy of CALIPSO AOD, which will help to provide alternative AOD products in the presence of severe atmospheric pollution.

To assess the health risk of PM2.5, it is necessary to accurately estimate the actual exposure level of the population to PM2.5. However, the spatial distribution of PM2.5 may be inconsistent with that of the population, making it necessary for a high-spatial-resolution and refined assessment of the population exposure to air pollution. This study takes the Yangtze River Delta (YRD) Region as an example since it has a high-density population and a high pollution level. The brightness reflectance of night-time light, and MODIS-based (Moderate Resolution Imaging Spectroradiometer) vegetation index, elevation, and slope information are used as independent variables to construct a random-forest (RF) model for the estimation of the population spatial distribution, before any combination with the PM2.5 data retrieved from MODIS. This enables assessment of the population exposure to PM2.5 (i.e., intensity of population exposure to PM2.5 and population-weighted PM2.5 concentration) at a 3-km resolution, using the year 2013 as an example. Results show that the variance explained for the RF-model-estimated population density reaches over 80%, while the estimated errors in half of counties are < 20%, indicating the high accuracy of the estimated population. The spatial distribution of population exposure to PM2.5 exhibits an obvious urban−suburban−rural difference consistent with the population distribution but inconsistent with the PM2.5 concentration. High and low PM2.5 concentrations are mainly distributed in the northern and southern YRD Region, respectively, with the mean proportions of the population exposed to PM2.5 concentrations > 35μg/m3 close to 100% in all four seasons. A high-level population exposure to PM2.5 is mainly found in Shanghai, most of the Jiangsu Province, the central Anhui Province, and some coastal cities of the Zhejiang Province. The highest risk of population exposure to PM2.5 occurs in winter, followed by spring and autumn, and the lowest in summer, consistent with the PM2.5 seasonal variation. Seasonal-averaged population-weighted PM2.5 concentrations are different from PM2.5 concentrations in the region, which are closely related to the urban-exposed population density and pollution levels. This work provides a novel assessment of the proposed population-density exposure to PM2.5 by using multi-satellite retrievals to determine the high-spatial-resolution risk of air pollution and detailed regional differences in the population exposure to PM2.5.

An extreme haze event occurred in the Beijing area from 17 to 23 December 2015. Ground-based measurements and satellite observations during this event were used to further our understanding of the formation process of haze pollution and aerosol optical properties. The results suggest that high relative humidity, poor diffusion conditions (low wind speed and stable stratification) and favorable secondary transformation conditions under the hygroscopic growth of aerosol and high emissions led to this serious haze episode. During the haze period, the daily average value was 1.15 and 0.42 for aerosol optical depth (AOD500nm) and columnar water-vapor (CWV, in cm), respectively. On 19 December, the correlation coefficient between CWV and AOD500nm was 0.91, indicating the effect of hygroscopic growth of fine-mode articles. The daily average values for Ångström exponent, fine-mode fraction, aerosol absorption optical depth, and Ångström absorption exponent were 1.19, 0.81, 0.11 and 1.47, respectively, which suggests that fine aerosol particles were dominant in the atmosphere and fine-mode particles were the dominant contributor to atmospheric extinction during the haze period. Moreover, it also reflects that there were more absorbing aerosol particles during the haze period. Compared with other polluted periods with a bimodal distribution, there was an obvious trimodal distribution on 19 December. There were three peaks at radii of about 0.1 μm, 0.5–0.8 μm and 4 μm. Satellite observations show that there was an obvious aerosol layer in the Beijing area during the haze period, concentrated at ground level to within 2 km in the upper layers. The types of aerosol were mainly composed of mixed pollution aerosols.