Clouds have an enormous influence on the Earth's energy balance, climate, and weather. Cloud types have different cloud radiative effects, which is an essential indicator of the cloud effect on radiation. Therefore, identifying the cloud type is important in meteorology. In this letter, we propose a new convolutional neural network model, called CloudNet, for accurate ground‐based meteorological cloud classification. We build a ground‐based cloud data set, called Cirrus Cumulus Stratus Nimbus, which consists of 11 categories under meteorological standards. The total number of cloud images is three times that of the previous database. In particular, it is the first time that contrails, a type of cloud generated by human activity, have been taken into account in the ground‐based cloud classification, making the Cirrus Cumulus Stratus Nimbus data set more discriminative and comprehensive than existing ground‐based cloud databases. The evaluation of a large number of experiments demonstrates that the proposed CloudNet model could achieve good performance in meteorological cloud classification.

Drought has become a major threat to local sustainable development in dryland Asia, one of the largest grassland ecosystems in the world. However, empirical‐ and science‐based evidence regarding the extent of drought changes and the future trends of these changes in dryland Asia is variable and incomplete. Here, we first investigate the historical variations in drought conditions in dryland Asia, as measured by the drought intensity and arid area, using three widely used drought indices (the Palmer Drought Severity Index, the Standardized Precipitation Index, and the Standardized Precipitation Evapotranspiration Index). Then, we use Bayesian model averaging to reproduce the future drought conditions under two representative concentration pathways (RCP2.6 and RCP4.5) from the Coupled Model Intercomparison Project Phase 5 Earth system models. The Palmer Drought Severity Index, Standardized Precipitation Index, and Standardized Precipitation Evapotranspiration Index illustrate that dryland Asia has experienced an overall drying trend and an expansion of arid areas over the past 100 years (1901–2016). Both temperature and precipitation are projected to increase under both the 1.5 and 2.0 °C warming scenarios compared with the values from the reference period (1986–2005). The projected drought conditions in the 1.5 and 2.0 °C warming scenarios will worsen, especially across Kazakhstan and Northwest China. We found that the drought conditions under the 2.0 °C warming conditions will not be as severe as those under the 1.5 °C warming conditions due to the mitigating effect of the projected precipitation increase under RCP4.5. These results call for short‐term and long‐term mitigation and adaptation measurements for drought events in dryland Asia.

A team effort to develop a Community Integrated Earth System Model (CIESM) was initiated in China in 2012. The model was based on NCAR Community Earth System Model (Version 1.2.1) with several novel developments and modifications aimed to overcome some persistent systematic biases, such as the double Intertropical Convergence Zone problem and underestimated marine boundary layer clouds. Aerosols' direct and indirect effects are prescribed using the MACv2‐SP approach and data sets. The spin‐up of a 500‐year preindustrial simulation and three historical simulations are described and evaluated. Prominent improvements include alleviated double Intertropical Convergence Zone problem, increased marine boundary layer clouds, and better El Niño Southern Oscillation amplitude and periods. One deficiency of the model is the significantly underestimated Arctic and Antarctic sea ice in warm seasons. The historical warming is about 0.55 °C greater than observations toward 2014. CIESM has an equilibrium climate sensitivity of 5.67 K, mainly resulted from increased positive shortwave cloud feedback. Our efforts on porting and redesigning CIESM for the heterogeneous Sunway TaihuLight supercomputer are also introduced, including some ongoing developments toward a future version of the model.

In this paper, we present long-term observations of atmospheric nitrogen dioxide (NO2) and formaldehyde (HCHO) in Nanjing using a Multi-AXis Differential Optical Absorption Spectroscopy (MAX-DOAS) instrument. Ground-based MAX-DOAS measurements were performed from April 2013 to February 2017. The MAX-DOAS measurements of NO2 and HCHO vertical column densities (VCDs) are used to validate ozone monitoring instrument (OMI) satellite observations over Nanjing. The comparison shows that the OMI observations of NO2 correlate well with the MAX-DOAS data with Pearson correlation coefficient (R) of 0.91. However, OMI observations are on average a factor of 3 lower than the MAX-DOAS measurements. Replacing the a priori NO2 profiles by the MAX-DOAS profiles in the OMI NO2 VCD retrieval would increase the OMI NO2 VCDs by ∼30 % with correlation nearly unchanged. The comparison result of MAX-DOAS and OMI observations of HCHO VCD shows a good agreement with R of 0.75 and the slope of the regression line is 0.99. An age-weighted backward-propagation approach is applied to the MAX-DOAS measurements of NO2 and HCHO to reconstruct the spatial distribution of NO2 and HCHO over the Yangtze River Delta during summer and winter time. The reconstructed NO2 fields show a distinct agreement with OMI satellite observations. However, due to the short atmospheric lifetime of HCHO, the backward-propagated HCHO data do not show a strong spatial correlation with the OMI HCHO observations. The result shows that the MAX-DOAS measurements are sensitive to the air pollution transportation in the Yangtze River Delta, indicating the air quality in Nanjing is significantly influenced by regional transportation of air pollutants. The MAX-DOAS data are also used to evaluate the effectiveness of air pollution control measures implemented during the Youth Olympic Games 2014. The MAX-DOAS data show a significant reduction of ambient aerosol, NO2 and HCHO (30 %–50 %) during the Youth Olympic Games. Our results provide a better understanding of the transportation and sources of pollutants over the Yangtze River Delta as well as the effect of emission control measures during large international events, which are important for the future design of air pollution control policies.

Weather phenomenon recognition notably affects many aspects of our daily lives, for example, weather forecast, road condition monitoring, transportation, agriculture, forestry management, and the detection of the natural environment. In contrast, few studies aim to classify actual weather phenomenon images, usually relying on visual observations from humans. To the best of our knowledge, the traditional artificial visual distinction between weather phenomena takes a lot of time and is prone to errors. Although some studies improved the recognition accuracy and efficiency of weather phenomenon by using machine learning, they identified fewer types of weather phenomena. In this paper, a novel deep convolutional neural network (CNN) named MeteCNN is proposed for weather phenomena classification. Meanwhile, we establish a data set called the weather phenomenon database (WEAPD) containing 6,877 images with 11 weather phenomena, which has more categories than the previous data set. The classification accuracy of MeteCNN on the WEAPD testing set is around 92%, and the experimental result demonstrates the superiority and effectiveness of the proposed MeteCNN model. Realizing the automatic and high‐quality classification of weather phenomena images can provide a reference for future research on weather image classification and weather forecasting.

Ice clouds are mostly composed of different ice crystal habits. It is of great importance to classify ice crystal habits seeing as they could greatly impact single‐scattering properties of ice crystal particles. The single‐scattering properties play an important role in the study of cloud remote sensing and the Earth's atmospheric radiation budget. However, there are countless ice crystals with different shapes in ice clouds, and the task of empirical classification based on naked‐eye observations is unreliable, time consuming and subjective, which leads to classification results having obvious uncertainties and biases. In this paper, the images of ice crystals observed from airborne Cloud Particle Imager in China are used to establish an ice crystal data set called Ice Crystals Database in China, which consists of 10 habit categories containing over 7,000 images. We propose an automatic classification model of ice crystal habits, called TL‐ResNet152, which is a deep convolutional neural network based on the newly developed method of transfer learning. The results show that the TL‐ResNet152 model could achieve reliable performance in ice crystal habits classification with the accuracy of 96%, which is far more accurate than traditional classification methods. Achieving high‐precision automatic classification of ice crystal habits will help us better understand the radiation characteristics of ice clouds.