By using twice daily high‐resolution radiosonde observations, here we assessed spatiotemporal variability of temperature inversion (TI) and its impact on PM_2.5 pollution levels in China from 2014 to 2020. It was found that both surface‐based inversion (SBI) and elevated inversion (EI) became increasingly frequent across China, at a rate of 1.42% a⁻¹ (1.15% a⁻¹) and 2.82% a⁻¹ (3.23% a⁻¹) at 0800 (2000) Beijing time (BJT), respectively. However, the intensity of SBI and EI at 0800 (2000) BJT decreased at −0.17 (−0.43) and −0.07 (−0.05) °C 100m⁻¹ decade⁻¹, making annual mean PM_2.5 increment induced by TI dip by 52.5% (73.2%) for the whole study period. Still positive TI induced PM_2.5 increments demonstrate an offsetting effect between TI and emission control on haze pollution, underscoring the importance of fully considering TI contribution when assessing the emission control effect on haze reduction.

Convolution-based recurrent neural networks and convolutional neural networks have been used extensively in spatiotemporal prediction. However, these methods tend to concentrate on fixed-scale spatiotemporal state transitions and disregard the complexity of spatiotemporal motion. Through statistical analysis, we found that the distribution of the spatiotemporal sequence and the variety of spatiotemporal motion state transitions exhibit some regularity. In light of these statistics and observations, we propose the Multi-scale Spatiotemporal Neural Network (MSSTNet), an end-to-end neural network based on 3D convolution. It can be separated into three major child modules: a distribution feature extraction module, a multi-scale motion state capture module, and a feature decoding module. Furthermore, the MSST unit is designed to model multi-scale spatial and temporal information in the multi-scale motion state capture module. We first conduct the experiments on the MovingMNIST dataset, which is the most commonly used dataset in the field of spatiotemporal prediction, MSSTNet can achieve state-of-the-art results for this dataset, and ablation experiments demonstrate that the MSST unit has positive significance for spatiotemporal prediction. In addition, this paper applies the model to valuable precipitation nowcasting, due to efficiently capturing the multi-scale information of distribution and motion, the new MSSTNet model can predict the real-world radar echo more accurately.

The study of cloud types is critical for understanding atmospheric motions and climate predictions; for example, accurately classified cloud products help improve meteorological predicting accuracies. However, the current satellite cloud classification methods generally analyze the threshold change in a single pixel and do not consider the relationship between the surrounding pixels. The classification development relies heavily on human recourses and does not fully utilize the data-driven advantages of computer models. Here, a new intelligent cloud classification method based on the U-Net network (CLP-CNN) is developed to obtain more accurate, higher frequency, and larger coverage cloud classification products. The experimental results show that the CLP-CNN network can complete a cloud classification task of 800 × 800 pixels in 0.9 s. The classification area covers most of China, and the classification task only needs to use the original L1-level data, which can meet the requirements of a real-time operation. With the Himawari-8 CLTYPE product and the CloudSat 2B-CLDCLASS product as the test comparison target, the CLP-CNN network results matched the Himawari-8 product highly by 76.8%. The probability of detection (POD) was greater than 0.709 for clear skies, deep-convection, and Cirrus–Stratus-type clouds. The probability of detection (POD) and accuracy are improved compared with other deep learning methods.

Urbanization is a pressing challenge for earth’s humans because it is changing not only natural environments but also agricultural lands. Yet, the consequences of cropland loss on pest insect populations that largely depend on these habitats remain largely unclear. We used a 17-year data set to investigate the dynamics of three moth pest species (i.e., striped stem borer, yellow stem borer, and pink stem borer) and their driving forces across the largest mega-urban region of China. Total abundance of three pest species is declined by about 80%, which was strongly associated with cropland loss during rapid urbanization. Our findings indicate that not only the increasing conversion of natural areas to human-dominated landscapes but also that of agricultural lands to urban landscapes can be critical to insect populations. It is therefore essential to monitor and understand the insect dynamics in rapidly urbanizing regions, which are currently found in many developing countries worldwide.