Abstract
Cloud recognition is a basic task in ground meteorological observation. It is of great significance to accurately identify cloud types from long-time-series satellite cloud images for improving the reliability and accuracy of weather forecasting. However, different from ground-based cloud images with a small observation range and easy operation, satellite cloud images have a wider cloud coverage area and contain more surface features. Hence, it is difficult to effectively extract the structural shape, area size, contour shape, hue, shadow and texture of clouds through traditional deep learning methods. In order to analyze the regional cloud type characteristics effectively, we construct a China region meteorological satellite cloud image dataset named CRMSCD, which consists of nine cloud types and the clear sky (cloudless). In this paper, we propose a novel neural network model, UATNet, which can realize the pixel-level classification of meteorological satellite cloud images. Our model efficiently integrates the spatial and multi-channel information of clouds. Specifically, several transformer blocks with modified self-attention computation (swin transformer blocks) and patch merging operations are used to build a hierarchical transformer, and spatial displacement is introduced to construct long-distance cross-window connections. In addition, we introduce a Channel Cross fusion with Transformer (CCT) to guide the multi-scale channel fusion, and design an Attention-based Squeeze and Excitation (ASE) to effectively connect the fused multi-scale channel information to the decoder features. The experimental results demonstrate that the proposed model achieved 82.33% PA, 67.79% MPA, 54.51% MIoU and 70.96% FWIoU on CRMSCD. Compared with the existing models, our method produces more precise segmentation performance, which demonstrates its superiority on meteorological satellite cloud recognition tasks.
Highlights
According to the global cloud cover data provided by the International Satellite CloudClimatology Project (ISCCP), more than 66% area above the earth is covered by a large number of clouds [1]
We propose a cloud recognition network model based on the U-shaped architecture, in which the transformer is introduced to build the encoder and encoder–decoder connection, and the attention mechanism is designed to integrate the features of both the encoder and decoder
We propose the U-shape Attention-based Transformer Net (UATNet) model and introduce a transformer into meteorological satellite cloud recognition task, which solves the problem of convolutional neural network (CNN) receptive field limitation and captures global context information effectively while ensuring the computing efficiency
Summary
According to the global cloud cover data provided by the International Satellite CloudClimatology Project (ISCCP), more than 66% area above the earth is covered by a large number of clouds [1]. An important member of the climate system, is the most common, extremely active and changeable weather phenomenon. It directly affects the radiation and water cycle of the earth-atmosphere system, and plays an important role in the global energy budget and water resources distribution [2,3]. Cloud observation is a significant content in meteorological work It is fundamental for weather forecasting and climate research to correctly identifying such elements as cloud shape, cloud amount and cloud height, as well as the distribution and change of clouds, which plays a key role in navigation and positioning, flight support and national economic development [4]. There are four main types of cloud observation: ground-based artificial observation, groundbased instrument observation, aircraft or balloon observation and meteorological satellite
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
