Open AccessA Novel Computer-Aided Cloud Type Classification Method Based on Convolutional Neural Network with Squeeze-And- Excitation
Author(s) -
Guanshen Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1802/3/032051
Subject(s) - cloud computing , convolutional neural network , computer science , deep learning , set (abstract data type) , artificial neural network , enhanced data rates for gsm evolution , artificial intelligence , programming language , operating system
Clouds have a huge impact on the energy balance, climate and weather of the earth. Cloud types have different cloud radiation effects, which is an important indicator of cloud radiation effects. Therefore, determining the type of cloud is of great significance in meteorology. In this paper, the Convolutional neural network with Squeeze & Excitation Networks (SENet) are mainly used to solve this probelm. CNN can automatically learn the filters that need to be manually set before, and can learn complex edge, spatial and texture information in the image which are difficult for traditional methods to learn and extract. Moerover, a website and a deep learning framework are established to showcase the results of this article and to further develop our models and methods through open source methods.