Methods for automatic cloud classification from MODIS data
- 作者: Astafurov V.1,2, Kuriyanovich K.2, Skorokhodov A.2
-
隶属关系:
- Tomsk State University of Control Systems and Radioelectronics
- Zuev Institute of Atmospheric Optics, Siberian Branch
- 期: 卷 52, 编号 9 (2016)
- 页面: 1110-1119
- 栏目: Studying Atmospheric Processes from Space
- URL: https://journals.rcsi.science/0001-4338/article/view/148514
- DOI: https://doi.org/10.1134/S0001433816090061
- ID: 148514
如何引用文章
详细
In this paper, different texture-analysis methods are used to describe different cloud types in MODIS satellite images. A universal technique is suggested for the formation of efficient sets of textural features using the algorithm of truncated scanning of the features for different classifiers based on neural networks and cluster-analysis methods. Efficient sets of textural features are given for the considered classifiers; the cloud-image classification results are discussed. The characteristics of the classification methods used in this work are described: the probabilistic neural network, K-nearest neighbors, self-organizing Kohonen network, fuzzy C-means, and density clustering algorithm methods. It is shown that the algorithm based on a probabilistic neural network is the most efficient. It provides for the best classification reliability for 25 cloud types and allows the recognition of 11 cloud types with a probability greater than 0.7. As an example, the cloud classification results are given for the Tomsk region. The classifications were carried out using full-size satellite cloud images and different methods. The results agree with each other and agree well with the observational data from ground-based weather stations.
作者简介
V. Astafurov
Tomsk State University of Control Systems and Radioelectronics; Zuev Institute of Atmospheric Optics, Siberian Branch
编辑信件的主要联系方式.
Email: astafurov@iao.ru
俄罗斯联邦, Tomsk; Tomsk
K. Kuriyanovich
Zuev Institute of Atmospheric Optics, Siberian Branch
Email: astafurov@iao.ru
俄罗斯联邦, Tomsk
A. Skorokhodov
Zuev Institute of Atmospheric Optics, Siberian Branch
Email: astafurov@iao.ru
俄罗斯联邦, Tomsk