Deep learning satellite data cloud detection method supported by hyperspectral data

Abstract

The invention discloses a deep learning satellite data cloud detection method supported by hyperspectral data. The method comprises the following steps: selecting enough cloud and clear sky pixels toconstruct a hyperspectral data sample library, and performing analog computation on the hyperspectral pixel sample library according to parameters such as a spectral response function and a waveband width of a to-be-detected sensor to obtain a cloud and clear sky surface pixel library of the to-be-detected sensor; based on a Keras deep learning framework, designing a deep BP neural network for cloud detection, inputting multispectral sample data obtained through simulation into the network for training and learning, and obtaining a multispectral sensor cloud detection rule based on spectral characteristics; based on a Markov random field model, optimizing a cloud detection result by utilizing an iterative condition mode algorithm, and removing a part of misclassification and misclassification errors of cloud detection. According to the method, various sensor data are selected and compared with a cloud coverage result of artificial visual interpretation for analysis, and the result shows that the algorithm achieves a better cloud detection effect and can meet the requirements of data application for cloud detection.

Description

technical field [0001] The invention relates to a cloud detection method using satellite data, in particular to a hyperspectral data-supported deep learning satellite data cloud detection method. Background technique [0002] In optical remote sensing images, cloud occlusion is a common phenomenon and has become the main factor restricting the ability of optical remote sensing to observe the earth. Statistical analysis of MODIS cloud mask data shows that clouds cover approximately 67 percent of the Earth's surface. Among them, the cloud coverage over the land is about 55%, and it is related to seasonal changes; the cloud coverage over the ocean is higher than that of the land, about 72%, and there is no obvious seasonal change characteristic. Affected by cloud occlusion, optical sensors cannot effectively receive spectral information from surface objects, resulting in imaging deviations, resulting in attenuation or even complete loss of surface information in cloud-covered ...

AI Technical Summary

Problems solved by technology

Due to the wide range of spectral response capabilities of sensors, it is often necessary to study different cloud detection algorithms for different remote sensing data, which brings great difficulties to the promotion and application of algorithms.

Images