A sea ice type remote sensing classification method based on convolution neural network

Abstract

The invention discloses a sea ice type remote sensing classification method based on a convolution neural network, and belongs to the field of remote sensing geoscience application technology. The method uses satellite radar altimeter data to classify sea ice (divided into multi-year ice, one-year ice and open water). The steps include obtaining longitude and latitude coordinates of measurement points from altimeter data and radar echo waveform; downloading the sea ice type data and extracting the sea ice type information at the corresponding measurement point. The extracted data information is spatially matched and converted into vector point data with longitude and latitude coordinates. The radar echo waveform and the corresponding sea ice type are used as training data to train the convolution neural network, and the radar echo waveform to be classified is used to identify the sea ice type. After classification, the sea ice types are marked on the vector data. The tagged vector dataare processed by projection transformation, raster transformation and spatial resampling to obtain the sea ice type of the whole study area.

Description

technical field [0001] The invention relates to a sea ice type remote sensing classification method based on a convolutional neural network, belonging to the technical field of remote sensing applications. technical background [0002] Changes in sea ice type are an important indicator of climate change, with changes affecting sea ice thickness inversions, ship routing, and other important human polar activities. Early sea ice type data can only be obtained through manual field surveys. Later, optical and SAR remote sensing images can be used to classify sea ice. However, due to the small space coverage of remote sensing images, optical images are greatly affected by light and clouds. Due to the relatively high cost and other difficult constraints, it is difficult to achieve large-scale sea ice classification. With the development of satellite radar altimeters, altimeter data can be used to classify sea ice. Although altimeters are often used to retrieve the thickness of s...

AI Technical Summary

Problems solved by technology

Early sea ice type data can only be obtained through manual field surveys. Later, optical and SAR remote sensing images can be used to classify sea ice. However, due to the small space coverage of remote sensing images, optical images are greatly affected by light and clouds. Difficult constraints such as relatively high costs make it difficult to achieve large-scale sea ice classification

Images