The fully executable procedure of the U-Net model combined with the Multi-textRG algorithm to achieve fine ice-water classification.

This code source is related to the manuscript titled "Combining the U-Net model and a Multi-textRG algorithm for fine SAR ice-water classification", which will be submitted to the journal---The Cryosphere.  

This code source is developed based on the U-Net CNN model (coppyed from https://platform.ai4eo.eu/auto-ice/data) and a Multi-textRG algorithm proposed by us to achieve the Arctic sea-ice and water classification in high precision and with great performance for depicting ice edge details, under various conditions covering both summer and winter seasons. 

• 1_AI4ArcticSeaIceChallenge-U-Net  --->  need to be run in Pycharm platform.
• 2_SAR_denoise;  3_glcm_textures_SAR_dual_polarizations; 4_SAR_Multi-textRG_algorithm; 5_newSIC_labels  --->  need to be run in MATLAB.

2)  "data.zip" includes the testing files.  ---->  there are "data_supports" and "example_processings" folders. 

• the processing results wil be saved in "example_processings" folder.

3)  The "ready-to-train-fused_01.zip"  to "ready-to-train-fused_10.zip" include 200 scenes of data-fused SIC labels.  They are used for further training or model experiments.  

• Do not need to download them at the first. Using the "codes.zip" and "data.zip" can help you understand the method usage. 
• The "ready-to-train-fused_11.zip"  to "ready-to-train-fused_21.zip" include another 332 scenes of data-fused SIC labels accessible with doi: 10.5281/zenodo.10974340,  https://zenodo.org/records/10974340.

Please feel free to download and test the method, and to give your valuable comments.