CESBIO ALCD Snow masks

"CNES ALCD Snow masks" is a reference dataset for snow masks based on Sentinel-2 (L1C) images. This dataset has been generated with the Active Learning for Cloud Detection (ALCD) software developed by CNES/Cesbio, that enables to generate any kind of reference mask using satellite images. This procedure involves between 1 or 2 hours of work to generate each reference image : create reference points on the image ( land, cloud, snow...) manually, do the training (based on Random Forest of OTB) and prediction with ALCD, add new reference points for the most problematic areas, repeat new training/predictions as many times as necessary (usually 3-5 iterations), and finally, do a manual correction of persistent errors. The dataset contains 10 folders each containing 1 geotiff file (scene) at 20m resolution for 110kmx110km size, 1 quicklook of the scene before and 1 quicklook after classification. The content of pixels of the geotiff files follows the following naming rule : 0 = nodata; 3 = Cloud; 5 = Land; 7 = Snow Format of folder names: {location}_{tile}_{YYYMMDD} Where tile = reference Sentinel 2 tile (Cesbio post) , YYYYMMDD = date of Sentinel 2 acquisition, location = name of the site (ex: "PYR" = Pyrenees) Example: PYR_31TCH_20191117

CNES ALCD 雪覆盖掩码数据集（CNES ALCD Snow masks）是一款基于哨兵二号（Sentinel-2）L1C级影像的雪覆盖掩码参考数据集。该数据集由CNES/Cesbio开发的云检测主动学习软件（Active Learning for Cloud Detection, ALCD）生成，该工具可基于卫星影像生成各类参考掩码。生成单幅参考影像需耗时1至2小时，具体流程如下：手动在影像上标注参考点（陆地、云、雪等）；基于OTB的随机森林开展模型训练，并通过ALCD工具完成预测；针对问题突出的区域补充新的参考点，按需重复训练与预测流程（通常需3至5轮迭代）；最后对持续存在的错误进行人工校正。本数据集共包含10个文件夹，每个文件夹内均包含1幅分辨率为20米、尺寸为110km×110km的GeoTIFF影像（场景文件），以及分类前与分类后的场景快速预览图各1份。GeoTIFF文件的像素值遵循如下编码规则：0代表无数据（nodata），3代表云，5代表陆地，7代表雪。文件夹命名格式为：{location}_{tile}_{YYYMMDD}，其中tile为参考Sentinel-2瓦片（Cesbio后处理结果），YYYMMDD为Sentinel-2影像的采集日期，location为研究区域名称（例如："PYR"代表比利牛斯山脉）。示例：PYR_31TCH_20191117

搜集汇总

背景与挑战

背景概述

CESBIO ALCD Snow masks是基于Sentinel-2 (L1C)图像的雪掩膜参考数据集，包含10个20米分辨率的geotiff文件，用于区分无数据、云、土地和雪。数据集通过ALCD软件生成，结合了手动标注和机器学习方法，适用于GIS和水文学研究。