CNES ALCD Open water masks

"CNES ALCD Open water masks" is a reference dataset for water masks based on Sentinel-2 (L1C) images. This dataset generation has been funded by CNES under the SWOT-Downstream programme. <strong>Generation Method</strong> 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 (water, 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. <strong>Dataset format (raw masks)</strong> The dataset contains 16 files (scenes) at 10m resolution for 110km x 110km size. The content of pixels of the scene files (geotiff) follows the following naming rule<br> 0 = Non Water observation (as land, snow)<br> 1 = Open Water observation<br> 255 = no data (as clouds) Format of file names: T{tile}_{YYYMMDD}_{site}_{season}.tif where : tile = reference Sentinel 2 tile (Cesbio post), YYYYMMDD = date of Sentinel 2 acquisition, site = name of the site, season = summer, winter Example : T30TXQ_20180201_Bordeaux_winter.tif T30UXU_20180708_Bretagne_summer.tif <br> <strong>Dataset format (inland masks)</strong><br> <br> This dataset has a version without coastal/ocean waters called "inland masks" aimed to characterize just inland waters. The dataset has been processed with the coastal lines of GSSHG layers : https://www.soest.hawaii.edu/pwessel/gshhg/ in H level, and using an erosion of 400m towards the continent.<br> Thus, any pixel closer to the GSSHG coast line than 400m and beyond will be considered as "no data"(value=255). The format of the pixels content and file naming follow the same rules as in the "raw masks" version.CNES ALCD 开放水域掩膜数据集（CNES ALCD Open water masks）是一款基于哨兵2号（Sentinel-2）L1C级影像构建的水域掩膜参考数据集。本数据集的生成由法国国家空间研究中心（Centre National d'Études Spatiales, CNES）在SWOT-Downstream项目框架下资助完成。 <strong>生成方法</strong> 本数据集采用法国国家空间研究中心/法国海洋科学与空间生物研究中心（CNES/Cesbio）开发的<strong>云检测主动学习（Active Learning for Cloud Detection, ALCD）</strong>软件生成，该工具可基于卫星影像生成各类参考掩膜。单幅参考影像的生成需耗时1至2小时：首先手动在影像上标注水域、陆地、云、积雪等参考点，随后基于OTB框架下的随机森林模型开展训练与ALCD预测；针对问题最为突出的区域新增参考点，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手动校正。 <strong>数据集格式（原始掩膜）</strong> 本数据集包含16幅10米分辨率的影像场景，单幅尺寸为110km×110km。场景文件采用GeoTIFF格式，其像素值遵循如下规则： 0 = 非水域观测（如陆地、积雪） 1 = 开放水域观测 255 = 无数据（如云覆盖区域） 文件名格式为：`T{tile}_{YYYMMDD}_{site}_{season}.tif`，各字段含义如下： - tile：参考哨兵2号影像瓦片（Cesbio后处理版本） - YYYYMMDD：哨兵2号影像采集日期 - site：研究区域名称 - season：拍摄季节，仅支持summer（夏季）与winter（冬季） 示例文件名如下：`T30TXQ_20180201_Bordeaux_winter.tif`、`T30UXU_20180708_Bretagne_summer.tif` <strong>数据集格式（内陆掩膜）</strong> 本数据集另有一个剔除近岸与远洋水域的版本，称为“内陆掩膜”，仅用于表征内陆水域。该版本基于GSSHG（通用海岸线与水文数据集，Generalized Shoreline and Hydrographic Dataset）图层的海岸线数据进行处理：采用https://www.soest.hawaii.edu/pwessel/gshhg/ 提供的H级海岸线数据，并向陆地方向执行400米的侵蚀缓冲。 据此，所有距离GSSHG海岸线不足400米且位于海域一侧的像素将被标记为无数据（像素值=255）。该版本的像素值规则与文件名格式均与“原始掩膜”版本保持一致。