ELC10: European 10 m resolution land cover map 2018

Refer to preprint here: https://arxiv.org/abs/2104.10922 A land cover classification for Europe at 10 m resolution produced with a machine learning workflow driven by Sentinel optical and radar satellite imagery. The classification model was trained on land cover reference data form the LUCAS (Land Use/Cover Area frame Survey) dataset. The map represents conditions in 2018. The methodology is currently under review, but this will be updated as soon as the paper is available online. Please refer to the publication for accuracy estimates and usage guidelines. The map is split up into a number of raster tiles with the coordinate reference system "EPSG:3035 - ERTS89 / LAEA Europe".The filename of each tile is in the form baseFilename-yMin-xMin where xMin and yMin are the coordinates of each tile within the overall bounding box of the entire ELC10 image. The pixel values, their definitions and suggested hex color codes include: 0 (not mapped #000000), 1 (Artificial land, #CC0303), 2 (Cropland, #CDB400), 3 (Woodland, #235123), 4 (Shrubland, #B76124), 5 (Grassland, #92AF1F), 6 (Bare land, #F7E174), 7 (Water/permanent snow/ice, #2019A4), 8 (Wetland, #AEC3D6).请参阅预印本：https://arxiv.org/abs/2104.10922。本数据集为欧洲10米分辨率土地覆盖分类产品，采用基于哨兵（Sentinel）光学与雷达卫星影像驱动的机器学习工作流生成。该分类模型的训练数据取自LUCAS（土地利用/覆盖面积框架调查，Land Use/Cover Area frame Survey）数据集。本土地覆盖图反映了2018年的地表状况。本研究方法目前处于审稿阶段，待论文正式上线后将及时更新相关信息。如需了解精度评估与使用规范，请参阅正式发表的论文。该数据集的土地覆盖图采用"EPSG:3035 - ERTS89 / LAEA Europe"坐标参考系统，并被分割为若干栅格瓦片（raster tiles）。每个瓦片的文件名格式为`baseFilename-yMin-xMin`，其中xMin与yMin为该瓦片在整个ELC10影像全局边界框内的坐标值。各像素值对应的含义及推荐十六进制色码如下：0（未映射，#000000）、1（人工地表，#CC0303）、2（耕地，#CDB400）、3（林地，#235123）、4（灌丛地，#B76124）、5（草地，#92AF1F）、6（裸地，#F7E174）、7（水体/永久积雪/冰川，#2019A4）、8（湿地，#AEC3D6）。