Glacial Lake Image Dataset for "Efficient glacial lake mapping by leveraging deep transfer learning and a new annotated glacial lake dataset"
收藏资源简介：
Glacial lake dataset for the paper "Efficient glacial lake mapping by leveraging deep transfer learning and a new annotated glacial lake dataset" (https://doi.org/10.1016/j.jhydrol.2025.133072) The GLID dataset contains a total of 18,367 samples, and the size of each sample is 512*512. Each sample consists of an image and a corresponding label. Four glacial lake types including supraglacial lake, proglacial lake, ice-marginal lake, and unconnected glacial lake are involved. The pixel value of the glacier lake in annotation map is labeled 255 and background is labeled 0. GLID.rar contains the training dataset (16,000 samples), and val.zip contains the validation dataset (2,367 samples). GLID_annotation.zip contains the annotated shapefile of GLID with a CRS of WGS 84. Optical_images_source.xlsx contains the optical images ID/names and acquisition time of each platform (e.g., WV2, LC08, S2B, and GF02) used in GLID. Transferability validation.zip contains the images, labels, and predictions for transferability validation, which is independent of GLID (not used for model training or validation). The file structure is shown below: Transferability validation.zip images AS.tif GL.tif NA.tif SA.tif labels AS_gt.tif GL_gt.tif NA_gt.tif SA_gt.tif predictions AS_pred.tif GL_pred.tif NA_pred.tif SA_pred.tif AS, GL, NA, and SA represent Asia, Greenland, North America, and South America, respectively. Four high-quality Landsat-8/9 images (each cloud cover less than 6%) were used for testing, and we manually annotated the glacial lakes in each image as labels. The pixel value of the glacier lake in annotation map is labeled 255 and background is labeled 0. Files in transferability validation.zip have a same CRS of WGS 84. If you find this dataset is helpful in your research, please consider cite this paper: Ma D, Li J, Jiang L. 2025. Efficient glacial lake mapping by leveraging deep transfer learning and a new annotated glacial lake dataset. Journal of Hydrology 657: 133072.
用于论文《借助深度迁移学习与全新标注冰湖数据集实现高效冰湖制图》（https://doi.org/10.1016/j.jhydrol.2025.133072）的GLID数据集。 GLID数据集共计包含18367个样本，每个样本尺寸为512×512，由一幅光学影像与对应的标注标签组成。该数据集涵盖冰面湖、冰前湖、冰缘湖与孤立冰湖四类冰湖。标注影像中，冰湖区域的像素值设为255，背景区域设为0。 GLID.rar压缩包内含训练集（共计16000个样本），val.zip压缩包内含验证集（共计2367个样本）。 GLID_annotation.zip压缩包内含GLID数据集的标注形状文件，其坐标系为WGS 84。 Optical_images_source.xlsx文件收录了GLID数据集所用各影像平台（如WV2、LC08、S2B、GF02）的光学影像ID/名称与获取时间。 Transferability validation.zip压缩包内含迁移性验证所用的影像、标签与模型预测结果，该部分独立于GLID数据集，未参与模型训练与验证流程。其文件结构如下： - images文件夹：内含AS.tif、GL.tif、NA.tif、SA.tif - labels文件夹：内含AS_gt.tif、GL_gt.tif、NA_gt.tif、SA_gt.tif - predictions文件夹：内含AS_pred.tif、GL_pred.tif、NA_pred.tif、SA_pred.tif 其中AS、GL、NA、SA分别代表亚洲、格陵兰、北美与南美。本次验证共使用4幅云量均低于6%的高质量陆地卫星Landsat-8/9影像，并手动标注每幅影像中的冰湖作为标签。标注影像中冰湖区域像素值设为255，背景区域设为0。Transferability validation.zip压缩包内所有文件的坐标系均为WGS 84。 若本数据集对您的研究有所助益，请引用以下论文： Ma D, Li J, Jiang L. 2025. Efficient glacial lake mapping by leveraging deep transfer learning and a new annotated glacial lake dataset. Journal of Hydrology 657: 133072.
