Labeled high-resolution orthoimagery time-series of an alluvial river corridor; Elwha River, Washington, USA.

Labeled high-resolution orthoimagery time-series of an alluvial river corridor; Elwha River, Washington, USA.
Daniel Buscombe, Marda Science LLC
There are two datasets in this data release:
1. Model training dataset. A manually (or semi-manually) labeled image dataset that was used to train and evaluate a machine (deep) learning model designed to identify subaerial accumulations of large wood, alluvial sediment, water, and vegetation in orthoimagery of alluvial river corridors in forested catchments. 
2. Model output dataset. A labeled image dataset that uses the aforementioned model to estimate subaerial accumulations of large wood, alluvial sediment, water, and vegetation in a larger orthoimagery dataset of alluvial river corridors in forested catchments. 
All of these label data are derived from raw gridded data that originate from the U.S. Geological Survey (Ritchie et al., 2018). That dataset consists of 14 orthoimages of the Middle Reach (MR, in between the former Aldwell and Mills reservoirs) and 14 corresponding Lower Reach (LR, downstream of the former Mills reservoir) of the Elwha River, Washington, collected between the period 2012-04-07 and 2017-09-22. That orthoimagery was generated using SfM photogrammetry (following Over et al., 2021) using a photographic camera mounted to an aircraft wing. The imagery capture channel change as it evolved under a ~20 Mt sediment pulse initiated by the removal of the two dams. The two reaches are the ~8 km long Middle Reach (MR) and the lower-gradient ~7 km long Lower Reach (LR). 
The orthoimagery have been labeled (pixelwise, either manually or by an automated process) according to the following classes (inter class in the label data in parentheses):
1. vegetation / other (0)
2. water (1)
3. sediment (2)
4. large wood (3)
1. Model training dataset.
Imagery was labeled using a combination of the open-source software Doodler (Buscombe et al., 2021; https://github.com/Doodleverse/dash_doodler) and hand-digitization using QGIS at 1:300 scale, rasterizeing the polygons, and gridded and clipped in the same way as all other gridded data. Doodler facilitates relatively labor-free dense multiclass labeling of natural imagery, enabling relatively rapid training dataset creation. The final training dataset consists of 4382 images and corresponding labels, each 1024 x 1024 pixels and representing just over 5% of the total data set. The training data are sampled approximately equally in time and in space among both reaches. All training and validation samples purposefully included all four label classes, to avoid model training and evaluation problems associated with class imbalance (Buscombe and Goldstein, 2022). 
Data are provided in geoTIFF format. The imagery and label grids (imagery) are reprojected to be co-located in the NAD83(2011) / UTM zone 10N projection, and to consist of 0.125 x 0.125m pixels.
Pixel-wise labels measurements such as these facilitate development and evaluation of image segmentation, image classification, object-based image-analysis (OBIA), and object-in-image detection models, and numerous potential other machine learning models for the general purposes of river corridor classification, description, enumeration, inventory, and process or state quantification. For example this dataset may serve in transfer learning contexts for application in different river or coastal environments or for different tasks or class ontologies.
Files:
1. Labels_used_for_model_training_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip, 63 MB, label tiffs
2. Model_training_ images1of4.zip, 1.5 GB, imagery tiffs
3. Model_training_ images2of4.zip, 1.5 GB, imagery tiffs
4. Model_training_ images3of4.zip, 1.7 GB, imagery tiffs
5. Model_training_ images4of4.zip, 1.6 GB, imagery tiffs
2. Model output dataset.
Imagery was labeled using a deep-learning based semantic segmentation model (Buscombe, 2023) trained specifically for the task using the Segmentation Gym (Buscombe and Goldstein, 2022) modeling suite. We use the software package Segmentation Gym (Buscombe and Goldstein, 2022) to fine-tune a Segformer (Xie et al., 2021) deep learning model for semantic image segmentation. We take the instance (i.e. model architecture and trained weights) of the model of Xie et al. (2021), itself fine-tuned on ADE20k dataset (Zhou et al., 2019) at resolution 512x512 pixels, and fine-tune it on our 1024x1024 pixel training data consisting of 4-class label images.
The spatial extent of the imagery in the MR is [455157.2494695878122002,5316532.9804129302501678 : 457076.1244695878122002,5323771.7304129302501678] (NAD83(2011) / UTM zone 10N). Imagery width is 15351 pixels and imagery height is 57910 pixels. The spatial extent of the imagery in the LR is [457704.9227139975992031,5326631.3750646486878395 : 459241.6727139975992031,5333311.0000646486878395] (NAD83(2011) / UTM zone 10N). Imagery width is 12294 pixels and imagery height is 53437 pixels. Data are provided in Cloud-Optimzed geoTIFF (COG) format. The imagery and label grids (imagery) are reprojected to be co-located in the NAD83(2011) / UTM zone 10N projection, and to consist of 0.125 x 0.125m pixels. All grids have been clipped to the union of extents of active channel margins during the period of interest.
Reach-wide pixel-wise measurements such as these facilitate comparison of wood and sediment storage at any scale or location. These data may be useful for studying the morphodynamics of wood-sediment interactions in other geomorphically complex channels, wood storage in channels, the role of wood in ecosystems and conservation or restoration efforts. 
Files:
1. Elwha_MR_labels_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip, 9.67 MB, label COGs from Elwha River Middle Reach (MR)
2. ElwhaMR_ imagery_ part1_ of_ 2.zip, 566 MB, imagery COGs from Elwha River Middle Reach (MR)
3. ElwhaMR_ imagery_ part2_ of_ 2.zip, 618 MB, imagery COGs from Elwha River Middle Reach (MR)
3. Elwha_LR_labels_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip, 10.96 MB, label COGs from Elwha River Lower Reach (LR)
4. ElwhaLR_ imagery_ part1_ of_ 2.zip, 622 MB, imagery COGs from Elwha River Middle Reach (MR)
5. ElwhaLR_ imagery_ part2_ of_ 2.zip, 617 MB, imagery COGs from Elwha River Middle Reach (MR) 
This dataset was created using open-source tools of the Doodleverse, a software ecosystem for geoscientific image segmentation, by Daniel Buscombe (https://github.com/dbuscombe-usgs) and Evan Goldstein (https://github.com/ebgoldstein). Thanks to the contributors of the Doodleverse!. Thanks especially Sharon Fitzpatrick (https://github.com/2320sharon) and Jaycee Favela for contributing labels. 
References
• Buscombe, D. (2023). Doodleverse/Segmentation Gym SegFormer models for 4-class (other, water, sediment, wood) segmentation of RGB aerial orthomosaic imagery (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8172858
• Buscombe, D., Goldstein, E. B., Sherwood, C. R., Bodine, C., Brown, J. A., Favela, J., et al. (2021). Human-in-the-loop segmentation of Earth surface imagery. Earth and Space Science, 9, e2021EA002085. https://doi.org/10.1029/2021EA002085
• Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym
• Over, J.R., Ritchie, A.C., Kranenburg, C.J., Brown, J.A., Buscombe, D., Noble, T., Sherwood, C.R., Warrick, J.A., and Wernette, P.A., 2021, Processing coastal imagery with Agisoft Metashape Professional Edition, version 1.6—Structure from motion workflow documentation: U.S. Geological Survey Open-File Report 2021–1039, 46 p., https://doi.org/10.3133/ofr20211039.
• Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.
• Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M. and Luo, P., 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, pp.12077-12090.
• Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A. and Torralba, A., 2019. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127, pp.302-321.

美国华盛顿州埃尔瓦河（Elwha River）冲积河道带的高分辨率正射影像（orthoimagery）时序标注数据集；作者：Daniel Buscombe，Marda Science LLC

本数据发布包含两个数据集：
1. 模型训练数据集
本数据集为人工（或半人工）标注的影像数据集，用于训练与评估一款机器学习（深度学习）模型，该模型旨在识别森林流域冲积河道带正射影像中的大型枯木、冲积沉积物、水体与植被的地表暴露堆积体。
2. 模型输出数据集
本数据集基于前述模型，对森林流域冲积河道带的更大范围正射影像数据集进行标注，以估算其中大型枯木、冲积沉积物、水体与植被的地表暴露堆积体。

所有标注数据均源自美国地质调查局（U.S. Geological Survey，Ritchie等，2018）提供的原始网格化数据。该原始数据集包含2012年4月7日至2017年9月22日期间采集的华盛顿州埃尔瓦河中游河段（MR，位于原奥尔德韦尔水库与米尔斯水库之间）的14幅正射影像，以及对应下游河段（LR，位于原米尔斯水库下游）的14幅正射影像。本正射影像采用搭载于机翼的摄影相机，通过运动恢复结构（SfM，Structure from Motion）摄影测量法生成（遵循Over等，2021的流程）。影像记录了两座大坝拆除后引发的约2000万吨沉积物脉冲过程中，河道的演变变化。两个河段分别为长约8km的中游河段（MR），以及坡度更低的长约7km的下游河段（LR）。

本正射影像已按照以下类别进行逐像素标注（可通过人工或自动化流程完成），标注数据中的类别编号以括号标注：
1. 植被/其他（0）
2. 水体（1）
3. 沉积物（2）
4. 大型枯木（3）

1. 模型训练数据集
本影像采用开源软件Doodler（Buscombe等，2021；https://github.com/Doodleverse/dash_doodler）与QGIS软件按1:300比例尺手动数字化相结合的方式进行标注，随后对多边形进行栅格化处理，并按照与其他网格化数据一致的流程进行网格化与裁切。Doodler可大幅降低自然影像多类别密集标注的人力成本，实现训练数据集的快速构建。最终训练数据集包含4382幅影像及对应标注，每幅影像与标注的分辨率均为1024×1024像素，仅占总数据集的5%以上。训练数据在两个河段的时间与空间维度上均进行了近似均匀的采样。所有训练与验证样本均刻意包含全部4个标注类别，以避免由类别不平衡引发的模型训练与评估问题（Buscombe与Goldstein，2022）。

数据以geoTIFF格式提供。影像与标注网格均已重投影至NAD83(2011)/UTM 10N坐标系，像素分辨率为0.125×0.125米。

此类逐像素标注数据可用于开发与评估影像分割、影像分类、面向对象影像分析（OBIA，Object-Based Image Analysis）以及影像内目标检测等模型，以及众多其他可用于河道带分类、描述、计数、清查以及过程或状态量化的机器学习模型。本数据集可应用于迁移学习场景，例如适配不同河流或海岸环境，或用于不同任务与类别体系。

数据文件如下：
1. Labels_used_for_model_training_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip，63 MB，标注TIFF文件
2. Model_training_ images1of4.zip，1.5 GB，影像TIFF文件
3. Model_training_ images2of4.zip，1.5 GB，影像TIFF文件
4. Model_training_ images3of4.zip，1.7 GB，影像TIFF文件
5. Model_training_ images4of4.zip，1.6 GB，影像TIFF文件

2. 模型输出数据集
本数据集采用专为该任务训练的深度学习语义分割模型（Buscombe，2023）进行标注，训练过程基于Segmentation Gym（Buscombe与Goldstein，2022）建模套件完成。我们使用Segmentation Gym软件套件，对SegFormer（Xie等，2021）深度学习模型进行微调以适配语义影像分割任务。我们采用Xie等（2021）提出的模型实例（即模型架构与训练权重），该模型原在ADE20k数据集（Zhou等，2019）上以512×512像素分辨率进行微调，本次我们将其在我们的1024×1024像素分辨率的4类别标注训练数据集上再次微调。

中游河段（MR）影像的空间范围为[455157.2494695878122002,5316532.9804129302501678 : 457076.1244695878122002,5323771.7304129302501678]（NAD83(2011)/UTM 10N坐标系），影像宽度为15351像素，高度为57910像素。下游河段（LR）影像的空间范围为[457704.9227139975992031,5326631.3750646486878395 : 459241.6727139975992031,5333311.0000646486878395]（NAD83(2011)/UTM 10N坐标系），影像宽度为12294像素，高度为53437像素。数据以Cloud-Optimzed geoTIFF（COG，Cloud-Optimzed GeoTIFF）格式提供。影像与标注网格均已重投影至NAD83(2011)/UTM 10N坐标系，像素分辨率为0.125×0.125米。所有网格均已裁切至研究时段内活跃河道边缘范围的并集。

此类河段尺度的逐像素测量数据可支持任意尺度与位置的枯木与沉积物存储量对比分析。本数据集可用于研究其他地貌复杂河道中枯木与沉积物相互作用的地貌动力学、河道内枯木存储量、枯木在生态系统中的作用以及生态保护与修复工作。

数据文件如下：
1. Elwha_MR_labels_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip，9.67 MB，埃尔瓦河中游河段（MR）标注COG文件
2. ElwhaMR_ imagery_ part1_ of_ 2.zip，566 MB，埃尔瓦河中游河段（MR）影像COG文件
3. ElwhaMR_ imagery_ part2_ of_ 2.zip，618 MB，埃尔瓦河中游河段（MR）影像COG文件
4. Elwha_LR_labels_Buscombe_Labeled_high_resolution_orthoimagery_time_series_of_an_alluvial_river_corridor_Elwha_River_Washington_USA.zip，10.96 MB，埃尔瓦河下游河段（LR）标注COG文件
5. ElwhaLR_ imagery_ part1_ of_ 2.zip，622 MB，埃尔瓦河中游河段（MR）影像COG文件
6. ElwhaLR_ imagery_ part2_ of_ 2.zip，617 MB，埃尔瓦河中游河段（MR）影像COG文件

本数据集由Daniel Buscombe（https://github.com/dbuscombe-usgs）与Evan Goldstein（https://github.com/ebgoldstein）基于面向地球科学影像分割的开源软件生态系统Doodleverse开发。感谢Doodleverse的所有贡献者！特别感谢Sharon Fitzpatrick（https://github.com/2320sharon）与Jaycee Favela贡献标注数据。

参考文献
• Buscombe, D. (2023). Doodleverse/Segmentation Gym SegFormer models for 4-class (other, water, sediment, wood) segmentation of RGB aerial orthomosaic imagery (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8172858
• Buscombe, D., Goldstein, E. B., Sherwood, C. R., Bodine, C., Brown, J. A., Favela, J., et al. (2021). Human-in-the-loop segmentation of Earth surface imagery. Earth and Space Science, 9, e2021EA002085. https://doi.org/10.1029/2021EA002085
• Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym
• Over, J.R., Ritchie, A.C., Kranenburg, C.J., Brown, J.A., Buscombe, D., Noble, T., Sherwood, C.R., Warrick, J.A., and Wernette, P.A., 2021, Processing coastal imagery with Agisoft Metashape Professional Edition, version 1.6—Structure from motion workflow documentation: U.S. Geological Survey Open-File Report 2021–1039, 46 p., https://doi.org/10.3133/ofr20211039.
• Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.
• Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M. and Luo, P., 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, pp.12077-12090.
• Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A. and Torralba, A., 2019. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127, pp.302-321.