建筑屋顶面积（BRA）的大型和最新地图对于制定政策决策和可持续发展至关重要。此外，作为人类活动的细粒度指标，BRA可以为城市规划和能源建模做出贡献，为人类福祉带来好处。然而，现有的大规模BRA数据集，如Microsoft和谷歌的数据集，不包括中国，因此中国没有BRA的全覆盖地图。为此，我们根据2016-2021年的Sentinel-2图像制作了分辨率为2.5米的多年中国建筑屋顶面积数据集（CBRA）。CBRA是中国首个全覆盖、多年一度的BRA数据。CBRA在城市地区取得了良好的F1得分，基于250,000个测试样本的F1得分为62.55%（与中国之前的BRA数据相比+10.61%），基于农村地区的30,000个测试样本，召回率为78.94%。\n
CBRA 以GeoTIFF（.tif）栅格文件格式组织，具有单个波段和GCS_WGS_1984坐标系。像素值为 0 和 255，其中 0 表示背景，255 表示建筑物屋顶区域。此外，为了方便数据的使用，CBRA 被分成 215 个空间网格图块，命名为“CBRA_year_E/W**N/S**.tif”，其中“year”是采样年份，“E/W**N/S**”是图块数据左上角的纬度和经度坐标。", "ds_source": "
Sentinel-2数据，用于 CBRA 映射。Sentinel-2 光学图像用于 CBRA 映射。Sentinel-2是欧洲航天局（ESA）下属的地球观测任务 哥白尼计划，包括一个由两颗卫星组成的星座，即 Sentinel-2A 和 Sentinel-2B。该产品具有通过系统的辐射校准和几何和欧空局的地形校正。为了解决云噪声，我们利用 GEE（Gorelick 等人，2017 年）过滤掉图像 超过 20% 的云，并进一步通过质量波段进行云和阴影去除，以获得无云像素。最后，我们在 1 年间隔内对过滤图像进行中位数合成。", "ds_process_way": "
超分辨率和语义分割方法和弱监督学习算法。提高深度学习方法的地理空间泛化（即扩展到中国所有地区），还收集了土地覆盖数据 中国从 2016 年到 2021 年来自动态世界产品。它包括 10 种土地覆被类型，并提供概率每种类型的估计值。", "ds_quality": "
在城市地区对250000个测试样本进行了回收，回收率为78.94%，在农村地区的30000个测试样本中。", "ds_acq_start_time": "2016-01-01 00:00:00", "ds_acq_end_time": "2021-12-31 00:00:00", "ds_acq_place": "中国", "ds_acq_lon_east": 136.05916666666667, "ds_acq_lat_south": 17.532777777777778, "ds_acq_lon_west": 72.075, "ds_acq_lat_north": 54.19694444444444, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 23050816789, "ds_files_count": 7, "ds_format": "tif", "ds_space_res": "2.5m", "ds_time_res": "年", "ds_coordinate": "WGS84", "ds_projection": "", "ds_thumbnail": "adce9598-a882-4160-bf49-ce033765931f.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "0a4269e1-65f4-45f1-aeba-88ea3068eebf", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 3, "publish_time": "2024-04-25 16:20:12", "last_updated": "2026-01-14 10:34:44", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.ZENODO.DB6436.2024", "i18n": { "en": { "title": "CBRA: The first multi-annual (2016-2021) and high-resolution (2.5 m) building rooftop area dataset in China derived with Super-resolution Segmentation from Sentinel-2 imagery", "ds_format": "tif", "ds_source": "
Sentinel-2 data, used for CBRA mapping. Sentinel-2 optical images are used for CBRA mapping. Sentinel-2 is an Earth observation mission under the European Space Agency's (ESA) Copernicus program, consisting of a constellation of two satellites, Sentinel-2A and Sentinel-2B. This product has radiation calibration through the system and terrain correction through geometry and the European Space Agency. To address cloud noise, we used GEE (Gorelick et al., 2017) to filter out more than 20% of clouds in the image, and further performed cloud and shadow removal through quality bands to obtain cloud free pixels. Finally, we performed median synthesis on the filtered images within a one-year interval.", "ds_quality": "
250000 test samples were collected in urban areas with a recovery rate of 78.94%, compared to 30000 test samples in rural areas.", "ds_ref_way": "", "ds_abstract": "
A large and up-to-date map of Building Roof Area (BRA) is crucial for policy-making and sustainable development. In addition, as a fine-grained indicator of human activities, BRA can contribute to urban planning and energy modeling, bringing benefits to human well-being. However, existing large-scale BRA datasets, such as those from Microsoft and Google, do not include China, so China does not have a fully covered BRA map. For this purpose, we have created a multi-year Chinese Building Roof Area Dataset (CBRA) with a resolution of 2.5 meters based on Sentinel-2 images from 2016 to 2021. CBRA is China's first fully covered, multi-year BRA data. CBRA achieved good F1 scores in urban areas, with an F1 score of 62.55% based on 250000 test samples (+10.61% compared to previous BRA data in China), and a recall rate of 78.94% based on 30000 test samples in rural areas.\n
CBRA is organized in GeoTIFF (. tif) raster file format, with a single band and a GCSWGS_1984 coordinate system. The pixel values are 0 and 255, where 0 represents the background and 255 represents the roof area of the building. In addition, for the convenience of data usage, CBRA is divided into 215 spatial grid blocks, named \"CBRA_year-E/W * * N/S * *. tif\", where \"year\" is the sampling year and \"E/W * * N/S * *\" is the latitude and longitude coordinates of the upper left corner of the block data.
", "ds_time_res": "年", "ds_acq_place": "China", "ds_space_res": "2.5m", "ds_projection": "", "ds_process_way": "Super resolution and semantic segmentation methods, as well as weakly supervised learning algorithms. Improve the geographic generalization of deep learning methods (i.e. extend to all regions of China), and also collect land cover data from China from 2016 to 2021 from dynamic world products. It includes 10 types of land cover and provides estimated probabilities for each type.", "ds_ref_instruction": "" } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "CC BY 4.0", "doi_reg_from": "reg_outside", "cstr_reg_from": "reg_outside", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "建筑", "屋顶面积", "CBRA" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "中国" ], "ds_time_tags": [ 2016, 2017, 2018, 2019, 2020, 2021 ], "ds_contributors": [ { "true_name": "唐宏", "email": "hongtang@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "唐宏", "email": "hongtang@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "ds_managers": [ { "true_name": "唐宏", "email": "hongtang@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "category": "其他" }