该数据集是利用谷歌地球引擎上的大量大地遥感卫星图像制作的。首先，根据前提知识、现有土地覆被基线图和时间加权动态时间扭曲法收集训练样本。其次，将从时间序列陆地卫星图像中获得的多年物候特征输入随机森林分类器，以获得每个像素的年度耕地概率。第三，采用 LandTrendr 变化检测算法将耕地概率时间序列分为若干段，并记录其中的断点和相应的变化年份。第四，根据既定的判别规则，从 LandTrendr 分段结果中确定年度耕地类型。最后，进行分类后处理，以更好地完善耕地地图。", "ds_source": "
Landsat TM/ETM+/OLI （Landsat 5/7/8）（1986-2021年）。\n
土地覆盖数据集（CLCD）（2020和2021年数据）。 \n
航天飞机雷达地形任务 （SRTM） 数字高程数据集。", "ds_process_way": "
基于轨迹的方法，该方法结合了机器学习和变化检测技术，用于绘制年度农田动态图。本研究中的一年生耕地定义为一块至少 0.25 公顷（最小宽度为 30 m）的土地，在播种或种植日期后的 12 个月内至少播种/种植和可收获一次。该定义与作物评估和监测联合实验 （JECAM） 网络制定的标准一致，并采用了符合粮农组织土地覆盖元语言的共享耕地范围。在本研究中，辨别一年生农田的一个关键标准是，遥感图像中的植被信号必须在 12 个月内表现出明显的变化，反映种植和收获活动。\n
数据处理过程如下：（1）训练数据生成；（2）特征空间构建；（3）坡地概率估计；（4）时间分割；（5）年度农田测绘；（6）分类后处理；（7）准确性评估和比较。", "ds_quality": "
本研究结合自动训练样本生成、随机森林监督分类和 LandTrendr 时间分割算法，提出了一种经济高效、高分辨率的农田动态监测方案。利用 Landsat 影像的完整档案和 GEE 云计算平台，我们创新性地以 30 m 的分辨率绘制了 1986 年至 2021 年中国每年的农田分布图。由此得出的 CACD 年度地图达到了令人鼓舞的精度F1得分为 0.79 ± 0.02，优于 CLCD、CLUD、GLAD 和 GFSAD 等其他产品。此外，第三方样本集的验证、与省级统计数据的回归以及多种产品之间的空间细节比较表明 CACD 在描绘农田动态的空间分布和时间趋势方面的合理性。2021 年中国耕地总面积为 1 725 200 ± 212 400 公里2，代表增加了 30 300 公里2（1.79%）。", "ds_acq_start_time": "1986-01-01 00:00:00", "ds_acq_end_time": "2021-12-31 00:00:00", "ds_acq_place": "中国", "ds_acq_lon_east": null, "ds_acq_lat_south": null, "ds_acq_lon_west": null, "ds_acq_lat_north": null, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 22999412171, "ds_files_count": 37, "ds_format": "tif", "ds_space_res": "", "ds_time_res": "", "ds_coordinate": "WGS84", "ds_projection": "", "ds_thumbnail": "b8ef2a90-f0c2-48c5-82a5-9250a43e4844.png", "ds_thumb_from": 2, "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": [ "170.4510" ], "quality_level": 3, "publish_time": "2024-11-28 11:01:06", "last_updated": "2026-01-14 10:36:15", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.ZENODO.DB6649.2024", "i18n": { "en": { "title": "A 30 m annual cropland dataset of China from 1986 to 2021", "ds_format": "tif", "ds_source": "
Landsat TM/ETM+/OLI (Landsat 5/7/8) (1986-2021).\n
Land Cover Dataset (CLCD) (2020 and 2021 data). \n
The Space Shuttle Radar Topography Mission (SRTM) digital elevation dataset.", "ds_quality": "
This study proposes an economically efficient and high-resolution dynamic monitoring scheme for farmland by combining automatic training sample generation, random forest supervised classification, and LandTrendr time segmentation algorithm. Using the complete archive of Landsat imagery and the GEE cloud computing platform, we innovatively created annual agricultural distribution maps of China from 1986 to 2021 at a resolution of 30 meters. The CACD annual map obtained from this has achieved an encouraging accuracy F1 score of 0.79 ± 0.02, which is superior to other products such as CLCD, CLUD, GLAD, and GFSAD. In addition, the validation of third-party sample sets, regression with provincial statistical data, and spatial detail comparisons between multiple products demonstrate the rationality of CACD in depicting the spatial distribution and temporal trends of farmland dynamics. In 2021, the total cultivated land area in China was 1725200 ± 212400 square kilometers, representing an increase of 30300 square kilometers (1.79%).", "ds_ref_way": "", "ds_abstract": "
This dataset was created using a large number of Earth remote sensing satellite images from Google Earth Engine. Firstly, collect training samples based on prerequisite knowledge, existing land cover baseline maps, and time weighted dynamic time distortion method. Secondly, the multi-year phenological features obtained from time-series land satellite images will be input into a random forest classifier to obtain the annual cultivated land probability for each pixel. Thirdly, the LandTrendr change detection algorithm is used to divide the probability time series of cultivated land into several segments, and record the breakpoints and corresponding change years within them. Fourthly, based on the established discrimination rules, determine the annual cultivated land type from the LandTrendr segmentation results. Finally, perform classification post-processing to better improve the farmland map.
", "ds_time_res": "", "ds_acq_place": "China", "ds_space_res": "", "ds_projection": "", "ds_process_way": "The trajectory based method combines machine learning and change detection techniques to draw annual dynamic maps of farmland. The annual cultivated land in this study is defined as a piece of land of at least 0.25 hectares (with a minimum width of 30 meters) that has been sown/planted and harvested at least once within 12 months after the sowing or planting date. This definition is consistent with the standards developed by the Joint Experiment on Crop Assessment and Monitoring (JECAM) network and adopts a shared arable land scope that conforms to the FAO Land Cover Meta Language. In this study, a key criterion for identifying annual farmland is that vegetation signals in remote sensing images must exhibit significant changes within 12 months, reflecting planting and harvesting activities.\n
The data processing process is as follows: (1) training data generation; (2) Feature space construction; (3) Slope probability estimation; (4) Time division; (5) Annual farmland surveying and mapping; (6) Post classification processing; (7) Accuracy assessment and comparison.", "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": [ "30m", "农田", "中国" ], "ds_subject_tags": [ "自然地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "中国" ], "ds_time_tags": [ 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021 ], "ds_contributors": [ { "true_name": "徐冰", "email": "bingxu@tsinghua.edu.cn", "work_for": "清华大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "徐冰", "email": "bingxu@tsinghua.edu.cn", "work_for": "清华大学", "country": "中国" } ], "ds_managers": [ { "true_name": "徐冰", "email": "bingxu@tsinghua.edu.cn", "work_for": "清华大学", "country": "中国" } ], "category": "生态" }