准确、空间明确的全球作物产量信息对于指导决策和确保粮食安全至关重要。然而，大多数公共数据集的空间和时间分辨率都很低。在此，我们利用数据驱动模型开发了一个从 1982 年到 2020 年全球小麦产量的 4 公里数据集（GlobalWheatYield4km）。首先，我们提出了一种基于物候学的方法来绘制春小麦和冬小麦的空间分布图。然后，我们通过比较两种数据驱动模型（即随机森林模型（RF）和长短期记忆模型（LSTM））与公开数据（即来自谷歌地球引擎（GEE）平台的卫星和气候数据、土壤特性以及覆盖约 11000 个政治单位的国家级以下人口普查数据）的性能，确定了最佳网格尺度产量估算模型。结果表明，GlobalWheatYield4km 在所有国家以下地区和年份捕捉到了 82% 的产量变化，均方根误差为 619.8 千克/公顷。此外，与空间生产分配模型（SPAM）（R2 20 ~ 0.49）相比，我们的数据集在所有国家以下地区和三个年份的准确度更高（R2 ~ 0.71）。数据集可能会在更大范围的作物系统建模和气候影响评估中发挥重要作用。
", "ds_source": "（1）遥感数据：我们在谷歌地球引擎（GEE）平台上获取了高分辨率辐射计（AVHRR）传感器的 1981-2021 年全球每日 0.05°归一化植被指数（NDVI）数据(https://developers.google.com/earth-engine/datasets/)。\n
\n(2) 小麦收获面积和产量:我们收集了 54 个国家约 11000 个行政单位的国家以下各级普查数据，包括收获面积（单位：公顷）、产量（单位：吨）和单产（单位：千克/公顷），最长时间跨度为 1981-2020 年。产量按产量除以收获面积计算。总体而言，97% 的数据来自二级行政单位（ADM2）和三级行政单位（ADM3）。欧盟的数据收集于 NUTS-2 级。整个研究区域的时间覆盖范围各不相同。我们剔除了普查数据中与平均值相差 +/- 2 个标准差的异常值。\n
\n(3) 环境数据：气象信息来自高空间分辨率（1/24°，约 4 千米）的 TerraClimate 月度数据集。本分析使用的气候变量包括 1981 年至 2021 年的最高气温（Tmin）、最低气温（Tmax）、降水量（Pre）、蒸气压（Vap）、蒸气压差（Vpd）、参考蒸散量（Petref）、土壤水分（Soil）、帕尔默干旱严重程度指数（Pdsi）和向下的地表短波辐射（Srad）。此外，土壤特性来自 0.00833°（约 1 公里）的世界统一土壤数据库 (HWSD)，包括表土（0-30 厘米）的容重、有机碳含量、pH 值、砾石、粘土、沙和淤泥成分。
", "ds_process_way": "应用了全球小麦生产绘图系统（GWPMS）框架，并从两个方面进行了改进。我们按照以下方法进行了研究： 1）通过基于物候学的算法绘制春小麦和冬小麦的收获面积图；2）比较ML和DL两种方法在预测网格产量方面的性能；3）使用最优模型生成 GlobalWheatYield4km 数据集；4）评估数据集的精度和不确定性。
", "ds_quality": "数据质量良好。
", "ds_acq_start_time": "1982-01-01 00:00:00", "ds_acq_end_time": "2020-12-31 00:00:00", "ds_acq_place": "全球", "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": "apply-access", "ds_total_size": 7342618984, "ds_files_count": 2, "ds_format": ".tif", "ds_space_res": "4000", "ds_time_res": "年", "ds_coordinate": "无", "ds_projection": "EPSG：3395", "ds_thumbnail": "f61f04f0-2495-4490-837c-4a689ebaf54a.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "用户在使用数据时请在正文中明确声明数据的来源，并在参考文献部分引用本元数据提供的引用方式。", "ds_from_station": null, "organization_id": "a4dd5849-78f2-44c5-b0f1-3450e952b2a2", "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": "2023-11-27 15:39:20", "last_updated": "2023-11-27 15:39:20", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.FIGSHARE.DB4094.2023", "i18n": { "en": { "title": "Accurately estimating global wheat yields at 4-km resolution during 1982-2020 (GlobalWheatYield4km)", "ds_format": ".tif", "ds_source": "（1）Remote sensing data.We acquired the global daily 0.05° Normalized Difference Vegetation Index (NDVI) data during 1981-2021 derived from the Advanced Very High-Resolution Radiometer (AVHRR) sensor on the Google Earth Engine (GEE) platform(https://developers.google.com/earth-engine/datasets/). \n
\n(2) Wheat harvested area and yield.We collected subnational-level census data on harvested area (unit: ha), production (unit: ton), and yield (unit: kg/ha) from ~11000 administrative units for the 54 countries, with the longest time coverage spanning from 1981-2020. Yield is calculated as production divided by harvested area. Overall, 97% of data came from administrative unit level 2 (ADM2) and 3 (ADM3). For European Union, the data was collected at NUTS-2 level. The temporal coverage differs across the study area. We eliminated outliers of census data with values +/− 2 standard deviation from the average. \n
\n(3) Environmental Data.Meteorological information was obtained from high-spatial resolution (1/24°, ~4-km) monthly TerraClimate datasets. The climate variables used for this analysis were maximum temperature (Tmin), minimum temperatures (Tmax), precipitation (Pre), vapor pressure (Vap), vapor pressure deficit (Vpd), reference evapotranspiration (Petref), Soil moisture (Soil), palmer drought severity index (Pdsi), and downward surface shortwave radiation (Srad) from 110 1981 to 2021. In addition, soil properties were derived from Harmonized World Soil Database (HWSD) at 0.00833°(~1 km), involving bulk density, organic carbon content, pH, gravel, clay, sand and silt fraction for the topsoil (0-30cm).
", "ds_quality": "The data quality is good.
", "ds_ref_way": "", "ds_abstract": "Accurate and spatially explicit information on global crop yield is paramount for guiding policy-making and ensuring food security. However, most public datasets are at coarse resolution in both space and time. Here, we used datadriven models to develop a 4-km dataset of global wheat yield (GlobalWheatYield4km) from 1982 to 2020. First, we proposed 15 a phenology-based approach to map spatial distributions of spring and winter wheat. Then we determined the optimal gridscale yield estimation model by comparing the performance of two data-driven models (i.e., Random Forest (RF) and Long Short-Term Memory (LSTM)), with publicly available data (i.e., satellite and climatic data from the Google Earth Engine (GEE) platform, soil properties, and subnational-level census data covering ~11000 political units). The results showed that GlobalWheatYield4km captured 82% of yield variations with RMSE of 619.8 kg/ha across all subnational regions and years. In addition, our dataset had a higher accuracy (R2~0.71) as compared with Spatial Production Allocation Model (SPAM) (R2 20 ~ 0.49) across all subnational regions and three years. The GlobalWheatYield4km dataset might play important roles in modelling crop system and assessing climate impact over larger areas.
", "ds_time_res": "年", "ds_acq_place": "Global", "ds_space_res": "4000", "ds_projection": "", "ds_process_way": "We applied the framework, Global Wheat Production Mapping System (GWPMS) with two aspects of improvements. We conducted the study according to the follows: 1) mapping the harvesting area of spring and winter wheat by a phenology-based algorithm; 2) comparing the performances of two ML and DL approaches in predicting gridded yield, 3) generating the GlobalWheatYield4km dataset using the optimal model, and 4) evaluating the accuracy and uncertainty of the dataset.
", "ds_ref_instruction": "When using data, please clearly state the source of the data in the main text and cite the citation provided by this metadata in the reference section." } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "https://creativecommons.org/licenses/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": [ "小麦", "4 千米", "全球", "全球小麦生产测绘系统", "模拟农业生产系统" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "全球" ], "ds_time_tags": [ 1982, 1983, 1984, 1985, 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 ], "ds_contributors": [ { "true_name": "张朝", "email": "zhangzhao@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "张朝", "email": "zhangzhao@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "ds_managers": [ { "true_name": "张朝", "email": "zhangzhao@bnu.edu.cn", "work_for": "北京师范大学", "country": "中国" } ], "category": "生态" }