遇见数据集

Projected Global Fertilizers Consumption Datasets during 2020-2100 under SSP scenarios

收藏
Zenodo2026-02-03 更新2026-05-26 收录
官方服务:

资源简介:

1. Background Accurate projections of future global fertilizer consumption are critical for advancing research in earth system modeling, agricultural sustainability, and fertilizer industry planning. However, existing datasets often lack long-term temporal coverage and high spatial resolution. To address this gap, we present the Projected Global Fertilizers Consumption Datasets (PGFCD), which provide spatially explicit estimates of nitrogen (N), phosphorus (P), and potassium (K) fertilizer consumption from 2020 to 2100 under five Shared Socioeconomic Pathway (SSP) scenarios: SSP1 (sustainable development), SSP2 (intermediate development), and SSP3 (regional rivalry), SSP4 (unequal development), and SSP5 (fossil-fueled development). 2. Methodology 2.1 Ensemble Machine Learning (EML) Framework Algorithms: Integrated six machine learning models: Multiple Linear Regression (MLR) Decision Trees (DT) Autoregressive Integrated Moving Average (ARIMA) Multi-Layer Perceptron (MLP) Radial Basis Function (RBF) Random Forests (RF) Training Data: Historical national/regional fertilizer consumption (FAOSTAT, 1961–2015). Validation Metrics: Nash-Sutcliffe Efficiency (NSE): 0.93 Kling-Gupta Efficiency (KGE): 0.89 Mean Absolute Percentage Error (MAPE): 10.97% 2.2 Spatial Downscaling Baseline: FAO 2000 fertilizer data combined with gridded nutrient application maps for major crops in 2000. Dynamic Projection: Annual change rates applied to 5′ × 5′ grids under SSP-specific socioeconomic drivers. 3. Dataset Overview 3.1 Key Features Temporal Coverage: 2020–2100 (10-year intervals). Spatial Resolution: 5-arcminute (≈10 km at the equator). Scenarios: SSP1, SSP2, SSP3, SSP4, SSP5. Variables: N, P, and K fertilizer consumption (tonnes/year). 3.2 Dataset Structure The dataset is provided as a compressed archive (PGFCD_Ver6.0.rar), containing: 1. Fertilization_Consumption_GeoTiff/ Subfolders: N_fer/: Nitrogen fertilizer projections P_fer/: Phosphorus fertilizer projections K_fer/: Potassium fertilizer projections File Format: GeoTIFF (135 files total). Naming Convention:[FertilizerType]_fer_con_[SSP]_[Year].tif Example: K_fer_con_SSP1_2020.tif 2. Country_region_based/ Shapefiles: National/regional fertilizer consumption for 26 prediction units (2020–2100). Excel File: Global Fertilizer Consumption (2020-2100).xlsx. 3. Technical Annex.docx Detailed methodology, validation, and workflow documentation. 4. Applications This dataset supports: Earth System Modeling: Improved parameterization of fertilization impacts on biogeochemical cycles. Agricultural Policy: Scenario-based planning for sustainable fertilizer use. Industry Strategy: Long-term market analysis under diverse socioeconomic pathways. Note: Global aggregated totals of fertilizer consumption derived from the 26 prediction units (country/regional scale) may exhibit minor discrepancies compared to sums calculated from the 5-arcminute gridded data (≈10 km resolution). Such differences stem from variations in spatial aggregation methods, file formats (vector vs. raster), and underlying data processing frameworks. Users may select the dataset best aligned with their analytical objectives: The country/region-based data (26 units) is recommended for national-scale analyses or policy evaluations requiring administrative boundaries. The 5-arcminute gridded data is preferable for spatially explicit modeling or subnational assessments. Both datasets maintain equivalent quality and methodological rigor; the choice depends on the desired spatial granularity and application context. We are profoundly indebted to Dr. Andreas Gericke at Section II 2.3 Protection of the Seas and Polar Regions, German Environment Agency, and Dr. Veronika Schlosser at Chair of Sustainability Assessment of Food and Agricultural Systems, Technical University of Munich for their diligent review and insightful feedback on the previously submitted data. Their expertise has enabled us to thoroughly correct the identified inaccuracies, strengthening the integrity of our research. We hold Dr. Andreas Gericke and Dr. Veronika Schlosser in the highest esteem and sincerely apologize for any oversights that may have marred our work.

1. 研究背景 准确预测未来全球化肥消费量,对于地球系统建模、农业可持续性研究以及化肥产业规划具有至关重要的推动作用。然而,现有数据集往往缺乏长期时间覆盖范围与高空间分辨率。为填补这一研究空白,本研究推出预测型全球化肥消费量数据集(Projected Global Fertilizers Consumption Datasets, PGFCD),该数据集提供了2020年至2100年氮(Nitrogen, N)、磷(Phosphorus, P)及钾(Potassium, K)化肥消费量的空间显式估算结果,涵盖5种共享社会经济路径(Shared Socioeconomic Pathway, SSP)情景:SSP1(可持续发展路径)、SSP2(中等发展路径)、SSP3(区域竞争路径)、SSP4(不均衡发展路径)以及SSP5(化石燃料驱动发展路径)。 2. 研究方法 2.1 集成机器学习(Ensemble Machine Learning, EML)框架 本框架集成了6种机器学习模型: 多元线性回归(Multiple Linear Regression, MLR)、决策树(Decision Trees, DT)、差分整合移动平均自回归(Autoregressive Integrated Moving Average, ARIMA)、多层感知机(Multi-Layer Perceptron, MLP)、径向基函数(Radial Basis Function, RBF)以及随机森林(Random Forests, RF)。 训练数据:1961年至2015年的历史国家/区域化肥消费量数据(来源:FAOSTAT)。 验证指标: 纳什-舒特克利夫效率(Nash-Sutcliffe Efficiency, NSE):0.93 克林-古普塔效率(Kling-Gupta Efficiency, KGE):0.89 平均绝对百分比误差(Mean Absolute Percentage Error, MAPE):10.97% 2.2 空间降尺度 基准数据:2000年FAO化肥数据与2000年主要作物栅格化养分施用图谱相结合。 动态预测:基于对应SSP情景的社会经济驱动因子,将年度变化速率应用于5′×5′的栅格单元。 3. 数据集概览 3.1 核心特征 时间覆盖范围:2020年至2100年,时间间隔为10年。 空间分辨率:5弧分(赤道处约合10公里)。 情景类型:SSP1、SSP2、SSP3、SSP4、SSP5。 变量类型:氮、磷、钾化肥消费量(单位:吨/年)。 3.2 数据集结构 本数据集以压缩归档文件(PGFCD_Ver6.0.rar)形式提供,包含以下内容: 1. Fertilization_Consumption_GeoTiff/ 子文件夹: N_fer/:氮化肥消费量预测结果目录 P_fer/:磷化肥消费量预测结果目录 K_fer/:钾化肥消费量预测结果目录 文件格式:GeoTIFF,总计135个文件。 命名规则:[FertilizerType]_fer_con_[SSP]_[Year].tif 示例:K_fer_con_SSP1_2020.tif 2. Country_region_based/ 矢量数据文件:涵盖26个预测单元(2020年至2100年)的国家/区域化肥消费量数据。 Excel表格文件:Global Fertilizer Consumption (2020-2100).xlsx。 3. Technical Annex.docx:详细的方法论说明、验证流程与工作流文档。 4. 应用场景 本数据集可支撑以下研究与应用方向: - 地球系统建模:优化施肥对生物地球化学循环影响的参数化设置。 - 农业政策制定:面向可持续化肥使用的情景化规划。 - 产业战略规划:多元社会经济路径下的长期市场分析。 备注:由26个预测单元(国家/区域尺度)汇总得到的全球化肥消费总量,与从5弧分栅格数据(约10公里分辨率)计算得到的总量可能存在微小差异。此类差异源于空间聚合方法、文件格式(矢量与栅格的差异)以及底层数据处理框架的不同。用户可根据分析目标选择适配的数据集: - 若需开展国家尺度分析或基于行政边界的政策评估,推荐使用国家/区域级数据集(26个单元版本)。 - 若需进行空间显式建模或次国家尺度评估,优先选用5弧分栅格数据。 两类数据集的质量与方法学严谨性保持一致,具体选择取决于所需的空间粒度与应用场景。 本研究衷心感谢德国环境部海洋与极地保护II 2.3科的Andreas Gericke博士,以及慕尼黑工业大学食品与农业系统可持续性评估教研室的Veronika Schlosser博士,感谢他们对前期提交的数据进行的严谨审阅与富有洞见的反馈。他们的专业支持帮助团队彻底修正了发现的不准确之处,提升了本研究成果的严谨性。 本研究团队对Andreas Gericke博士与Veronika Schlosser博士致以最崇高的敬意,并为研究中可能存在的任何疏漏致以诚挚歉意。

提供机构:
Zenodo
创建时间:
2023-07-29
二维码
社区交流群
二维码
科研交流群
商业服务