Abstract. Accurate and spatially explicit information on crop yield over large areas is paramount for ensuring global food security and guiding policy-making. However, most public datasets are coarse resolution in both space and time. Here, we used data-driven models to develop a 4-km dataset of global wheat yield (GlobalWheatYield4km) from 1982 to 2020. First, we proposed a phenology-based approach to map spatial distribution. Then we determined the optimal grid-scale 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 statistics covering ~11000 political units). The results showed that GlobalWheatYield4km captured 82 % of yield variations with RMSE of 619.8 kg/ha. In addition, our dataset had a higher accuracy (R² ~0.73) as compared with Spatial Production Allocation Model (R² ~ 0.49) across all regions and years. The GlobalWheatYield4km dataset will play important roles in modelling crop system and assessing climate impact over larger areas ((DOI of the referenced dataset: https://doi.org/10.6084/m9.figshare.10025006; Luo et al., 2022b).

中文翻译：

---

GlobalWheatYield4km：基于深度学习方法的 1982-2020 年 4 公里分辨率的全球小麦产量数据集

摘要。关于大面积作物产量的准确和空间明确的信息对于确保全球粮食安全和指导政策制定至关重要。然而，大多数公共数据集在空间和时间上都是粗分辨率。在这里，我们使用数据驱动模型开发了一个 4 公里的全球小麦产量数据集（GlobalWheatYield4km），从 1982 年到 2020 年。首先，我们提出了一种基于物候学的空间分布图方法。然后，我们通过比较两种数据驱动模型（即随机森林（RF）和长短期记忆（LSTM））与公开可用数据（即卫星和气候来自 Google 地球引擎 (GEE) 平台的数据、土壤特性和涵盖约 11000 个政治单位的地方统计数据）。结果表明，GlobalWheatYield4km 捕获了 82% 的产量变化，RMSE 为 619.8 kg/ha。此外，我们的数据集具有更高的准确性（R ² ~0.73) 与所有地区和年份的空间生产分配模型 ( R ^{2 ~ 0.49) 相比。}GlobalWheatYield4km 数据集将在模拟作物系统和评估更大区域的气候影响方面发挥重要作用（（参考数据集的 DOI：https://doi.org/10.6084/m9.figshare.10025006；Luo 等人，2022b）。