A wide variety of methods exist nowadays to address the important problem of estimating crop yields from available remote sensing and climate data. Among the different approaches, machine learning (ML) techniques are being increasingly adopted, since they allow exploiting all the information on crop progress and environmental conditions and their relations with crop yield, achieving reliable and accurate estimations. However, interpreting the relationships learned by the ML models, and hence getting insights about the problem, remains a complex and usually unexplored task. Without accountability, confidence and trust in the ML models can be compromised. Here, we develop interpretable ML approaches for crop yield estimation that allow us investigating the most informative agro-ecological drivers and influencial regions learned by the models. We conduct a set of experiments to learn the selection of agro-ecological drivers leading to best estimations of main crops grown in Europe: corn, barley and wheat. As input data, we consider a variety of multi-scale Earth observation products sensitive to canopy greenness (e.g. EVI and LAI), its water-uptake dynamics (e.g. VOD) and available water (soil moisture), as well as climatic variables from the ERA5-Land reanalysis (e.g. temperature and radiation). Our results show that the best performances (R²>0.55 for corn and R²>0.8 for both barley and wheat) are obtained when descriptors of soil, vegetation, and atmosphere status are used as input in the ML models. This combination of variables outperforms the results obtained using single variables as inputs or all variables altogether. We then further analyze the relations of input features with crop yield in the developed models by means of Gaussian Process Regression (GPR). We show how the information learned by the GPR model allows us to identify atypical or anomalous crop seasons across the study region, and investigate the underlying factors behind crop progress and failure in Europe.

目前存在多种方法来解决从可用遥感和气候数据估算作物产量的重要问题。在不同的方法中，机器学习 (ML) 技术正被越来越多地采用，因为它们允许利用有关作物进展和环境条件的所有信息及其与作物产量的关系，实现可靠和准确的估计。然而，解释 ML 模型学习到的关系，从而深入了解问题，仍然是一项复杂且通常未经探索的任务。如果没有问责制，对 ML 模型的信心和信任就会受到损害。在这里，我们为作物产量估计开发了可解释的 ML 方法，使我们能够调查最有用的农业生态驱动因素和模型学习的影响区域。我们进行了一系列实验，以了解农业生态驱动因素的选择，从而对欧洲种植的主要作物：玉米、大麦和小麦进行最佳估计。作为输入数据，我们考虑了对冠层绿度（例如 EVI 和 LAI）、其吸水动态（例如 VOD）和可用水（土壤水分）以及来自地球的气候变量敏感的各种多尺度地球观测产品。 ERA5-土地再分析（例如温度和辐射）。我们的结果表明，最佳性能 (R VOD）和可用水（土壤水分），以及来自 ERA5-Land 再分析的气候变量（例如温度和辐射）。我们的结果表明，最佳性能 (R VOD）和可用水（土壤水分），以及来自 ERA5-Land 再分析的气候变量（例如温度和辐射）。我们的结果表明，最佳性能 (R² >0.55（玉米）和 R ² >0.8（大麦和小麦）是当土壤、植被和大气状况的描述符用作 ML 模型的输入时获得的。这种变量组合优于使用单个变量作为输入或所有变量获得的结果。然后，我们通过高斯过程回归（GPR）进一步分析开发模型中输入特征与作物产量的关系。我们展示了 GPR 模型学习的信息如何使我们能够识别整个研究区域的非典型或异常作物季节，并调查欧洲作物进展和失败背后的潜在因素。