YieldSAT：面向高分辨率作物产量预测的多模态基准数据集
YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction
把作物产量预测重新定义为基于多光谱卫星影像的像素级回归任务，并给出多模态融合架构与深度集成在真实分布偏移下的对比基线，可直接复用于遥感密集回归与域偏移鲁棒性研究。
原文依据 We demonstrate the potential of large-scale and high-resolution crop yield prediction as a pixel regression task by comparing various deep learning models and data fusion architectures.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论作物产量预测需要大量数据才能训练可扩展的模型。然而，产量预测数据集的构建受制于高昂的采集成本、异构的数据质量以及数据隐私法规。因此，现有数据集稀缺、质量偏低，或仅限于区域尺度或单一作物类型，阻碍了可扩展的数据驱动解决方案的发展。在本工作中，我们发布 YieldSAT，一个面向高分辨率作物产量预测的大规模、高质量、多模态数据集。YieldSAT 跨越多个国家的多种气候带，包括阿根廷、巴西、乌拉圭和德国，涵盖玉米、油菜、大豆和小麦等主要作物类型，覆盖 2,173 块由专家整理的田块。总计提供超过 1,220 万个产量样本，每个样本的空间分辨率为 10 米。每块田块都配有多光谱卫星影像，共得到 113,555 张带标注的卫星图像，并辅以环境辅助数据。我们通过比较多种深度学习模型与数据融合架构，展示了将大规模、高分辨率作物产量预测作为像素回归任务的潜力。此外，我们指出了在真实世界条件下真值数据中严重分布偏移所带来的开放挑战。为缓解这一问题，我们探索了一种融入领域知识的深度集成方法，其表现出显著的性能提升。数据集可在 https://yieldsat.github.io/ 获取。
英文原文摘要 1486 字符
Crop yield prediction requires substantial data to train scalable models. However, creating yield prediction datasets is constrained by high acquisition costs, heterogeneous data quality, and data privacy regulations. Consequently, existing datasets are scarce, low in quality, or limited to regional levels or single crop types, hindering the development of scalable data-driven solutions. In this work, we release YieldSAT, a large, high-quality, and multimodal dataset for high-resolution crop yield prediction. YieldSAT spans various climate zones across multiple countries, including Argentina, Brazil, Uruguay, and Germany, and includes major crop types, including corn, rapeseed, soybeans, and wheat, across 2,173 expert-curated fields. In total, over 12.2 million yield samples are available, each with a spatial resolution of 10 m. Each field is paired with multispectral satellite imagery, resulting in 113,555 labeled satellite images, complemented by auxiliary environmental data. We demonstrate the potential of large-scale and high-resolution crop yield prediction as a pixel regression task by comparing various deep learning models and data fusion architectures. Furthermore, we highlight open challenges arising from severe distribution shifts in the ground truth data under real-world conditions. To mitigate this, we explore a domain-informed Deep Ensemble approach that exhibits significant performance gains. The dataset is available at https://yieldsat.github.io/.