发表机构
Agroscope（阿格罗斯普（瑞士农业研究机构））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究推出覆盖2019-2025年7个生长季的国家级作物制图基准SwissCrop25，通过留一法年份交叉验证协议测试三类模型，发现领域特定模型表现更优，TSViT整体性能最佳，还揭示了年际分布偏移及季内模型性能权衡等关键结论。
AI 中文摘要
业务化作物制图需要模型具备跨年份泛化能力、能区分细粒度作物分类，以及能将农田与周边景观区分开。然而，现有作物制图数据集仅能孤立地评估这些需求。为此，我们推出SwissCrop25，这是一个覆盖7个生长季（2019-2025年）的国家级作物制图基准数据集。SwissCrop25融合了Sentinel-2时间序列、每日气温观测数据、包含草地管理类型的73类细粒度作物分类，以及5类明确的非农田土地覆盖类型。为评估实际部署条件，我们定义了留一法年份交叉验证协议，同时开展农田边界划分与作物分类，以对代表性作物制图架构进行基准测试。对U-TAE（卷积时间注意力模型）、TSViT（基于Transformer的时空模型）和Galileo（地球观测基础模型）的评估显示，传统基准会掩盖不同架构间的性能差异。在该设置下，领域特定模型的表现优于Galileo，其中TSViT取得最佳整体性能，较U-TAE高出12个百分点的宏平均交并比（macro-mIoU）。SwissCrop25还揭示了显著的年际分布偏移，且纳入气温衍生的物候信息可提升模型鲁棒性。最后，季内评估显示模型间存在权衡：U-TAE在生长季初期表现更好，而TSViT因对稀有类别的区分能力提升，在后期获得优势。SwissCrop25为评估实际业务化条件下的作物制图系统提供了具有挑战性的测试平台，且已在该httpsURL公开发布。
英文摘要
Operational crop mapping requires models that generalise across years, resolve fine-grained crop taxonomies, and distinguish cropland from surrounding landscapes. However, existing crop mapping datasets enable evaluation of these requirements only in isolation. We therefore introduce SwissCrop25, a national-scale crop mapping benchmark dataset spanning seven growing seasons (2019-2025). SwissCrop25 combines Sentinel-2 time series, daily temperature observations, a fine-grained 73 crop taxonomy including grassland management types, and 5 explicit non-crop land cover classes. To evaluate realistic deployment conditions, we define a leave-one-year-out protocol with joint cropland delineation and crop classification for benchmarking representative crop mapping architectures. Evaluating U-TAE (convolutional temporal-attention model), TSViT (transformer-based spatio-temporal model), and Galileo (EO foundation model) reveals differences between architectures hidden by conventional benchmarks. In this setting, domain-specific models outperform Galileo, with TSViT achieving the best overall performance and a 12 pp macro-mIoU advantage over U-TAE. SwissCrop25 also exposes substantial interannual distribution shifts and shows that incorporating temperature-derived phenological information improves robustness. Finally, in-season evaluation reveals a trade-off between models, with U-TAE performing better early in the season and TSViT gaining an advantage later through improved rare-class discrimination. SwissCrop25 provides a challenging testbed for evaluating crop mapping systems under realistic operational conditions and is publicly released at https://huggingface.co/datasets/EOA-team/SwissCrop25 .
CommentsAccepted at the ECCV 2026 Workshop TerraBytes II. To appear in the workshop proceedings
