SwissCrop25: A National Multi-Year Benchmark for Operational Crop Mapping
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created SwissCrop25, a detailed dataset for mapping crops in Switzerland over seven years, which helps test crop identification models under realistic conditions. Their dataset includes many types of crops, non-crop areas, satellite images, and temperature data. They tested different computer models and found that models specialized for crop data worked better than a general Earth observation model. They also discovered that adding temperature information helps models handle yearly changes, and some models are better at different times during the growing season. SwissCrop25 is shared publicly to help improve crop mapping tools.
crop mappingSentinel-2time seriesphenologyspatio-temporal modelsleave-one-year-out protocoldomain-specific modelsmacro-mIoUtemperature observationsland cover classification
Authors
Thomas Lauber, Mehmet Ozgur Turkoglu, Sélène Ledain, Helge Aasen
Abstract
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 .