Support data for paper "Temporal Attention Multi-Resolution Fusion of Satellite Image Time-Series, applied to Landsat-8 and Sentinel-2: all bands, any time, at best spatial resolution"

Description This dataset contains support data for the following paper: Julien Michel, Jordi Inglada. Temporal Attention Multi-Resolution Fusion of Satellite Image Time-Series, applied to Landsat-8/9 and Sentinel-2: all bands, any time, at best spatial resolution. 2025. ⟨hal-05101526v2⟩ It contains two zip files: model.zip : The baseline pre-trained TAMRF model and its hydra configuration (as well as all models trained during ablation studies), to be used with test script in source code (see https://github.com/Evoland-Land-Monitoring-Evolution/tamrfsits) results.zip : CSV files containing the results presented in the paper, as well as additional result data. Licence Creative Commons Attribution 4.0 InternationalThe Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited. Acknowledgments This work was partly performed using HPC resources from GENCI-IDRIS (Grant 2023-AD010114835) This work was partly performed using HPC resources from CNES Computing Center. The authors acknowledge funding from the EvoLand project (Evolution of the Copernicus Land Service portfolio, grant agreement No 101082130) funded from the European Union's Horizon Europe research and innovation program.数据集说明 本数据集为以下论文提供支撑数据： 朱利安·米歇尔（Julien Michel）、霍尔迪·因格拉达（Jordi Inglada）. 卫星图像时间序列的时序注意力多分辨率融合：应用于Landsat-8/9与Sentinel-2：全波段、任意时序、最优空间分辨率. 2025. ⟨hal-05101526v2⟩ 本数据集包含两个压缩包文件： model.zip：基线预训练时序注意力多分辨率融合（Temporal Attention Multi-Resolution Fusion，简称TAMRF）模型及其Hydra配置文件（同时包含消融实验中训练的全部模型），需配合源码中的测试脚本使用（详见https://github.com/Evoland-Land-Monitoring-Evolution/tamrfsits） results.zip：包含论文中展示的实验结果及额外补充数据的CSV格式文件 许可协议 知识共享署名4.0国际版（Creative Commons Attribution 4.0 International）。该许可协议允许对授权作品进行再分发与再使用，但需对原作者予以恰当署名。 致谢 本研究部分依托GENCI-IDRIS提供的高性能计算（High Performance Computing，HPC）资源（项目编号2023-AD010114835）完成。 本研究部分依托法国国家空间研究中心（CNES）计算中心的高性能计算资源完成。 作者感谢欧盟地平线欧洲（Horizon Europe）研究与创新计划资助的EvoLand项目（哥白尼陆地服务组合演进，项目协议编号101082130）提供的资金支持。