Companion Dataset for the Article "Deep Learning Meets Tree Phenology Modeling: PhenoFormer vs. Process-Based Models" Garnot et al., 2025 This archive contains the dataset used in the numerical experiments for the article. It includes: - Phenological observations from the Swiss Phenology Network for 9 woody plant species across 175 sites over 70 years. - Daily meteorological variables from the DaymetCH dataset for each observation site and year. Dataset format: - learning-models-data – Formatted for use with Python code for deep learning and machine learning models. - process-models-data – Formatted for use with R code for process-based models. Code repository: https://github.com/VSainteuf/PhenoFormer Citation: @article{phenoformer, title={Deep learning meets tree phenology modeling: PhenoFormer vs. process-based models}, author={Garnot, Vivien Sainte Fare and Spafford, Lynsay and Lever, Jelle and Sigg, Christian and Pietragalla, Barbara and Vitasse, Yann and Gessler, Arthur and Wegner, Jan Dirk}, journal={{Methods in Ecology and Evolution}}, year={2025} } Data source and processing: - Data source: Federal Office of Meteorology and Climatology (MeteoSwiss) - Meteorological data processing: Swiss Federal Institute for Forest, Snow and Landscape Research (WSL)