The SwissPhenoCam dataset: Country-scale phenology monitoring at the individual tree level

Understanding vegetation phenology at landscape to continental scales is essential for tracking ecosystem responses to climate change, improving biodiversity assessments, and strengthening land-surface models. While satellite remote sensing provides broad spatial coverage, it often lacks the temporal and structural detail necessary to resolve fine-scale phenological dynamics. In particular, satellite phenology products struggle to resolve  species-specific responses to climatic stress. In the past decade, PhenoCam networks have been developed to address such blind spots of satellite remote sensing. Here, we build on these efforts and introduce a new Switzerland-scale phenocam dataset covering both individual and canopy-level phenological signals. We curate a large dataset of high-frequency, high-resolution webcam imagery and use it to monitor expert-annotated regions of interest (ROI) of both individual trees with known species and tree canopies. 

The first iteration of our dataset is based on webcam imagery captured in 32 sites across Switzerland and spanning the different elevational ranges of its territory. The first images date back to 2010 for some sites and cover the entire period up to the present day. On average, each site has a history of 6 years, amounting to a total of 175 site-years. The dataset currently includes over 5,000 tree-years of observations for individual trees, providing a view of changes in phenology at the species level. For approximately 1,000 trees, expert-annotated phenophase dates are available, offering a unique benchmark for calibration and validation. Additionally, for all individuals and canopy-level ROIs, we employed automated greenness-based methods to extract green-up and green-down dates and study species-specific trends along Switzerland’s different climatic zones, strongly shaped by elevational belts.  We also quantify the agreement between our phenological transition dates and those obtained from common satellite remote sensing platforms.

By making high-frequency phenological observations accessible at the country scale, this dataset provides an unprecedented resource for phenology monitoring, and supports the development of methods for ecological forecasting, and climate-change research. We invite the community to utilize this dataset to advance understanding of vegetation dynamics in a rapidly changing world.