Near-surface remote sensing observations for monitoring deciduous broadleaf forest species phenology

Since several years, more and more studies aim at developing phenology products from satellite time-series at high temporal frequency such as those provided by the VEGETATION or MODIS sensors. Reflectance times-series at high spatial resolution, such as those that will be obtained from SENTINEL2, will soon available to monitor the phenology response of forests under climate change at the level of the forest stand or the tree species. There is a great need for continuous in situ monitoring of phenology to calibrate and validate the current and future remotely-sensed phenology products. In this context, we proposed a method based on near surface remote sensing techniques to monitor the seasonal change in LAI (Leaf area Index) and date key stages of the leaf phenology. As it is important to use a network of sensors with autonomous recording systems at a minimal cost in order to maximize the spatial sampling, we selected a method based on the transmittance continuous measurement of photosynthetic active radiation (PAR). We evaluated and validated the method for a deciduous forest species (Quercus petraea) over two sites encompassing a large variation in the timing of spring leafing, where direct visual phenology observations were performed. A specific preprocessing and modeling of the measured temporal signal was developed. The performances for dating the leaf unfolding in spring are satisfying: the bias is lower than ~1 day and the RMSE is (generally) lower than ~ 4 days.