Inferring the tree regeneration niche from inventory data using a dynamic forest model

The regeneration niche of trees is governed by many processes and factors that are challenging to determine. Besides a species's geographic distribution, which determines if seeds are available, a myriad of local processes in forest ecosystems (e.g., competition and pathogens) exert influences on tree regeneration. Consequently, the representation of tree regeneration in dynamic forest models is a notoriously complicated process which often involves many subprocesses that are often data deficient. The ForClim forest gap model solved this problem by linking species traits to regeneration properties. However, this regeneration module was never validated with large-scale data. Here, we compare this trait-based approach with an inverse calibration approach where we estimate regeneration parameters directly from a large dataset of unmanaged European forests. The inverse calibration was done using Bayesian inference, estimating shade and drought tolerance as well as the temperature requirements for 11 common tree species along with the intensity of regeneration (i.e., the maximum regeneration rate). We find that the parameters determining the species' light niche (i.e., light requirements) are similar for the trait-based and calibrated values for both model variants, but only a more complex model variant that included competition between recruits leads to plausible estimates of the drought niche. The trait-derived temperature niche did not match to the estimates from either model variant using inverse calibration. The parameter estimates differed between the complex and the simple model, with the estimates for the complex model being closer to the trait-based parameters. In both model variants, the calibration strongly changed the parameters that determine regeneration intensity compared to the default.We conclude that the regeneration niche of trees can be recovered from a large forestry dataset in terms of the stand-level parameters light availability and regeneration intensity, while abiotic drivers (temperature and drought) are more elusive. The higher performance (better fit to hold out) of the inversely calibrated models underpins the importance of informing dynamic models by real-world observations. Future research should focus on even greater environmental coverage of observations of demographic processes in unmanaged forests to verify our findings at species range limits under extreme climatic conditions.