Biogeochemical model Biome-BGCMuSo v6.2 provides plausible and accurate simulations of carbon cycle in Central European beech forests

Abstract. Process-based ecosystem models are increasingly important for predicting forest dynamics under future environmental conditions, which may encompass non-analogous climate coupled with unprecedented disturbance regimes. However, challenges persist due to the extensive number of model parameters, scarce calibration data, and the trade-offs between the local precision and the model wide-ranging applicability. In this paper, we describe a protocol that allows a modeller to collect transferable ecosystem properties based on ecosystem characteristic criteria and to compile the parameters that need to be described in the field.

We applied the procedure to develop a new parameterization for the European beech (Fagus sylvatica L.) for the Biome-BGCMuSo model, the most advanced member of the Biome-BGC family. For model calibration and testing, we utilized multiyear forest carbon data from 87 plots distributed across five European countries. The initial values of 48 new ecophysiological parameters were defined based on the literature review. The final values of 6 calibrated parameters were optimised for single sites as well as for multiple sites using the Generalised Likelihood Uncertainty Estimation and model output conditioning that ensured plausible simulations based on user-defined ranges of carbon stock output variables (carbon stock in aboveground wood biomass, soil, and litter) and finding the intersections of site-specific plausible parameter hyperspaces. To support the model use, we tested the model performance in simulating tree aboveground wood, soil, and litter carbon across a large geographical gradient of Central Europe and evaluated the trade-offs between parameters tailored to single plots and parameters estimated using multiple sites.

Our findings indicated that parameter sets derived from single sites provided an improved local accuracy of simulations of aboveground wood, soil, and litter carbons stocks by 35 %, 55 %, and 11 % in comparison to the a priori parameter set. However, their broader applicability was very limited. A multi-site optimised parameter set, on the other hand, performed satisfactorily across the entire geographical domain studied here, including sites not involved in the parameter estimation, but the errors were on average by 26 %, 35 % and 9 % greater for the aboveground wood, soil, and litter carbons stocks than those obtained with the site-specific parameter sets. Importantly, model simulations demonstrated plausible responses across large-scale environmental gradients, featuring a clear production optimum of beech that aligns with empirical studies. These findings suggest that the model is capable of accurately simulating the dynamics of the European beech across its range and can be used for more comprehensive experimentations.