Process-based models outcompete correlative models in projecting spring phenology of trees in a future warmer climate

Many phenology models have been developed to explain historical trends in plant phenology and to forecast future ones. Two main types of model can be distinguished: correlative models, that statistically relate descriptors of climate to the date of occurrence of a phenological event, and process-based models that build upon explicit causal relationships determined experimentally. While process-based models are believed to provide more robust projections in novel conditions, it is still unclear whether this assertion always holds true and why. In addition, the efficiency and robustness of the two model categories have rarely been compared. Here we aimed at comparing the efficiency and the robustness of correlative and process-based phenology models with contrasting levels of complexity in both historical and future climatic conditions. Models were calibrated, validated and compared using budburst dates of five tree species across the French Alps collected during 8 years by a citizen-science program. Process-based models were less efficient, yet more robust than correlative models, even when their parameter estimates relied entirely on inverse modeling, i.e. parameter values estimated using observed budburst dates and optimization algorithms. Their robustness further slightly increased when their parameter estimates relied on forward estimation, i.e. parameter values measured experimentally. Our results therefore suggest that the robustness of process-based models comes both from the fact that they describe causal relationships and the fact that their parameters can be directly measured. Process-based models projected a reduction in the phenological cline along the elevation gradient for all species by the end of the 21st century. This was due to a delaying effect of winter warming at low elevation where conditions will move away from optimal chilling conditions that break bud dormancy vs an advancing effect of spring warming at high elevation where optimal chilling conditions for dormancy release will persist even under the most pessimistic emissions scenario RCP 8.5. These results advocate for increasing efforts in developing process-based phenology models as well as forward modelling, in order to provide accurate projections in future climatic conditions.