Comparing Data-Driven and Mechanistic Models for Predicting Phenology in Deciduous Broadleaf Forests
This work addresses improving climate predictions for policymakers by enhancing phenology modeling, but it is incremental as it focuses on a specific domain without broad SOTA impact.
The study tackled predicting tree phenology dates in deciduous broadleaf forests by training a deep neural network on meteorological time series, finding it outperformed traditional process-based models, though specific numerical gains were not provided.
Understanding the future climate is crucial for informed policy decisions on climate change prevention and mitigation. Earth system models play an important role in predicting future climate, requiring accurate representation of complex sub-processes that span multiple time scales and spatial scales. One such process that links seasonal and interannual climate variability to cyclical biological events is tree phenology in deciduous broadleaf forests. Phenological dates, such as the start and end of the growing season, are critical for understanding the exchange of carbon and water between the biosphere and the atmosphere. Mechanistic prediction of these dates is challenging. Hybrid modelling, which integrates data-driven approaches into complex models, offers a solution. In this work, as a first step towards this goal, train a deep neural network to predict a phenological index from meteorological time series. We find that this approach outperforms traditional process-based models. This highlights the potential of data-driven methods to improve climate predictions. We also analyze which variables and aspects of the time series influence the predicted onset of the season, in order to gain a better understanding of the advantages and limitations of our model.