Reconstructing Past Global Vegetation With Random Forest Machine Learning, Sacrificing the Dynamic Response for Robust Results

Vegetation is an important component in the Earth system, providing a direct link between the biosphere and atmosphere. As such, a representative vegetation pattern is needed to accurately simulate climate. We attempt to model global vegetation (biomes) with a data-driven approach, to test if this allows us to create robust global and regional vegetation patterns. This not only provides quantitative reconstructions of past vegetation cover as a climate forcing, but also improves our understanding of past land cover-climate interactions which have important implications for the future. By using a Random Forest (RF) machine learning tool, we train the vegetation reconstruction with available biomized pollen data of present and past conditions to produce broad-scale vegetation patterns for the preindustrial (PI), the mid-Holocene (MH, similar to 6,000 years ago), and the Last Glacial Maximum (LGM, similar to 21,000 years ago). We test the method's robustness by introducing a systematic temperature bias based on existing climate model spread and compare the result with that of LPJ-GUESS, an individual-based dynamic global vegetation model. The results show that the RF approach is able to produce robust patterns for periods and regions well constrained by evidence (the PI and the MH), but fails when evidence is scarce (the LGM). The apparent robustness of this method is achieved at the cost of sacrificing the ability to model dynamic vegetation response to a changing climate. Plain Language Summary This study introduces a simple but robust method to create global vegetation patterns. The distribution of forests, grasslands, deserts, and other vegetation types are important boundary conditions to model climate, because they have different albedo (affecting short-wave radiation), shape and height (affecting friction), evapotranspiration effects (affecting humidity and latent heat flux), and photosynthesis features (affecting atmospheric CO2 concentration). Our method uses artificial intelligence to produce these patterns using known examples of vegetation and modeled climate together. A great advantage of this method to reconstruct vegetation patterns compared to other models involving empirical or realistic physical and biological processes is that it can be less affected by biases in the climate forcing. For instance, because the model does not know the correct relationships beforehand, it is possible to introduce an error in the climate data and still produce the same vegetation patterns. We perturb the temperature, which drives vegetation changes in a complex dynamic vegetation model, but produces almost no change in our simple method. We show that it is possible to construct robust vegetation maps despite uncertainties in the climate forcing. However, the method needs more evidence than what is currently available to reconstruct vegetation for the last ice age.

Automated summary

This study introduces a simple but robust method to create global vegetation patterns using artificial intelligence. The method is able to construct robust vegetation maps despite uncertainties in the climate forcing, but requires more evidence to reconstruct vegetation for the last ice age.