PeatClim: A climate-driven machine-learning model for predicting potential paleo-peatland distribution and its key climate controls

Peatlands and their fossilized counterpart, coal, are key indicators of past and present climate. However, tools for predicting their potential global distribution in the geological past remain limited. Here we use machine learning to build a climate-driven peatland distribution model, PeatClim, and to identify key climatic controls on peatland formation. The model partitions global peatlands into low- and high-temperature subsets, trains them separately, and identifies key bioclimatic controls on peatland formation.

PeatClim is designed for climate-model applications, especially for use with palaeoclimate model outputs, facilitating the prediction of potential coal deposits in Earth’s history and palaeoclimate model-performance evaluation.

PeatClim v1.0.1 is a patch release that updates README.md metadata and citation text relative to PeatClim v1.0. No code, configuration, or workflow changes were made.