LAUSR

Digital leaf physiognomy (DLP) is considered as one of the most promising methods for estimating past climate. However, current models built using the DLP data set still lack precision, especially for mean annual precipitation (MAP). To improve predictive power, we developed five machine learning (ML) models for mean annual temperature (MAT) and MAP respectively, and then tested the precision of these models and some of their averaging compared with that obtained from other models. The precision of all models was assessed using a repeated stratified 10‐fold cross‐validation. For MAT, three combinations of models (R2 = .77) presented moderate improvements in precision over the multiple linear regression (MLR) model (R2 = .68). For loge(MAP), the averaging of the support vector machine (SVM) and boosting models improved the R2 from .19 to .63 compared with that of the MLR model. For MAP, the R2 of this model combination was 0.49, which was much better than that of the artificial neural network (ANN) model (R2 = .21). Even the bagging model, which had the lowest R2 (.37) for loge(MAP), demonstrated better precision (R2 = .27) for MAP. Our palaeoclimate estimates for nine fossil floras were also more accurate, because they were in better agreement with independent paleoclimate evidence. Our study confirms that our ML models and their averaging can improve paleoclimatic reconstructions, providing a better understanding of the relationship between climate and leaf physiognomy.