Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method

Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. In this work, we propose a framework to evaluate the predictive capacity of 11 multi-model ensemble methods (MMEs), including random forest (RF), to estimate reference evapotranspiration (ET0) using 10 AR5 models for the scenarios RCP4.5 and RCP8.5. The study was carried out in the Segura Hydrographic Demarcation (SE of Spain), a typical Mediterranean semiarid area. ET0 was estimated in the historical scenario (1970-2000) using a spatially calibrated Hargreaves model. MMEs obtained better results than any individual model for reproducing daily ET0. In validation, RF resulted more accurate than other MMEs (Kling-Gupta efficiency (KGE) M=0.903, SD=0.034 for KGE and M=3.17, SD=2.97 for absolute percent bias). A statistically significant positive trend was observed along the 21st century for RCP8.5, but this trend stabilizes in the middle of the century for RCP4.5. The observed spatial pattern shows a larger ET0 increase in headwaters and a smaller increase in the coast.

Automated summary

Large ensembles of climate models are increasingly available and provide additional data for improving adaptation strategies to climate change. This study evaluates the predictive capacity of 11 multi-model ensemble methods to estimate reference evapotranspiration, with results showing that MMEs outperform individual models. The random forest model was found to be more accurate in validation, and a statistically significant positive trend was observed for the RCP8.5 scenario in the 21st century.