Spatio-temporal variation of reference evapotranspiration in northwest China based on CORDEX-EA

Abstract

One of the major components of the hydrological cycle, reference evapotranspiration ( ET 0 ) represents the maximum amount of water transferred from the land surface to the atmosphere. Vital to quantifying crop water needs, accurate predictions of ET 0 are particularly critical in arid regions, where they allow for informed water resources management adjustments through changes to agricultural irrigation rates and scheduling. Drawing upon 84 meteorological stations in northwest China, spatiotemporal variations in present-day ET 0 were investigated. Support vector regression (SVR), Extreme learning machine (ELM), and Multivariate adaptive regression spline (MARS) — three machine learning (ML) techniques — served to establish relationships between historical ET 0 and the Coordinated Regional Climate Downscaling Experiment – East Asia (CORDEX-EA), drawn from the output data sets of each of three regional climate models (RCM): Weather Research and Forecasting (WRF), Regional Climate Model version 4.0 (RegCM4) and the Mesoscale Model version 5 (MM5). The ML-RCM combinations were calibrated and validated with separate batches (66:34, respectively) of historical ET 0 data, and their respective performance and level of uncertainty were assessed statistically. In the historical period (1960–2017) ET 0 declined by −0.15, −0.75, and − 0.42 mm y − 1 in north Xinjiang, south Xinjiang, and Qinghai region, respectively, and increased in the Hexi Corridor by 0.5 mm y − 1 . For all four regions, the MARS-WRF and MARS-MM5 combinations performed well and showed greater predictive accuracy than either ELM-WRF or ELM-MM5 combinations. Performances in predicting future (2035–2050) ET 0 from CORDEX-EA outputs based on regional climate predictions RCP 4.5 and RCP 8.5 scenarios, depended to a greater extent on the RCM outputs that were selected, rather than the modeling methods. Future ET 0 predicted from RCMs generally exhibit increasing trends, and more significantly under the RCP 8.5 scenario. The representation and characterization ability of RCMs to future climate change is crucial for future ET 0 projection. Uncertainty analysis, achieved by employing multiple RCMs to predict future ET 0 , is highly recommended. Knowledge of trends in future ET 0 can help guide the management of agricultural irrigation in oases and support decision-makers engaged in water resources management in the future. • Historical ET 0 declined in Xinjiang, and Qinghai, and increased in Hexi Corridor, China. • The combination of MARS-WRF had the best predictive accuracy. • Prediction of ET 0 depends more on the RCM chosen rather than modeling methods. • Future ET 0 had an increasing trend, especially under RCP 8.5.