CR 83:91-110 (2021)  -  DOI: https://doi.org/10.3354/cr01634

ABSTRACT: The accuracy of different downscaling methods in projecting future precipitation and air temperature from general circulation models (GCMs) has rarely been addressed with regards to the Tibetan Plateau, and this information is important for future water resource management in the region. The performance of automated statistical downscaling (ASD) and Delta downscaling methods in predicting precipitation and air temperature was evaluated at 19 meteorological stations in the Qilian Mountains and Hexi Corridor (QM-HC) by comparing with in situ observations from 2006-2015. These comparisons, based on Representative Concentration Pathway 4.5 (RCP4.5), suggest that the difference in annual precipitation between the ASD model and the Delta method is 17 mm. Testing different weights of the 2 downscaling methods indicates that combining the 2 methods results in lower uncertainty. The downscaling of annual precipitation projected by weighting the results of the 2 methods suggested that, based on RCP4.5, precipitation will not increase significantly from 2021-2100 compared to the past (1961-2005) and will fluctuate steadily in the coming decades. These projections are in contrast with previous projections of a significant increase. Air temperature is projected to increase by approximately 0.2°C decade^-1 from 2021-2100 according to the weighted average of the ASD model and Delta method based on RCP4.5. This study indicates that management measures based on projected increased precipitation should be carefully reconsidered in different regions.

KEY WORDS: Automated statistical downscaling · ASD model · Delta method · Qilian Mountains · Hexi Corridor · Weighted average · RCP4.5