Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin

Abstract

Downscaling considerably alleviates the drawbacks of regional climate simulation by general circulation models (GCMs). However, little information is available regarding the downscaling using machine learning methods, specifically at hydrological basin scale. This study developed multiple machine learning (ML) downscaling models, based on a Bayesian model average (BMA), to downscale the precipitation simulation of 8 Coupled Model Intercomparison Project Phase 5 (CMIP5) models using model output statistics (MOS) for the years 1961–2005 in the upper Han River basin. A series of statistical metrics, including Pearson’s correlation coefficient (PCC), root mean squared error (RMSE), and relative bias (Rbias), were used for evaluation and comparative analyses. Moreover, the BMA and the best ML downscaling model were used to downscale precipitation in the 21st century under Representative Concentration Pathway 4.5 (RCP4.5) and RCP8.5 scenarios. The results show the following: (1) The performance of the BMA ensemble simulation is clearly better than that of the individual models and the simple mean model ensemble (MME). The PCC reaches 0.74, and the RMSE is reduced by 28%–60% for all the GCMs and 33% compared to the MME. (2) The downscaled models greatly improved station simulation performance. Support vector machine for regression (SVR) was superior to multilayer perceptron (MLP) and random forest (RF). The downscaling results based on the BMA ensemble simulation and SVR models were regarded as the best performing overall (PCC, RMSE, and Rbias were 0.82, 35.07, mm and −5.45%, respectively). (3) Based on BMA and SVR models, the projected precipitations show a weak increasing trend on the whole under RCP4.5 and RCP8.5. Specifically, the average rainfall during the mid- (2040–2069) and late (2070–2099) 21st century increased by 3.23% and 1.02%, respectively, compared to the base year (1971–2000) under RCP4.5, while they increased by 4.25% and 8.30% under RCP8.5. Additionally, the magnitude of changes during winter and spring was higher than that during summer and autumn. Furthermore, future work is recommended to study the improvement of downscaling models and the effect of local climate.

General Circulation Model of Climate Change in the Lower River Niger, Nigeria

“…p r e c i p i t a t i o n a m o u n t s a l o n g w i t h t h e corresponding standard deviations comparing the GCM predictions from CGCM3, CSIROMk3 and HadCM3 with the observation values derived from rain gauge measurements further reveals the inadequacies of the GCMs in accurately predicting the variability in the annual rainfall. This is in consonance with previous studies which have shown the capacity of GCMs in predicting rainfall at higher resolution scales and the importance of downscaling techniques to provide improved forecasts and modelling (Xu et. al., 2020;Narimisa and Narimisa, 2018).…”

A Gaussian Process Classification and Target Recognition Algorithm for SAR Images

“…At the same time, it has been further studied in the field of machine learning [15,16]. [17]. is is to find out the rules between data by analyzing the characteristics and association of data and to mine all kinds of information needed by human beings at a deeper level.…”

MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain

“…A novel method (ClimAlign) was introduced in [42] for unsupervised, generative downscaling of temperature and precipitation based on normalizing flows for variational inference. Further works [4,[43][44][45][46][47][48][49][50] opted for downscaling based on ML and DL, and they helped assess both strengths and weaknesses of such methods. The results reported in these studies show that downscaling models based on ML allow better performance with respect to the other statistical approaches presented in [51][52][53].…”