Improving accuracy of downscaling rainfall by combining predictions of different statistical downscale models

Osman, Yassin Z. ORCID: 0000-0003-1121-6598 and Abdellatif, Mawada E. (2016) Improving accuracy of downscaling rainfall by combining predictions of different statistical downscale models. Water Science, 30 (2). pp. 61-75. ISSN 1110-4929

Osman Y.Z Abdellatif M.E. Improving accuracy of downscaling Water Science.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview
Official URL:


A flexible framework of multi-model of three statistical downscaling approaches was established in which predictions from these models were used as inputs to Artificial Neural Network (ANN). Traditional ANN, Simple Average Method (SAM), and combining models (SDSM, Multiple Linear Regressions (MLR), Generalized Linear Model (GLM)) were applied to a studied site in North-western England. Model performance criteria of each of the primary and combining models were evaluated. The obtained results indicate that different downscaling methods can gain diverse usefulness and weakness in simulating various rainfall characteristics under different circumstances. The combining ANN model showed more adaptability by acquiring better overall performance, while GLM, MLR and showed comparable results and the SDSM reveals relatively less accurate results in modelling most of the rainfall amount. Furthermore traditional ANN has been tested and showed poor performance in reproducing the observed rainfall compared with above methods. The results also show that the superiority of the combining approach model over the single models is promising to be implemented to improve downscaling rainfall at a single site.

Item Type: Article
Additional Information: Open Access funded by National Water Research Center under a Creative Commons license
Divisions: School of Engineering > Civil Engineering
Depositing User: Tracey Gill
Date Deposited: 24 Mar 2017 16:13
Last Modified: 07 Mar 2018 14:57
Identification Number: 10.1016/j.wsj.2016.10.002

Actions (login required)

Edit Item Edit Item


Downloads per month over past year

View more statistics