University of Oulu

Parviz, L., Rasouli, K. & Torabi Haghighi, A. Improving Hybrid Models for Precipitation Forecasting by Combining Nonlinear Machine Learning Methods. Water Resour Manage 37, 3833–3855 (2023).

Improving hybrid models for precipitation forecasting by combining nonlinear machine learning methods

Saved in:
Author: Parviz, Laleh1; Rasouli, Kabir2; Torabi Haghighi, Ali3
Organizations: 1Faculty of Agriculture, Azarbaijan Shahid Madani University, Tabriz, East Azarbaijan, Iran
2Department of Geography, The University of British Columbia, Vancouver, BC, Canada
3Water, Energy and Environmental Engineering Research Unit, University of Oulu, Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.6 MB)
Persistent link:
Language: English
Published: Springer Nature, 2023
Publish Date: 2023-09-25


Precipitation forecast is key for water resources management in semi-arid climates. The traditional hybrid models simulate linear and nonlinear components of precipitation series separately. But they do not still provide accurate forecasts. This research aims to improve hybrid models by using an ensemble of linear and nonlinear models. Preprocessing configurations and each of the Gene Expression Programming (GEP), Support Vector Regression (SVR), and Group Method of Data Handling (GMDH) models were used as in the traditional hybrid models. They were compared against the proposed hybrid models with a combination of all these three models. The performance of the hybrid models was improved by different methods. Two weather stations of Tabriz and Rasht in Iran with respectively annual and monthly time steps were selected to test the improved models. The results showed that Theil’s coefficient, which measures the inequality degree to which forecasts differ from observations, improved by 9% and 15% for SVR and GMDH relative to GEP for the Tabriz station. The applied error criteria indicated that the proposed hybrid models have a better representation of observations than the traditional hybrid models. Mean square error decreased by 67% and Nash Sutcliffe increased by 5% in the Rasht station when we combined the three machine learning models using genetic algorithm instead of SVR. Generally, the representation of the nonlinear models within the improved hybrid models showed better performance than the traditional hybrid models. The improved models have implications for modeling highly nonlinear systems using the full advantages of machine learning methods.

see all

Series: Water resources management
ISSN: 0920-4741
ISSN-E: 1573-1650
ISSN-L: 0920-4741
Volume: 37
Issue: 10
Pages: 3833 - 3855
DOI: 10.1007/s11269-023-03528-7
Type of Publication: A1 Journal article – refereed
Field of Science: 1172 Environmental sciences
Funding: Open Access funding provided by University of Oulu including Oulu University Hospital. L.P. received in-kind financial support from the Azarbaijan Shahid Madani University for this research.
Copyright information: © The Author(s) 2023. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit