A multi-hybrid model approach optimizing discharge forecasts in karst catchment under climate change

Sezen, Cenk (author), Šraj, Mojca (author)

Rainfall-runoff modelling in karst catchments is challenging due to complex hydrogeological and climatic conditions. Conventional hydrological models can struggle to simulate the nonlinear dynamics. To address this challenge, this study proposes a multiple hybrid modelling approach to enhance daily rainfall-runoff simulations in the karst Ljubljanica River catchment in Slovenia. This approach integrates the Technische Universität Wien (TUW) and the Génie Rural à 5 paramètres Journalier (GR5J) lumped conceptual models, which consider the snow processes, with the symbolic regression- genetic programming (SR-GP) data-driven model. The hybrid model, TUW-CemaNeige GR5J-SR-GP, was fortified by grey wolf optimisation (GWO) for calibration, ensemble empirical mode decomposition (EEMD) for data decomposition, and recursive feature elimination (RFE) for feature selection. Rainfall-runoff modelling was conducted for the observed and projected datasets under the Representative Concentration Pathway 4.5 (RCP4.5) and 8.5 (RCP8.5) climate change scenarios. The hybrid model improved baseflow simulation performance by 41% (TUW) and 36% (CemaNeige GR5J), enhanced monthly peak discharge simulation performance by 5% and 13%, and yielded notable improvements in simulating low and high flows under the RCP4.5 and RCP8.5 scenarios. The algebraic equations of the SR-GP model and sensitivity analysis highlighted the influence of the slow-flow components on discharge simulations. The hybrid modelling approach is a promising alternative for compensating for the limitations of the stand-alone models in karst catchments for efficient water resources management.

• Language: English
• Keywords: hydrology, conceptual model, data-driven model, multiple hybrid modelling, karst catchment, Ljubljanica river
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FGG - Faculty of Civil and Geodetic Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: Str. 1-23
• Numbering: jan., part C, ǂart. ǂ134620, Letn. 664
• PID: 20.500.12556/RUL-176109
• UDC: 502/504:556
• ISSN on article: 0022-1694
• DOI: 10.1016/j.jhydrol.2025.134620
• COBISS.SI-ID: 258179843
• Publication date in RUL: 21.11.2025

Record is a part of a journal

• Title: Journal of hydrology
• Shortened title: J. Hydrol.
• Publisher: North-Holland, Elsevier
• ISSN: 0022-1694
• COBISS.SI-ID: 25750784

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Title: Večhibridni model za optimizacijo napovedi odtoka s kraškega porečja v spremenljivih podnebnih razmerah

Abstract

Modeliranje padavin in odtoka s kraških porečij je zahtevno zaradi kompleksnih hidrogeoloških in klimatskih razmer. Konvencionalni hidrološki modeli imajo težave pri simuliranju nelinearne dinamike. Da bi se spopadli s tem izzivom, študija predlaga večhibridni modelski pristop za izboljšanje dnevnih simulacij padavin in odtoka v kraškem porečju reke Ljubljanice v Sloveniji. Ta pristop združuje konceptualna modela Technische Universität Wien (TUW) in Génie Rural à 5 paramètres Journalier (GR5J), ki upoštevata snežne procese, s simboličnim regresijsko-genetskim programskim (SR-GP) modelom, ki temelji na podatkih. Hibridni model TUW-CemaNeige GR5J-SR-GP je bil nadgrajen z optimizacijo sivega volka (GWO) za kalibracijo, empirično dekompozicijo (EEMD) za dekompozicijo podatkov in rekurzivno eliminacijo značilnosti (RFE) za izbiro značilnosti. Modeliranje padavin in odtoka je bilo izvedeno za opazovane in napovedane podatkovne nize v okviru scenarijev podnebnih sprememb Representative Concentration Pathway 4.5 (RCP4.5) in 8.5 (RCP8.5). Hibridni model je izboljšal zmogljivost simulacije osnovnega pretoka za 41 % (TUW) in 36 % (CemaNeige GR5J), izboljšal zmogljivost simulacije mesečnega največjega pretoka za 5 % in 13 % ter prinesel opazne izboljšave pri simulaciji nizkih in visokih pretokov v primeru scenarijev RCP4.5 in RCP8.5. Algebrske enačbe modela SR-GP in analiza občutljivosti so poudarile vpliv komponent baznega pretoka na simulacije odtoka. Hibridni modelski pristop je obetavna alternativa za kompenzacijo omejitev samostojnih modelov v kraških porečjih za učinkovito upravljanje vodnih virov.

• Keywords: hidrologija, konceptualni model, model na podlagi podatkov, večhibridni model, kraško porečje, Ljubljanica

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0180-2022
• Name: Vodarstvo in geotehnika: orodja in metode za analize in simulacije procesov ter razvoj tehnologij