Chapter 6 - Kernel-based predictive framework for groundwater level forecast in semiarid areas: a CEEMDAN-based GWO-KELM hybrid mode

Shahnazi , Saman and Hashemi, Hossein, "Chapter 6 - Kernel-based predictive framework for groundwater level forecast in semiarid areas: a CEEMDAN-based GWO-KELM hybrid mode" in Hydrological Insights (Amsterdam, Netherlands: Elsevier, 2026), 85-98.

Document type:
Book Chapter
Metadata
Links
Versions
Statistics
  • Author Shahnazi , Saman
    Hashemi, Hossein
    Chapter Title Chapter 6 - Kernel-based predictive framework for groundwater level forecast in semiarid areas: a CEEMDAN-based GWO-KELM hybrid mode
    Book Title Hydrological Insights
    Publication Date 2026
    Place of Publication Amsterdam, Netherlands
    Publisher Elsevier
    Start page 85
    End page 98
    Language eng
    Abstract Accurate prediction of groundwater levels (GWL) is essential for effective and sustainable water resource management, particularly in arid and semiarid regions where excessive extraction and climate change significantly accelerate aquifer depletion. The nonstationary characteristics of groundwater data pose significant challenges to the performance and reliability of conventional machine learning methods. To address this challenge and improve GWL prediction, this chapter introduces a hybrid framework that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the gray wolf optimizer (GWO), and the kernel extreme learning machine (KELM). The proposed CEEMDAN-GWO-KELM model was evaluated using 25 years of monthly GWL data (1996–2021), collected from 20 observation wells in the Marand Plain in Iran, a semiarid region facing severe aquifer depletion. The results indicated that incorporating CEEMDAN as a preprocessing step significantly enhances the robustness of predictions, achieving up to a 52% reduction in errors compared to the standalone GWO-KELM model. The optimal input configuration, comprising GWLₜ₋₁, GWLₜ₋₂, and GWLₜ₋₃, yielded strong predictive performance during the test phase, with a correlation coefficient (R) of 0.982, a Nash–Sutcliffe Efficiency of 0.942, and a root mean square error of 0.016. Among the evaluated kernel functions, the Polynomial kernel demonstrated superior performance compared to the others.
    Copyright Holder Elesevier
    Copyright Year 2026
    Copyright type All rights reserved
    DOI https://doi.org/10.1016/B978-0-443-36394-8.00014-5
  • This website has been archived and its online forms are no longer available. Please contact us by email at contact@unu.edu.

  • Citation counts
    Google Scholar Search Google Scholar
    Access Statistics: 0 Abstract Views  -  Detailed Statistics
    Created: Mon, 06 Apr 2026, 01:43:47 JST by Haideh Beigi on behalf of UNU INWEH