Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 1, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.0K

Optimizing LSTM networks and feature selection algorithms using GEE data.

Mohammad Kazemi1, Reza Naderi Samani2, Narges Kariminejad3

  • 1Hormoz Studies and Research Center, University of Hormozgan, Bandar Abbas, Iran.

Plos One
|April 29, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multivariate sensitivity analysis and threshold response of dust to drought indices and their underlying variables.

Journal of environmental management·2026
Same author

Moringa Oleifera Enhances the Cell Proliferation and Neural Differentiation of B65 and PC12 Cells.

Advanced biomedical research·2026
Same author

Effects of chitosan-titanium dioxide-Glucantime nanoassemblies on <i>Leishmania major</i>: An <i>in vitro</i> and <i>in vivo</i> study.

Iranian journal of basic medical sciences·2026
Same author

Circulating microRNA-219 in stroke: Lack associations with clinical parameters and post-stroke epilepsy risk.

IBRO neuroscience reports·2025
Same author

Evaluation of antimicrobial and antibiofilm activities of peptide Impatiens balsamina-M1 and Zinc oxide nanoparticles against Helicobacter pylori.

Scientific reports·2025
Same author

Exploring the Gut-Eye Axis: Microbial Dysbiosis in Vernal Keratoconjunctivitis.

Cornea·2025

This study introduces a novel framework for flood susceptibility mapping (FSM) using optimized deep learning and consensus feature selection. The developed model accurately identifies high-risk flood zones, aiding disaster risk reduction efforts.

Area of Science:

  • Geosciences and Environmental Science
  • Artificial Intelligence and Machine Learning
  • Disaster Risk Management

Background:

  • Flood susceptibility mapping (FSM) faces challenges from feature selection uncertainty and suboptimal model configuration.
  • Accurate FSM is crucial for effective disaster risk reduction, especially in flood-prone regions.

Purpose of the Study:

  • To develop an integrated framework coupling feature selection with metaheuristic-optimized deep learning for high-precision FSM.
  • To identify critical environmental predictors for flood susceptibility in Khuzestan Province, Iran.
  • To compare the performance of various metaheuristic algorithms for optimizing deep learning models in FSM.

Main Methods:

  • An ensemble of nine feature selection methods was employed to identify influential variables from 19 initial factors.

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.6K

Related Experiment Videos

Last Updated: May 1, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.0K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.6K
  • A frequency-based consensus rule retained variables selected by a majority of methods, identifying NDVI and TMMN as key predictors.
  • A Long Short-Term Memory (LSTM) model was developed and optimized using five metaheuristic algorithms (WOA, GWO, OOA, CSA, HOA).

    • Main Results:

    • The ensemble feature selection identified Normalized Difference Vegetation Index (NDVI) and Daily Minimum Temperature (TMMN) as the most critical predictors.
    • Hyperparameter optimization significantly improved model performance, with the LSTM-WOA model achieving the highest F1-Score (0.88) and Cohen's Kappa (0.75).
    • The final FSM indicated the highest flood susceptibility in the northwestern and central regions of Khuzestan Province.

    Conclusions:

    • The formalized consensus feature selection and comparative metaheuristic optimization provide a reliable and high-precision tool for FSM.
    • This integrated framework offers a robust approach for flood risk assessment in arid and semi-arid environments.
    • The findings support improved disaster risk reduction strategies through accurate identification of flood-prone areas.