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 Videos

Inductive learning approaches to rainfall-runoff modelling.

C W Dawson1, M R Brown, R L Wilby

  • 1Department of Computer Science, Loughborough University, Leicestershire, UK.

International Journal of Neural Systems
|May 8, 2000
PubMed
Summary
This summary is machine-generated.

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

City-wide wastewater genomic surveillance through the successive emergence of SARS-CoV-2 Alpha and Delta variants.

Water research·2022
Same author

Human myelomeningocele risk and ultra-rare deleterious variants in genes associated with cilium, WNT-signaling, ECM, cytoskeleton and cell migration.

Scientific reports·2021
Same author

River channel conveyance capacity adjusts to modes of climate variability.

Scientific reports·2019
Same author

A flow cytometry method for bacterial quantification and biomass estimates in activated sludge.

Journal of microbiological methods·2019
Same author

Coupled virus - bacteria interactions and ecosystem function in an engineered microbial system.

Water research·2019
Same author

Mosquito Peptide Hormones: Diversity, Production, and Function.

Advances in insect physiology·2019

This study shows that inductive learning, including decision trees and artificial neural networks, can effectively forecast river flow. These methods accurately predict flooding and low flow by analyzing complex rainfall-runoff factors.

Area of Science:

  • Hydrology and Water Resource Management
  • Environmental Science
  • Computational Science

Background:

  • Rainfall-runoff modeling is crucial for predicting floods, erosion, and low flow.
  • This process is complex, influenced by numerous explicit and implicit factors like precipitation, topography, and soil types.
  • Traditional methods struggle with the inherent complexity and unquantified variables in hydrological systems.

Purpose of the Study:

  • To evaluate the effectiveness of inductive learning approaches for river flow forecasting.
  • To compare decision trees and artificial neural networks (MLP, RBFN) against conventional flood forecasting systems.
  • To assess the capability of these models in handling complex hydrological data and predicting extreme events.

Main Methods:

Related Experiment Videos

  • Application of decision trees, multilayer perceptron (MLP), and radial basis function (RBFN) models.
  • Training and testing models using real hydrometric data from two flood-prone UK catchments.
  • Comparative analysis of inductive learning models' performance against conventional hydrological forecasting techniques.

    • Main Results:

    • Inductive learning models demonstrated strong performance in river flow forecasting.
    • Decision trees and artificial neural networks effectively captured complex relationships influencing river flow.
    • These advanced methods showed potential for improved accuracy in predicting flood and low flow events compared to traditional systems.

    Conclusions:

    • Inductive learning approaches, particularly decision trees and neural networks, offer a robust alternative for river flow forecasting.
    • These methods can interpret complex, non-linear relationships in hydrological data, improving prediction accuracy.
    • The study highlights the potential of AI-driven hydrological modeling for enhanced water resource management and flood prediction.