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

Landslide displacement interval prediction using lower upper bound estimation method with pre-trained random vector

Cheng Lian1, Zhigang Zeng2, Xiaoping Wang2

  • 1School of Automation, Wuhan University of Technology, Wuhan 430074, China.

Neural Networks : the Official Journal of the International Neural Network Society
|July 28, 2020
PubMed
Summary

Related Concept Videos

Prediction Intervals01:03

Prediction Intervals

3.0K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
3.0K
End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

1.0K
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
1.0K

You might also read

Related Articles

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

Sort by
Same author

Coexisting pollutants modulate cephalosporin bioavailability and shape antibiotic resistance evolution under co-exposure conditions.

Journal of hazardous materials·2026
Same author

Multi-imidazolium cage-like microspheres: Synergistic multi site hydrogen bonding and geometric confinement for selective <sup>99</sup>TcO<sub>4</sub><sup>-</sup>/ReO<sub>4</sub><sup>-</sup> capture in harsh media.

Journal of colloid and interface science·2026
Same author

Pore size engineering in covalent organic frameworks for high-performance anion exchange membranes.

Nanoscale·2026
Same author

Decoupling Electronic Effects in Oxygen Reduction Catalysts via a Model Nanowire Platform.

Angewandte Chemie (International ed. in English)·2026
Same author

Mercaptoimidazole-Engineered Microenvironment Enables Durable CO<sub>2</sub> Electroreduction in a Zero-Gap PEM Electrolyzer.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Orthogonal relay system for efficient CO-to-ethanol electrosynthesis.

Nature communications·2026
This summary is machine-generated.

This study introduces a new method for landslide prediction intervals using neural networks and evolutionary algorithms. The enhanced technique improves uncertainty quantification for landslide displacement, offering more reliable forecasts.

Area of Science:

  • Geosciences
  • Computational Engineering
  • Artificial Intelligence

Background:

  • Quantifying uncertainties in landslide evolution is crucial for effective risk management.
  • Traditional prediction methods often struggle to provide reliable uncertainty estimates.
  • Interval prediction offers a promising approach for landslide displacement forecasting.

Purpose of the Study:

  • To introduce and extend the lower upper bound estimation (LUBE) method for landslide displacement prediction intervals (PIs).
  • To develop a hybrid approach integrating ensemble empirical mode decomposition (EEMD) with LUBE for enhanced landslide prediction.
  • To validate the proposed methods using benchmark datasets and real-world reservoir-induced landslide cases.

Main Methods:

  • Utilizing a random vector functional link network (RVFLN) as the neural network (NN) within the LUBE framework.
Keywords:
Landslide displacement predictionLower upper bound estimationPopulation initializationPrediction intervalRandom vector functional link network

Related Experiment Videos

  • Employing a hybrid evolutionary algorithm, Particle Swarm Optimization-Gravitational Search Algorithm (PSOGSA), for training the LUBE model.
  • Redesigning the LUBE loss function to incorporate PI center quality and initializing populations using pre-trained RVFLN weights.

    • Main Results:

    • The improved LUBE method demonstrated robust performance across seven benchmark datasets for interval prediction.
    • The hybrid EEMD-LUBE approach showed significant capability in predicting displacement for six real-world reservoir-induced landslides.
    • The redesigned loss function and initialization strategy contributed to more comprehensive PI evaluations.

    Conclusions:

    • The enhanced LUBE method, particularly when combined with EEMD, provides a powerful tool for landslide displacement prediction and uncertainty quantification.
    • The study validates the effectiveness of hybrid evolutionary algorithms and advanced NN architectures in geotechnical engineering applications.
    • The proposed methods offer valuable insights for improving the safety and management of landslide-prone areas.