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

Application of the kernel method to the inverse geosounding problem.

Hugo Hidalgo1, Sonia Sosa León, Enrique Gómez-Treviño

  • 1CICESE, Km. 107 Carr. Tijuana-Eda., 22860, Ensenada, Mexico. hugo@cicese.mx

Neural Networks : the Official Journal of the International Neural Network Society
|April 4, 2003
PubMed
Summary

Support vector regression offers a robust method for inverting electromagnetic data to determine Earth's layered structure. This technique shows improved model recovery compared to traditional regularization methods.

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

Climate change and flood susceptibility in Bocas del Toro, Panama: A multi-criteria spatial analysis approach.

Journal of environmental management·2025
See all related articles

Area of Science:

  • Geophysics
  • Earth Science
  • Electromagnetic Methods

Background:

  • Determining Earth's layered structure involves solving inverse problems.
  • Electromagnetic soundings at low induction numbers present a linear inverse problem.
  • Electrical conductivity distribution is key to interpreting electromagnetic data.

Purpose of the Study:

  • To apply support vector (SV) regression for inverting electromagnetic sounding data.
  • To evaluate the effectiveness of SV regression as a geophysical modeling technique.
  • To compare SV regression with existing regularization methods.

Main Methods:

  • Utilizing support vector (SV) regression for geophysical data inversion.
  • Applying the SV learning algorithm for its regularizing properties.

Related Experiment Videos

  • Testing the method with both synthetic and field electromagnetic data.

    • Main Results:

    • SV regression demonstrated superior recovery of synthetic models compared to Tikhonov's regularization.
    • The SV formulation resulted in a smaller computational problem by solving in the data space.
    • For field data, SV regression produced models comparable to linear programming techniques, with enhanced robustness.

    Conclusions:

    • Support vector regression is an effective and robust technique for electromagnetic data inversion.
    • The method offers advantages in model recovery and computational efficiency over traditional approaches.
    • SV regression provides a valuable tool for geophysical modeling and understanding Earth's subsurface structure.