1887
PDF

Abstract

Summary

An adaptive learning inversion scheme was developed for geophysical data based on Gaussian Process and Active Learning, which goal is the reduction of the pool of data for training. The adaptive, physics-driven learning process uses evidence from field data as generated by an inversion process to provide real-world proxies to the machine learning training and ensure optimal generalization for field data applications. The dynamic learning model is obtained by an iterative feedback loop between the inversion process and an AI system progressively adapting to the characteristics of the field data. Convergence metrics is developed to monitor the flattening of the learning curve while ensuring the convergence of the data misfit from the physics-based procedure. The developed workflow enhances the generalization properties of machine learning for field data applications while ensuring only a small and statistically selected dataset are used for the task. The developed approach is tested on helicopter-borne transient EM and on seismic Full Waveform Inversion.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202379015
2023-11-21
2025-02-19
Loading full text...

Full text loading...

/deliver/fulltext/2214-4609/2023/2nd-eage-workshop-on-quantifying-uncertainty-in-depth-imaging/15_-_Sandoval_Curiel-Ernesto.html?itemId=/content/papers/10.3997/2214-4609.202379015&mimeType=html&fmt=ahah

References

  1. Berger, K., Rivera Caicedo, J.P., Martino, L., Wocher, M., Hank, T., and Verrelst, J. [2021] A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data.Remote Sensing, 13, 287.
    [Google Scholar]
  2. Colombo, D., Turkoglu, E., and Sandoval-Curiel, E. [2022] An airborne micro-TEM and physics deep learning solution to near-surface corrections in sand-covered areas.The Leading Edge, 41, 306–314.
    [Google Scholar]
  3. Colombo, D., Turkoglu, E., Li, W., Sandoval-Curiel, E., and Rovetta, D. [2021a] Physics-driven deep learning inversion with application to transient electromagnetics.Geophysics, 86(3), E209–E224.
    [Google Scholar]
  4. Colombo, D., Sandoval-Curiel, E., Rovetta, D., and Kontakis, A. [2021b] Near-surface full-waveform inversion in a transmission surface-consistent scheme.Geophysics, 86 (2): U1–U2.
    [Google Scholar]
  5. Trevor, H., Robert, T., and Jerome, F. [2009] The elements of statistical learning: data mining, inference, and prediction.Springer
    [Google Scholar]
/content/papers/10.3997/2214-4609.202379015
Loading
/content/papers/10.3997/2214-4609.202379015
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error