Preprints
https://doi.org/10.5194/hess-2021-201
https://doi.org/10.5194/hess-2021-201

  06 May 2021

06 May 2021

Review status: this preprint is currently under review for the journal HESS.

Using Machine Learning to Predict Optimal Electromagnetic Induction Instrument Configurations for Characterizing the Root Zone

Kim Madsen van't Veen1, Ty Paul Andrew Ferré2, Bo Vangsø Iversen1, and Christen Duus Børgesen1 Kim Madsen van't Veen et al.
  • 1Department of Agroecology, Aarhus University, Blichers Allé 20, 8830 Tjele, Denmark
  • 2Department of Hydrology and Atmospheric Science, University of Arizona, Tucson, AZ 85721

Abstract. Electromagnetic induction (EMI) is used widely for hydrological and other environmental studies. The apparent electrical conductivity (ECa), which can be mapped efficiently with EMI, correlates with a variety of important soil attributes. EMI instruments exist with several configurations of coil spacing, orientation, and height. There are general, rule-of-thumb guides to choose an optimal instrument configuration for a specific survey. The goal of this study was to use machine learning (ML) to improve this design optimization task. In this investigation, we used machine learning as an efficient tool for interpolating among the results of many forward model runs. Specifically, we generated an ensemble of 100,000 EMI forward models representing the responses of many EMI configurations to a range of three-layer subsurface models. We split the results into training and testing subsets and trained a decision tree (DT) with gradient boosting (GB) to predict the subsurface properties (layer thicknesses and EC values). We further examined the value of prior knowledge that could limit the ranges of some of the soil model parameters. We made use of the intrinsic feature importance measures of machine learning algorithms to identify optimal EMI designs for specific subsurface parameters. The optimal designs identified using this approach agreed with those that are generally recognized as optimal by informed experts for standard survey goals, giving confidence in the ML-based approach. The approach also offered insight that would be difficult if not impossible to offer based on rule-of-thumb optimization. We contend that such ML-informed design approaches could be applied broadly to other survey design challenges

Kim Madsen van't Veen et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-201', Anonymous Referee #1, 29 Jun 2021
    • AC1: 'Reply on RC1', Kim Madsen, 16 Aug 2021
  • RC2: 'Comment on hess-2021-201', Anonymous Referee #2, 09 Jul 2021
    • AC2: 'Reply on RC2', Kim Madsen, 16 Aug 2021

Kim Madsen van't Veen et al.

Kim Madsen van't Veen et al.

Viewed

Total article views: 408 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
324 71 13 408 1 2
  • HTML: 324
  • PDF: 71
  • XML: 13
  • Total: 408
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 06 May 2021)
Cumulative views and downloads (calculated since 06 May 2021)

Viewed (geographical distribution)

Total article views: 317 (including HTML, PDF, and XML) Thereof 317 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 21 Sep 2021
Download
Short summary
Geophysical instruments are often used in hydrological surveys. A geophysical model, that couple electrical conductivity in the subsurface layers with the measurements of an electromagnetic induction instrument, was combined with a machine learning algorithm. The study reveal that this combination can estimate the identifiability of electrical conductivity in a layered soil and provide insight about the best way to configurate the instrument for a specific field site.