Preprints
https://doi.org/10.5194/hess-2021-86
https://doi.org/10.5194/hess-2021-86
26 Apr 2021
 | 26 Apr 2021
Status: this preprint was under review for the journal HESS but the revision was not accepted.

Compositional balance should be considered in the mapping of soil particle-size fractions using hybrid interpolators

Mo Zhang and Wenjiao Shi

Abstract. Digital soil mapping of soil particle-size fractions (PSFs) using log-ratio methods is a widely used technique. As a hybrid interpolator, regression kriging (RK) provides a way to improve prediction accuracy. However, there have been few comparisons with other techniques when RK is applied for compositional data, and it is not known if its performance based on different balances of isometric log-ratio (ILR) transformation is robust. Here, we compared the generalized linear model (GLM), random forest (RF), and their hybrid patterns (RK) using different transformed data based on three ILR balances, with 29 environmental covariables (ECs) for the prediction of soil PSFs in the upper reaches of the Heihe River Basin (HRB), China. The results showed that the RF performed best, with more accurate predictions, but the GLM produced a more unbiased prediction. As a hybrid interpolator, RK was recommended because it widened the data ranges of the prediction values, and modified the bias and accuracy of most models, especially the RF. The prediction maps generated from RK revealed more details of the soil sampling points than the other models. Different data distributions were produced for the three ILR balances. Using the most abundant component of the compositional data as the first component of the permutations was not considered to be the right choice because it produced the worst performance. Based on the relative abundance of the components, we recommend that the focus should be on data distribution. This study provides a reference for the mapping of soil PSFs combined with transformed data at the regional scale.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Mo Zhang and Wenjiao Shi

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-86', Anonymous Referee #1, 13 Jun 2021
    • AC1: 'Reply on RC1', Wenjiao Shi, 18 Aug 2021
  • RC2: 'Comment on hess-2021-86', Anonymous Referee #2, 15 Jul 2021
    • AC2: 'Reply on RC2', Wenjiao Shi, 18 Aug 2021

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-86', Anonymous Referee #1, 13 Jun 2021
    • AC1: 'Reply on RC1', Wenjiao Shi, 18 Aug 2021
  • RC2: 'Comment on hess-2021-86', Anonymous Referee #2, 15 Jul 2021
    • AC2: 'Reply on RC2', Wenjiao Shi, 18 Aug 2021
Mo Zhang and Wenjiao Shi
Mo Zhang and Wenjiao Shi

Viewed

Total article views: 1,043 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
713 279 51 1,043 121 34 59
  • HTML: 713
  • PDF: 279
  • XML: 51
  • Total: 1,043
  • Supplement: 121
  • BibTeX: 34
  • EndNote: 59
Views and downloads (calculated since 26 Apr 2021)
Cumulative views and downloads (calculated since 26 Apr 2021)

Viewed (geographical distribution)

Total article views: 981 (including HTML, PDF, and XML) Thereof 981 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 06 Dec 2024
Download
Short summary
We paid more attention to explain the performance of linear model, machine-learning model and their hybrid patterns on both Euclidean space and Aitchison space using appropriate statistical methods. Different accuracy performance of soil particle-size fraction interpolation were revealed in terms of different compositional balances of isometric log ratio transformation. This study provides a reference for the mapping of soil PSFs combined with transformed data at the regional scale.