Preprints
https://doi.org/10.5194/hess-2021-86
https://doi.org/10.5194/hess-2021-86

  26 Apr 2021

26 Apr 2021

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

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

Mo Zhang1,2 and Wenjiao Shi1,3 Mo Zhang and Wenjiao Shi
  • 1Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
  • 2School of Earth Sciences and Resources, China University of Geosciences, Beijing 100083, China
  • 3College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China

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.

Mo Zhang and Wenjiao Shi

Status: open (until 21 Jun 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Mo Zhang and Wenjiao Shi

Mo Zhang and Wenjiao Shi

Viewed

Total article views: 133 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
115 14 4 133 6 1 1
  • HTML: 115
  • PDF: 14
  • XML: 4
  • Total: 133
  • Supplement: 6
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 26 Apr 2021)
Cumulative views and downloads (calculated since 26 Apr 2021)

Viewed (geographical distribution)

Total article views: 120 (including HTML, PDF, and XML) Thereof 120 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 May 2021
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.