Mirriam Makungwe
Performance of linear mixed models and random forests for spatial prediction of soil pH
Makungwe, Mirriam; Chabala, Lydia Mumbi; Chishala, Benson H.; Lark, R. Murray
Authors
Lydia Mumbi Chabala
Benson H. Chishala
MURRAY LARK MURRAY.LARK@NOTTINGHAM.AC.UK
Professor of Geoinformatics
Abstract
Digital soil maps describe the spatial variation of soil and provide important information on spatial variation of soil properties which provides policy makers with a synoptic view of the state of the soil. This paper presents a study to tackle the task of how to map the spatial variation of soil pH across Zambia. This was part of a project to assess suitability for rice production across the country. Legacy data on the target variable were available along with additional exhaustive environmental covariates as potential predictor variables. We had the option of undertaking spatial prediction by geostatistical or machine learning methods. We set out to compare the approaches from the selection of predictor variables through to model validation, and to test the predictors on a set of validation observations. We also addressed the problem of how to robustly validate models from legacy data when these have, as is often the case, a strongly clustered spatial distribution. The validation statistics results showed that the empirical best linear unbiased predictor (EBLUP) with the only fixed effect a constant mean (ordinary kriging) performed better than the other methods. Random forests had the largest model-based estimates of the expected squared errors. We also noticed that the random forest algorithm was prone to select as “important” spatially correlated random variables which we had simulated.
Citation
Makungwe, M., Chabala, L. M., Chishala, B. H., & Lark, R. M. (2021). Performance of linear mixed models and random forests for spatial prediction of soil pH. Geoderma, 397, Article 115079. https://doi.org/10.1016/j.geoderma.2021.115079
Journal Article Type | Article |
---|---|
Acceptance Date | Mar 5, 2021 |
Online Publication Date | Apr 2, 2021 |
Publication Date | Sep 1, 2021 |
Deposit Date | Oct 6, 2021 |
Publicly Available Date | Apr 3, 2023 |
Journal | Geoderma |
Print ISSN | 0016-7061 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 397 |
Article Number | 115079 |
DOI | https://doi.org/10.1016/j.geoderma.2021.115079 |
Public URL | https://nottingham-repository.worktribe.com/output/5481181 |
Publisher URL | https://www.sciencedirect.com/science/article/pii/S0016706121001592 |
Files
Revised Manuscript 2
(797 Kb)
PDF
You might also like
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: digital-library-support@nottingham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search