Aarhus University Seal / Aarhus Universitets segl

Mogens Humlekrog Greve

Improved disaggregation of conventional soil maps

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Standard

Improved disaggregation of conventional soil maps. / Møller, Anders Bjørn; Malone, Brendan; Odgers, Nathan P.; Beucher, Amélie; Iversen, Bo Vangsø; Greve, Mogens Humlekrog; Minasny, Budiman.

I: Geoderma, Bind 341, 01.05.2019, s. 148-160.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Harvard

APA

CBE

MLA

Vancouver

Author

Møller, Anders Bjørn ; Malone, Brendan ; Odgers, Nathan P. ; Beucher, Amélie ; Iversen, Bo Vangsø ; Greve, Mogens Humlekrog ; Minasny, Budiman. / Improved disaggregation of conventional soil maps. I: Geoderma. 2019 ; Bind 341. s. 148-160.

Bibtex

@article{6313b4ddd6844806b08ed5fd9cf4b2ee,
title = "Improved disaggregation of conventional soil maps",
abstract = "The disaggregation of conventional soil maps is an alternative for producing high-quality soil maps when point observations are not available. Previous studies developed the DSMART algorithm (“Disaggregation and Harmonisation of Soil Map Units Through Resampled Classification Trees”) for this purpose. In this study, we tested the sensitivity of DSMART towards the input data by using two different conventional soil maps covering Denmark at scales of 1:1,000,000 and 1:2,000,000. As a potential way to improve the algorithm, we tested an implementation of soil-landscape relationships, using maps of wetlands and soil texture. We also tested two different sampling schemes, generating either a set number of virtual samples per polygon in the input map or a number of virtual samples in proportion to the areas of the polygons. Thirdly, we tested the replacement of the resampling procedure and decision tree model with Random Forest. The original procedure repeated the generation of the virtual samples 50 times, fitting a decision tree in each repetition. We modified it by sampling only once and fitting a Random Forest model. The area-proportional sampling scheme and soil-landscape relationships both improved the accuracy. Random Forest yielded a lower accuracy than the original resampling and decision tree procedure, but was far more computationally efficient. The accuracy also depended strongly on the input maps. In the best case, the algorithm predicted soil types with 18{\%} accuracy and soil groups with 47{\%} accuracy. The results demonstrated that there are several ways to improve the disaggregation of conventional soil maps, and that a suitable approach can provide reliable soil maps at a national extent.",
keywords = "Decision trees, Denmark, Landscapes, Models, Soil group, Wetlands",
author = "M{\o}ller, {Anders Bj{\o}rn} and Brendan Malone and Odgers, {Nathan P.} and Am{\'e}lie Beucher and Iversen, {Bo Vangs{\o}} and Greve, {Mogens Humlekrog} and Budiman Minasny",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.geoderma.2019.01.038",
language = "English",
volume = "341",
pages = "148--160",
journal = "Geoderma",
issn = "0016-7061",
publisher = "Elsevier BV",

}

RIS

TY - JOUR

T1 - Improved disaggregation of conventional soil maps

AU - Møller, Anders Bjørn

AU - Malone, Brendan

AU - Odgers, Nathan P.

AU - Beucher, Amélie

AU - Iversen, Bo Vangsø

AU - Greve, Mogens Humlekrog

AU - Minasny, Budiman

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The disaggregation of conventional soil maps is an alternative for producing high-quality soil maps when point observations are not available. Previous studies developed the DSMART algorithm (“Disaggregation and Harmonisation of Soil Map Units Through Resampled Classification Trees”) for this purpose. In this study, we tested the sensitivity of DSMART towards the input data by using two different conventional soil maps covering Denmark at scales of 1:1,000,000 and 1:2,000,000. As a potential way to improve the algorithm, we tested an implementation of soil-landscape relationships, using maps of wetlands and soil texture. We also tested two different sampling schemes, generating either a set number of virtual samples per polygon in the input map or a number of virtual samples in proportion to the areas of the polygons. Thirdly, we tested the replacement of the resampling procedure and decision tree model with Random Forest. The original procedure repeated the generation of the virtual samples 50 times, fitting a decision tree in each repetition. We modified it by sampling only once and fitting a Random Forest model. The area-proportional sampling scheme and soil-landscape relationships both improved the accuracy. Random Forest yielded a lower accuracy than the original resampling and decision tree procedure, but was far more computationally efficient. The accuracy also depended strongly on the input maps. In the best case, the algorithm predicted soil types with 18% accuracy and soil groups with 47% accuracy. The results demonstrated that there are several ways to improve the disaggregation of conventional soil maps, and that a suitable approach can provide reliable soil maps at a national extent.

AB - The disaggregation of conventional soil maps is an alternative for producing high-quality soil maps when point observations are not available. Previous studies developed the DSMART algorithm (“Disaggregation and Harmonisation of Soil Map Units Through Resampled Classification Trees”) for this purpose. In this study, we tested the sensitivity of DSMART towards the input data by using two different conventional soil maps covering Denmark at scales of 1:1,000,000 and 1:2,000,000. As a potential way to improve the algorithm, we tested an implementation of soil-landscape relationships, using maps of wetlands and soil texture. We also tested two different sampling schemes, generating either a set number of virtual samples per polygon in the input map or a number of virtual samples in proportion to the areas of the polygons. Thirdly, we tested the replacement of the resampling procedure and decision tree model with Random Forest. The original procedure repeated the generation of the virtual samples 50 times, fitting a decision tree in each repetition. We modified it by sampling only once and fitting a Random Forest model. The area-proportional sampling scheme and soil-landscape relationships both improved the accuracy. Random Forest yielded a lower accuracy than the original resampling and decision tree procedure, but was far more computationally efficient. The accuracy also depended strongly on the input maps. In the best case, the algorithm predicted soil types with 18% accuracy and soil groups with 47% accuracy. The results demonstrated that there are several ways to improve the disaggregation of conventional soil maps, and that a suitable approach can provide reliable soil maps at a national extent.

KW - Decision trees

KW - Denmark

KW - Landscapes

KW - Models

KW - Soil group

KW - Wetlands

UR - http://www.scopus.com/inward/record.url?scp=85060715202&partnerID=8YFLogxK

U2 - 10.1016/j.geoderma.2019.01.038

DO - 10.1016/j.geoderma.2019.01.038

M3 - Journal article

VL - 341

SP - 148

EP - 160

JO - Geoderma

JF - Geoderma

SN - 0016-7061

ER -