Application of genetic algorithms to the robust estimation of soil organic and mineral fraction densities

A. M. Crowe; C. J. McClean; M. S. Cresser

doi:10.1016/j.envsoft.2006.03.001

Application of genetic algorithms to the robust estimation of soil organic and mineral fraction densities

A. M. Crowe, C. J. McClean, M. S. Cresser

Environment and Geography

Research output: Contribution to journal › Article › peer-review

Abstract

The development and use of a program that combines genetic algorithms and the least median of squares (LMS) method is reported. The combination of these two methods should provide a very robust approach for optimising non-linear functions. The program was specifically developed to estimate soil bulk density using a mass fraction model and was tested against a simulated dataset before being applied to the prediction of bulk density from a dataset created by combining measurements from a number of studies. The prediction of bulk density has a very important role in the calculation of soil elemental pools,, and the predictive ability provided by the models described can be used to improve estimates of the key parameters such as soil carbon storage. (c) 2006 Elsevier Ltd. All rights reserved.

Original language	English
Pages (from-to)	1503-1507
Number of pages	5
Journal	Environmental modelling & software
Volume	21
Issue number	10
DOIs	https://doi.org/10.1016/j.envsoft.2006.03.001
Publication status	Published - Oct 2006

Keywords

genetic algorithms
least median squares
bulk density
loss on ignition
soil
BULK-DENSITY
SQUARES REGRESSION
FOREST SOILS
MATTER
MODELS
CARBON

Access to Document

10.1016/j.envsoft.2006.03.001

Cite this

@article{dabc9a332d9c4a1b99e1759536a31efd,

title = "Application of genetic algorithms to the robust estimation of soil organic and mineral fraction densities",

abstract = "The development and use of a program that combines genetic algorithms and the least median of squares (LMS) method is reported. The combination of these two methods should provide a very robust approach for optimising non-linear functions. The program was specifically developed to estimate soil bulk density using a mass fraction model and was tested against a simulated dataset before being applied to the prediction of bulk density from a dataset created by combining measurements from a number of studies. The prediction of bulk density has a very important role in the calculation of soil elemental pools,, and the predictive ability provided by the models described can be used to improve estimates of the key parameters such as soil carbon storage. (c) 2006 Elsevier Ltd. All rights reserved.",

keywords = "genetic algorithms, least median squares, bulk density, loss on ignition, soil, BULK-DENSITY, SQUARES REGRESSION, FOREST SOILS, MATTER, MODELS, CARBON",

author = "Crowe, {A. M.} and McClean, {C. J.} and Cresser, {M. S.}",

year = "2006",

month = oct,

doi = "10.1016/j.envsoft.2006.03.001",

language = "English",

volume = "21",

pages = "1503--1507",

journal = "Environmental modelling & software",

issn = "1364-8152",

publisher = "Elsevier",

number = "10",

}

TY - JOUR

T1 - Application of genetic algorithms to the robust estimation of soil organic and mineral fraction densities

AU - Crowe, A. M.

AU - McClean, C. J.

AU - Cresser, M. S.

PY - 2006/10

Y1 - 2006/10

N2 - The development and use of a program that combines genetic algorithms and the least median of squares (LMS) method is reported. The combination of these two methods should provide a very robust approach for optimising non-linear functions. The program was specifically developed to estimate soil bulk density using a mass fraction model and was tested against a simulated dataset before being applied to the prediction of bulk density from a dataset created by combining measurements from a number of studies. The prediction of bulk density has a very important role in the calculation of soil elemental pools,, and the predictive ability provided by the models described can be used to improve estimates of the key parameters such as soil carbon storage. (c) 2006 Elsevier Ltd. All rights reserved.

AB - The development and use of a program that combines genetic algorithms and the least median of squares (LMS) method is reported. The combination of these two methods should provide a very robust approach for optimising non-linear functions. The program was specifically developed to estimate soil bulk density using a mass fraction model and was tested against a simulated dataset before being applied to the prediction of bulk density from a dataset created by combining measurements from a number of studies. The prediction of bulk density has a very important role in the calculation of soil elemental pools,, and the predictive ability provided by the models described can be used to improve estimates of the key parameters such as soil carbon storage. (c) 2006 Elsevier Ltd. All rights reserved.

KW - genetic algorithms

KW - least median squares

KW - bulk density

KW - loss on ignition

KW - soil

KW - BULK-DENSITY

KW - SQUARES REGRESSION

KW - FOREST SOILS

KW - MATTER

KW - MODELS

KW - CARBON

U2 - 10.1016/j.envsoft.2006.03.001

DO - 10.1016/j.envsoft.2006.03.001

M3 - Article

SN - 1364-8152

VL - 21

SP - 1503

EP - 1507

JO - Environmental modelling & software

JF - Environmental modelling & software

IS - 10

ER -