Utilization of soil-plant interrelations through the use of multiple regression and artificial neural network in order to predict soil properties in Hungarian solonetzic grasslands

Tibor Tóth, Marcel Schaap, Zsolt Molnár

Research output: Contribution to journalArticle

Abstract

Soil and plant interrelations are strong enough in semi-natural solonetzic grasslands to permit the use of plant cover as predictor variable for soil salinity, sodicity and alkalinity. Four data sets were analysed which covered 4-7 plant association types, with sample sizes ranging from 20 to 120 and quadrat sizes 0.16 to 20 m2; and correlation coefficients (R) of the multiple regression equations established between plant cover (independent or predictor variables) and soil (dependent or predicted variables) usually ranged from 0.65 to 0.80. Utilization of neural networks improved the prediction further and provided typically R values of 0.8. Plant cover observations consequently can be used to improve the precision of numerical maps of soil properties on solonetz soils and to delineate risk areas more precisely faster at a lower cost.

Original languageEnglish (US)
Pages (from-to)1447-1450
Number of pages4
JournalCereal Research Communications
Volume36
Issue numberSUPPL. 5
DOIs
StatePublished - 2008

Fingerprint

ground cover plants
neural networks
soil properties
Soil
grasslands
sodicity
soil
soil salinity
alkalinity
Salinity
prediction
Sample Size
Grassland
Costs and Cost Analysis
sampling

Keywords

  • Alkalinity
  • pH
  • Plant cover
  • Salinity
  • Salt-affected soil
  • Sodicity
  • Solonetz soil

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Genetics
  • Physiology

Cite this

@article{0e8bd41c1a894d648e9f58a15c9f01cb,
title = "Utilization of soil-plant interrelations through the use of multiple regression and artificial neural network in order to predict soil properties in Hungarian solonetzic grasslands",
abstract = "Soil and plant interrelations are strong enough in semi-natural solonetzic grasslands to permit the use of plant cover as predictor variable for soil salinity, sodicity and alkalinity. Four data sets were analysed which covered 4-7 plant association types, with sample sizes ranging from 20 to 120 and quadrat sizes 0.16 to 20 m2; and correlation coefficients (R) of the multiple regression equations established between plant cover (independent or predictor variables) and soil (dependent or predicted variables) usually ranged from 0.65 to 0.80. Utilization of neural networks improved the prediction further and provided typically R values of 0.8. Plant cover observations consequently can be used to improve the precision of numerical maps of soil properties on solonetz soils and to delineate risk areas more precisely faster at a lower cost.",
keywords = "Alkalinity, pH, Plant cover, Salinity, Salt-affected soil, Sodicity, Solonetz soil",
author = "Tibor T{\'o}th and Marcel Schaap and Zsolt Moln{\'a}r",
year = "2008",
doi = "10.1556/CRC.36.2008.Suppl.3",
language = "English (US)",
volume = "36",
pages = "1447--1450",
journal = "Cereal Research Communications",
issn = "0133-3720",
publisher = "Cereal Research Non-Profit Company",
number = "SUPPL. 5",

}

TY - JOUR

T1 - Utilization of soil-plant interrelations through the use of multiple regression and artificial neural network in order to predict soil properties in Hungarian solonetzic grasslands

AU - Tóth, Tibor

AU - Schaap, Marcel

AU - Molnár, Zsolt

PY - 2008

Y1 - 2008

N2 - Soil and plant interrelations are strong enough in semi-natural solonetzic grasslands to permit the use of plant cover as predictor variable for soil salinity, sodicity and alkalinity. Four data sets were analysed which covered 4-7 plant association types, with sample sizes ranging from 20 to 120 and quadrat sizes 0.16 to 20 m2; and correlation coefficients (R) of the multiple regression equations established between plant cover (independent or predictor variables) and soil (dependent or predicted variables) usually ranged from 0.65 to 0.80. Utilization of neural networks improved the prediction further and provided typically R values of 0.8. Plant cover observations consequently can be used to improve the precision of numerical maps of soil properties on solonetz soils and to delineate risk areas more precisely faster at a lower cost.

AB - Soil and plant interrelations are strong enough in semi-natural solonetzic grasslands to permit the use of plant cover as predictor variable for soil salinity, sodicity and alkalinity. Four data sets were analysed which covered 4-7 plant association types, with sample sizes ranging from 20 to 120 and quadrat sizes 0.16 to 20 m2; and correlation coefficients (R) of the multiple regression equations established between plant cover (independent or predictor variables) and soil (dependent or predicted variables) usually ranged from 0.65 to 0.80. Utilization of neural networks improved the prediction further and provided typically R values of 0.8. Plant cover observations consequently can be used to improve the precision of numerical maps of soil properties on solonetz soils and to delineate risk areas more precisely faster at a lower cost.

KW - Alkalinity

KW - pH

KW - Plant cover

KW - Salinity

KW - Salt-affected soil

KW - Sodicity

KW - Solonetz soil

UR - http://www.scopus.com/inward/record.url?scp=80053074570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053074570&partnerID=8YFLogxK

U2 - 10.1556/CRC.36.2008.Suppl.3

DO - 10.1556/CRC.36.2008.Suppl.3

M3 - Article

AN - SCOPUS:80053074570

VL - 36

SP - 1447

EP - 1450

JO - Cereal Research Communications

JF - Cereal Research Communications

SN - 0133-3720

IS - SUPPL. 5

ER -