Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils

Research output: Contribution to journalJournal articlepeer-review

Standard

Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils. / Pellegrini, Elisa; Rovere, Nicola; Zaninotti, Stefano; Franco, Irene; De Nobili, Maria; Contin, Marco.

In: Biology and Fertility of Soils, Vol. 57, No. 1, 2021, p. 145-151.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Pellegrini, E, Rovere, N, Zaninotti, S, Franco, I, De Nobili, M & Contin, M 2021, 'Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils', Biology and Fertility of Soils, vol. 57, no. 1, pp. 145-151. https://doi.org/10.1007/s00374-020-01498-1

APA

Pellegrini, E., Rovere, N., Zaninotti, S., Franco, I., De Nobili, M., & Contin, M. (2021). Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils. Biology and Fertility of Soils, 57(1), 145-151. https://doi.org/10.1007/s00374-020-01498-1

Vancouver

Pellegrini E, Rovere N, Zaninotti S, Franco I, De Nobili M, Contin M. Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils. Biology and Fertility of Soils. 2021;57(1):145-151. https://doi.org/10.1007/s00374-020-01498-1

Author

Pellegrini, Elisa ; Rovere, Nicola ; Zaninotti, Stefano ; Franco, Irene ; De Nobili, Maria ; Contin, Marco. / Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils. In: Biology and Fertility of Soils. 2021 ; Vol. 57, No. 1. pp. 145-151.

Bibtex

@article{d1805b0a14d24192bfe96f678d875b36,
title = "Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils",
abstract = "Soil microbial biomass (SMB-C) is one of the most frequently used parameters for the assessment of soil quality, but no threshold values have ever been proposed. We challenged the problem of a reliable numerical estimation of the SMB-C based on the knowledge of physicochemical soil properties. The aim was to evaluate artificial neural network (ANN) modelling for the prediction of SMB-C from a range of physical and chemical properties. The dataset used is composed of 231 vineyard soils of widely different characteristics and exposed to different temperature and moisture regimes. Each soil was described by ten physicochemical parameters: sand, clay, soil organic matter, total N, C/N ratio, pH, EC, exchangeable Na, active lime and total Cu. The ANN followed the topology: one input layer (1 to 11 nodes), one hidden layer (2 center dot n nodes) and one output node (SMB-C). Each soil sample was validated against the other 230 samples. The ANN model showed a much better fit than the linear model. The divergence between measured and predicted SMB-C was greatly restrained using the nonlinear approach, testifying the ability of the ANN to adapt to the highly variable dataset. The ANN analysis confirmed the primary importance of SOM for SMB-C prediction, being present in all of the best five models with the lowest root mean square relative error and in four out of five models with the lowest root mean square error. The prediction capability of SMB-C by ANN was limited at high SMB-C values, but the method can potentially be improved by expanding the dataset and introducing more parameters regarding soil physical properties and management.",
keywords = "Soil microbial biomass, Artificial neural networks, Vineyard soils, Critical values, ENZYME-ACTIVITIES, DIVERSITY, PARAMETERS, MANAGEMENT, COMMUNITY, AMENDMENT, QUALITY, SYSTEMS, COPPER",
author = "Elisa Pellegrini and Nicola Rovere and Stefano Zaninotti and Irene Franco and {De Nobili}, Maria and Marco Contin",
year = "2021",
doi = "10.1007/s00374-020-01498-1",
language = "English",
volume = "57",
pages = "145--151",
journal = "Biology and Fertility of Soils",
issn = "0178-2762",
publisher = "Springer",
number = "1",

}

RIS

TY - JOUR

T1 - Artificial neural network (ANN) modelling for the estimation of soil microbial biomass in vineyard soils

AU - Pellegrini, Elisa

AU - Rovere, Nicola

AU - Zaninotti, Stefano

AU - Franco, Irene

AU - De Nobili, Maria

AU - Contin, Marco

PY - 2021

Y1 - 2021

N2 - Soil microbial biomass (SMB-C) is one of the most frequently used parameters for the assessment of soil quality, but no threshold values have ever been proposed. We challenged the problem of a reliable numerical estimation of the SMB-C based on the knowledge of physicochemical soil properties. The aim was to evaluate artificial neural network (ANN) modelling for the prediction of SMB-C from a range of physical and chemical properties. The dataset used is composed of 231 vineyard soils of widely different characteristics and exposed to different temperature and moisture regimes. Each soil was described by ten physicochemical parameters: sand, clay, soil organic matter, total N, C/N ratio, pH, EC, exchangeable Na, active lime and total Cu. The ANN followed the topology: one input layer (1 to 11 nodes), one hidden layer (2 center dot n nodes) and one output node (SMB-C). Each soil sample was validated against the other 230 samples. The ANN model showed a much better fit than the linear model. The divergence between measured and predicted SMB-C was greatly restrained using the nonlinear approach, testifying the ability of the ANN to adapt to the highly variable dataset. The ANN analysis confirmed the primary importance of SOM for SMB-C prediction, being present in all of the best five models with the lowest root mean square relative error and in four out of five models with the lowest root mean square error. The prediction capability of SMB-C by ANN was limited at high SMB-C values, but the method can potentially be improved by expanding the dataset and introducing more parameters regarding soil physical properties and management.

AB - Soil microbial biomass (SMB-C) is one of the most frequently used parameters for the assessment of soil quality, but no threshold values have ever been proposed. We challenged the problem of a reliable numerical estimation of the SMB-C based on the knowledge of physicochemical soil properties. The aim was to evaluate artificial neural network (ANN) modelling for the prediction of SMB-C from a range of physical and chemical properties. The dataset used is composed of 231 vineyard soils of widely different characteristics and exposed to different temperature and moisture regimes. Each soil was described by ten physicochemical parameters: sand, clay, soil organic matter, total N, C/N ratio, pH, EC, exchangeable Na, active lime and total Cu. The ANN followed the topology: one input layer (1 to 11 nodes), one hidden layer (2 center dot n nodes) and one output node (SMB-C). Each soil sample was validated against the other 230 samples. The ANN model showed a much better fit than the linear model. The divergence between measured and predicted SMB-C was greatly restrained using the nonlinear approach, testifying the ability of the ANN to adapt to the highly variable dataset. The ANN analysis confirmed the primary importance of SOM for SMB-C prediction, being present in all of the best five models with the lowest root mean square relative error and in four out of five models with the lowest root mean square error. The prediction capability of SMB-C by ANN was limited at high SMB-C values, but the method can potentially be improved by expanding the dataset and introducing more parameters regarding soil physical properties and management.

KW - Soil microbial biomass

KW - Artificial neural networks

KW - Vineyard soils

KW - Critical values

KW - ENZYME-ACTIVITIES

KW - DIVERSITY

KW - PARAMETERS

KW - MANAGEMENT

KW - COMMUNITY

KW - AMENDMENT

KW - QUALITY

KW - SYSTEMS

KW - COPPER

U2 - 10.1007/s00374-020-01498-1

DO - 10.1007/s00374-020-01498-1

M3 - Journal article

VL - 57

SP - 145

EP - 151

JO - Biology and Fertility of Soils

JF - Biology and Fertility of Soils

SN - 0178-2762

IS - 1

ER -

ID: 247539456