Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site

Alberto Guadagnini, Shlomo P Neuman, Marcel Schaap, Monica Riva

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analyses of flow and transport in the shallow subsurface require information about spatial and statistical distributions of soil hydraulic properties (water content and permeability, their dependence on capillary pressure) as functions of scale and direction. Measuring these properties is relatively difficult, time consuming and costly. It is generally much easier, faster and less expensive to collect and describe the makeup of soil samples in terms of textural composition (e.g. per cent sand, silt, clay and organic matter), bulk density and other such pedological attributes. Over the last two decades soil scientists have developed a set of tools, known collectively as pedotransfer functions (PTFs), to help translate information about the spatial distribution of pedological indicators into corresponding information about soil hydraulic properties. One of the most successful PTFs is the nonlinear Rosetta neural network model developed by one of us. Among remaining open questions are the extents to which spatial and statistical distributions of Rosetta hydraulic property outputs, and their scaling behavior, reflect those of Rosetta pedological inputs. We address the last question by applying Rosetta, coupled with a novel statistical scaling analysis recently proposed by three of us, to soil sample data from an experimental site in southern Arizona, USA.

Original languageEnglish (US)
Title of host publicationSIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications
Pages489-494
Number of pages6
StatePublished - 2013
Event3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications, SIMULTECH 2013 - Reykjavik, Iceland
Duration: Jul 29 2013Jul 31 2013

Other

Other3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications, SIMULTECH 2013
CountryIceland
CityReykjavik
Period7/29/137/31/13

Fingerprint

Neural networks
Soils
Hydraulics
Capillarity
Silt
Biological materials
Water content
Spatial distribution
Clay
Sand
Chemical analysis

Keywords

  • Neural Network
  • Scaling
  • Soil Hydraulic Properties
  • Soil Texture
  • Spatial Statistics

ASJC Scopus subject areas

  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Guadagnini, A., Neuman, S. P., Schaap, M., & Riva, M. (2013). Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site. In SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications (pp. 489-494)

Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site. / Guadagnini, Alberto; Neuman, Shlomo P; Schaap, Marcel; Riva, Monica.

SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications. 2013. p. 489-494.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Guadagnini, A, Neuman, SP, Schaap, M & Riva, M 2013, Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site. in SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications. pp. 489-494, 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications, SIMULTECH 2013, Reykjavik, Iceland, 7/29/13.
Guadagnini A, Neuman SP, Schaap M, Riva M. Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site. In SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications. 2013. p. 489-494
Guadagnini, Alberto ; Neuman, Shlomo P ; Schaap, Marcel ; Riva, Monica. / Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site. SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications. 2013. pp. 489-494
@inproceedings{a1edc0daa4ce4693ba99743c9fe6be95,
title = "Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site",
abstract = "Analyses of flow and transport in the shallow subsurface require information about spatial and statistical distributions of soil hydraulic properties (water content and permeability, their dependence on capillary pressure) as functions of scale and direction. Measuring these properties is relatively difficult, time consuming and costly. It is generally much easier, faster and less expensive to collect and describe the makeup of soil samples in terms of textural composition (e.g. per cent sand, silt, clay and organic matter), bulk density and other such pedological attributes. Over the last two decades soil scientists have developed a set of tools, known collectively as pedotransfer functions (PTFs), to help translate information about the spatial distribution of pedological indicators into corresponding information about soil hydraulic properties. One of the most successful PTFs is the nonlinear Rosetta neural network model developed by one of us. Among remaining open questions are the extents to which spatial and statistical distributions of Rosetta hydraulic property outputs, and their scaling behavior, reflect those of Rosetta pedological inputs. We address the last question by applying Rosetta, coupled with a novel statistical scaling analysis recently proposed by three of us, to soil sample data from an experimental site in southern Arizona, USA.",
keywords = "Neural Network, Scaling, Soil Hydraulic Properties, Soil Texture, Spatial Statistics",
author = "Alberto Guadagnini and Neuman, {Shlomo P} and Marcel Schaap and Monica Riva",
year = "2013",
language = "English (US)",
isbn = "9789898565693",
pages = "489--494",
booktitle = "SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications",

}

TY - GEN

T1 - Statistical and scaling analyses of neural network soil property inputs/outputs at an arizona field site

AU - Guadagnini, Alberto

AU - Neuman, Shlomo P

AU - Schaap, Marcel

AU - Riva, Monica

PY - 2013

Y1 - 2013

N2 - Analyses of flow and transport in the shallow subsurface require information about spatial and statistical distributions of soil hydraulic properties (water content and permeability, their dependence on capillary pressure) as functions of scale and direction. Measuring these properties is relatively difficult, time consuming and costly. It is generally much easier, faster and less expensive to collect and describe the makeup of soil samples in terms of textural composition (e.g. per cent sand, silt, clay and organic matter), bulk density and other such pedological attributes. Over the last two decades soil scientists have developed a set of tools, known collectively as pedotransfer functions (PTFs), to help translate information about the spatial distribution of pedological indicators into corresponding information about soil hydraulic properties. One of the most successful PTFs is the nonlinear Rosetta neural network model developed by one of us. Among remaining open questions are the extents to which spatial and statistical distributions of Rosetta hydraulic property outputs, and their scaling behavior, reflect those of Rosetta pedological inputs. We address the last question by applying Rosetta, coupled with a novel statistical scaling analysis recently proposed by three of us, to soil sample data from an experimental site in southern Arizona, USA.

AB - Analyses of flow and transport in the shallow subsurface require information about spatial and statistical distributions of soil hydraulic properties (water content and permeability, their dependence on capillary pressure) as functions of scale and direction. Measuring these properties is relatively difficult, time consuming and costly. It is generally much easier, faster and less expensive to collect and describe the makeup of soil samples in terms of textural composition (e.g. per cent sand, silt, clay and organic matter), bulk density and other such pedological attributes. Over the last two decades soil scientists have developed a set of tools, known collectively as pedotransfer functions (PTFs), to help translate information about the spatial distribution of pedological indicators into corresponding information about soil hydraulic properties. One of the most successful PTFs is the nonlinear Rosetta neural network model developed by one of us. Among remaining open questions are the extents to which spatial and statistical distributions of Rosetta hydraulic property outputs, and their scaling behavior, reflect those of Rosetta pedological inputs. We address the last question by applying Rosetta, coupled with a novel statistical scaling analysis recently proposed by three of us, to soil sample data from an experimental site in southern Arizona, USA.

KW - Neural Network

KW - Scaling

KW - Soil Hydraulic Properties

KW - Soil Texture

KW - Spatial Statistics

UR - http://www.scopus.com/inward/record.url?scp=84888412759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888412759&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888412759

SN - 9789898565693

SP - 489

EP - 494

BT - SIMULTECH 2013 - Proceedings of the 3rd International Conference on Simulation and Modeling Methodologies, Technologies and Applications

ER -