Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks

J. F.Lavado Contador; M. Maneta; S. Schnabel

doi:10.1007/s10661-005-9116-2

Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks

J. F.Lavado Contador
, M. Maneta
, S. Schnabel

Geosciences

University of Extremadura

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

20 Scopus citations

Abstract

The capability of Artificial Neural Network models to forecast near-surface soil moisture at fine spatial scale resolution has been tested for a 99.5 ha watershed located in SW Spain using several easy to achieve digital models of topographic and land cover variables as inputs and a series of soil moisture measurements as training data set. The study methods were designed in order to determining the potentials of the neural network model as a tool to gain insight into soil moisture distribution factors and also in order to optimize the data sampling scheme finding the optimum size of the training data set. Results suggest the efficiency of the methods in forecasting soil moisture, as a tool to assess the optimum number of field samples, and the importance of the variables selected in explaining the final map obtained.

Original language	English
Pages (from-to)	211-230
Number of pages	20
Journal	Environmental Monitoring and Assessment
Volume	121
Issue number	1-3
DOIs	https://doi.org/10.1007/s10661-005-9116-2
State	Published - Oct 2006

Funding

PROHISEM (REN2001-2268-C02-02), EPIMODE (REN2003-08621(GLO) and CANOA (CGL-2004-04919-C02-02) Research Projects funded by the Spanish Ministry of Science and Technology economically supported this work. We would also thank to David Lagar Timón, Álvaro Gómez Gutiérrez and Arturo Sánchez Lorenzo for their help during the field work, and also to the two anonymous reviewers that kindly improved the quality of the manuscript.

Funder number
CGL-2004-04919-C02-02
REN2003-08621

Keywords

Dehesa
Forecasting soil moisture
Sampling
Topographic variables

Access to Document

10.1007/s10661-005-9116-2

Cite this

@article{a5cea83b29bc4556be8e269383154d3e,

title = "Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks",

abstract = "The capability of Artificial Neural Network models to forecast near-surface soil moisture at fine spatial scale resolution has been tested for a 99.5 ha watershed located in SW Spain using several easy to achieve digital models of topographic and land cover variables as inputs and a series of soil moisture measurements as training data set. The study methods were designed in order to determining the potentials of the neural network model as a tool to gain insight into soil moisture distribution factors and also in order to optimize the data sampling scheme finding the optimum size of the training data set. Results suggest the efficiency of the methods in forecasting soil moisture, as a tool to assess the optimum number of field samples, and the importance of the variables selected in explaining the final map obtained.",

keywords = "Dehesa, Forecasting soil moisture, Sampling, Topographic variables",

author = "Contador, \{J. F.Lavado\} and M. Maneta and S. Schnabel",

note = "Funding Information: PROHISEM (REN2001-2268-C02-02), EPIMODE (REN2003-08621(GLO) and CANOA (CGL-2004-04919-C02-02) Research Projects funded by the Spanish Ministry of Science and Technology economically supported this work. We would also thank to David Lagar Tim{\'o}n, {\'A}lvaro G{\'o}mez Guti{\'e}rrez and Arturo S{\'a}nchez Lorenzo for their help during the field work, and also to the two anonymous reviewers that kindly improved the quality of the manuscript.",

year = "2006",

month = oct,

doi = "10.1007/s10661-005-9116-2",

language = "English",

volume = "121",

pages = "211--230",

journal = "Environmental Monitoring and Assessment",

issn = "0167-6369",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "1-3",

}

TY - JOUR

T1 - Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks

AU - Contador, J. F.Lavado

AU - Maneta, M.

AU - Schnabel, S.

N1 - Funding Information: PROHISEM (REN2001-2268-C02-02), EPIMODE (REN2003-08621(GLO) and CANOA (CGL-2004-04919-C02-02) Research Projects funded by the Spanish Ministry of Science and Technology economically supported this work. We would also thank to David Lagar Timón, Álvaro Gómez Gutiérrez and Arturo Sánchez Lorenzo for their help during the field work, and also to the two anonymous reviewers that kindly improved the quality of the manuscript.

PY - 2006/10

Y1 - 2006/10

N2 - The capability of Artificial Neural Network models to forecast near-surface soil moisture at fine spatial scale resolution has been tested for a 99.5 ha watershed located in SW Spain using several easy to achieve digital models of topographic and land cover variables as inputs and a series of soil moisture measurements as training data set. The study methods were designed in order to determining the potentials of the neural network model as a tool to gain insight into soil moisture distribution factors and also in order to optimize the data sampling scheme finding the optimum size of the training data set. Results suggest the efficiency of the methods in forecasting soil moisture, as a tool to assess the optimum number of field samples, and the importance of the variables selected in explaining the final map obtained.

AB - The capability of Artificial Neural Network models to forecast near-surface soil moisture at fine spatial scale resolution has been tested for a 99.5 ha watershed located in SW Spain using several easy to achieve digital models of topographic and land cover variables as inputs and a series of soil moisture measurements as training data set. The study methods were designed in order to determining the potentials of the neural network model as a tool to gain insight into soil moisture distribution factors and also in order to optimize the data sampling scheme finding the optimum size of the training data set. Results suggest the efficiency of the methods in forecasting soil moisture, as a tool to assess the optimum number of field samples, and the importance of the variables selected in explaining the final map obtained.

KW - Dehesa

KW - Forecasting soil moisture

KW - Sampling

KW - Topographic variables

UR - https://www.scopus.com/pages/publications/33750368862

U2 - 10.1007/s10661-005-9116-2

DO - 10.1007/s10661-005-9116-2

M3 - Article

C2 - 16752041

AN - SCOPUS:33750368862

SN - 0167-6369

VL - 121

SP - 211

EP - 230

JO - Environmental Monitoring and Assessment

JF - Environmental Monitoring and Assessment

IS - 1-3

ER -

Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this