A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

This study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Fo...

Full description

Bibliographic Details
Main Authors: Ruhollah Taghizadeh-Mehrjardi, Hossein Khademi, Fatemeh Khayamim, Mojtaba Zeraatpisheh, Brandon Heung, Thomas Scholten
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/14/3/472
_version_ 1797485173410889728
author Ruhollah Taghizadeh-Mehrjardi
Hossein Khademi
Fatemeh Khayamim
Mojtaba Zeraatpisheh
Brandon Heung
Thomas Scholten
author_facet Ruhollah Taghizadeh-Mehrjardi
Hossein Khademi
Fatemeh Khayamim
Mojtaba Zeraatpisheh
Brandon Heung
Thomas Scholten
author_sort Ruhollah Taghizadeh-Mehrjardi
collection DOAJ
description This study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Forest base learners were the most effective in predicting soil organic matter and electrical conductivity, respectively. However, all seven model averaging techniques performed better than the base learners. For example, the Granger–Ramanathan averaging approach resulted in the highest prediction accuracy for soil organic matter, while the Bayesian model averaging approach was most effective in predicting sand content. These results indicate that the model averaging approaches could improve the predictive accuracy for soil properties. The resulting maps, produced at a 30 m spatial resolution, can be used as valuable baseline information for managing environmental resources more effectively.
first_indexed 2024-03-09T23:14:59Z
format Article
id doaj.art-b876e62398984d578a78e810d775fd14
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-09T23:14:59Z
publishDate 2022-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-b876e62398984d578a78e810d775fd142023-11-23T17:38:11ZengMDPI AGRemote Sensing2072-42922022-01-0114347210.3390/rs14030472A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil PropertiesRuhollah Taghizadeh-Mehrjardi0Hossein Khademi1Fatemeh Khayamim2Mojtaba Zeraatpisheh3Brandon Heung4Thomas Scholten5Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, 72070 Tübingen, GermanyDepartment of Soil Science, College of Agriculture, Isfahan University of Technology, Isfahan 8415683111, IranDepartment of Soil Science, College of Agriculture, Isfahan University of Technology, Isfahan 8415683111, IranHenan Key Laboratory of Earth System Observation and Modeling, Henan University, Kaifeng 475004, ChinaDepartment of Plant, Food, and Environmental Sciences, Faculty of Agriculture, Dalhousie University, Truro, NS B2N 5E3, CanadaDepartment of Geosciences, Soil Science and Geomorphology, University of Tübingen, 72070 Tübingen, GermanyThis study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Forest base learners were the most effective in predicting soil organic matter and electrical conductivity, respectively. However, all seven model averaging techniques performed better than the base learners. For example, the Granger–Ramanathan averaging approach resulted in the highest prediction accuracy for soil organic matter, while the Bayesian model averaging approach was most effective in predicting sand content. These results indicate that the model averaging approaches could improve the predictive accuracy for soil properties. The resulting maps, produced at a 30 m spatial resolution, can be used as valuable baseline information for managing environmental resources more effectively.https://www.mdpi.com/2072-4292/14/3/472spatial modelingmachine learningremote sensingmodel averaging
spellingShingle Ruhollah Taghizadeh-Mehrjardi
Hossein Khademi
Fatemeh Khayamim
Mojtaba Zeraatpisheh
Brandon Heung
Thomas Scholten
A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
Remote Sensing
spatial modeling
machine learning
remote sensing
model averaging
title A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
title_full A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
title_fullStr A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
title_full_unstemmed A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
title_short A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties
title_sort comparison of model averaging techniques to predict the spatial distribution of soil properties
topic spatial modeling
machine learning
remote sensing
model averaging
url https://www.mdpi.com/2072-4292/14/3/472
work_keys_str_mv AT ruhollahtaghizadehmehrjardi acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT hosseinkhademi acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT fatemehkhayamim acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT mojtabazeraatpisheh acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT brandonheung acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT thomasscholten acomparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT ruhollahtaghizadehmehrjardi comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT hosseinkhademi comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT fatemehkhayamim comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT mojtabazeraatpisheh comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT brandonheung comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties
AT thomasscholten comparisonofmodelaveragingtechniquestopredictthespatialdistributionofsoilproperties