Show simple item record

dc.contributor.author
Taghizadeh-Mehrjardi, Ruhollah
dc.contributor.author
Hamzehpour, Nikou
dc.contributor.author
Hassanzadeh, Maryam
dc.contributor.author
Heung, Brandon
dc.contributor.author
Ghebleh Goydaragh, Maryam
dc.contributor.author
Schmidt, Karsten
dc.contributor.author
Scholten, Thomas
dc.date.accessioned
2021-04-27T05:50:42Z
dc.date.available
2021-04-25T08:41:48Z
dc.date.available
2021-04-27T05:50:42Z
dc.date.issued
2021-10-01
dc.identifier.issn
0016-7061
dc.identifier.issn
1872-6259
dc.identifier.other
10.1016/j.geoderma.2021.115108
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/480382
dc.description.abstract
Digital soil mapping approaches predict soil properties based on the relationships between soil observations and related environmental covariates using techniques such as machine learning (ML) models. In this research, a wide range of ML models (12 base learners) were tested in predicting and mapping soil properties. Furthermore, a super learner approach was used to improve model accuracy by combining the predictions of the base learners. A major challenge of using super learner and complex models is that the exact contribution of individual covariates in the overall prediction is not always known. To address this issue, permutation feature importance (PFI) analysis was applied as a model-agnostic interpretation tool. The weights assigned to each ML base learner obtained from super learner, and feature importance values obtained from each ML base learner were used to quantify the contribution of individual covariates on the final prediction. The super learner and PFI techniques were tested by predicting a variety of soil physical and chemical properties of the Urmia Lake playa in Iran. As expected, the results indicated that the super learner had substantially higher accuracies for predicting soil properties in comparison to the individual base learners. For instance, the super learner showed an improved performance in comparison to linear regression by decreasing the root mean square error by an average of 46%. The PFI analysis revealed the important contribution of geomorphic and groundwater data in predicting soil properties. Overall, the proposed approach may be used for improving accuracy of ML models in digital soil mapping.
en_US
dc.language.iso
en
en_US
dc.publisher
Elsevier
en_US
dc.subject
Super learner
en_US
dc.subject
Model-agnostic
en_US
dc.subject
Digital soil mapping
en_US
dc.subject
Saline soils
en_US
dc.subject
Urmia Playa Lake
en_US
dc.subject
Iran
en_US
dc.title
Enhancing the accuracy of machine learning models using the super learner technique in digital soil mapping
en_US
dc.type
Journal Article
dc.date.published
2021-04-15
ethz.journal.title
Geoderma
ethz.journal.volume
399
en_US
ethz.journal.abbreviated
Geoderma
ethz.pages.start
115108
en_US
ethz.size
13 p.
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Amsterdam
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2021-04-25T08:41:57Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-04-27T05:50:52Z
ethz.rosetta.lastUpdated
2022-03-29T06:46:02Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Enhancing%20the%20accuracy%20of%20machine%20learning%20models%20using%20the%20super%20learner%20technique%20in%20digital%20soil%20mapping&rft.jtitle=Geoderma&rft.date=2021-10-01&rft.volume=399&rft.spage=115108&rft.issn=0016-7061&1872-6259&rft.au=Taghizadeh-Mehrjardi,%20Ruhollah&Hamzehpour,%20Nikou&Hassanzadeh,%20Maryam&Heung,%20Brandon&Ghebleh%20Goydaragh,%20Maryam&rft.genre=article&rft_id=info:doi/10.1016/j.geoderma.2021.115108&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record