Identifying electrical conductivity in topsoil by interpretable machine learning

Basit Öğe Kaydı
dc.authoridTutmez, Bulent/0000-0002-2618-3285
dc.contributor.authorTutmez, Bulent
dc.date.accessioned2024-08-04T20:54:46Z
dc.date.available2024-08-04T20:54:46Z
dc.date.issued2024
dc.departmentİnönü Üniversitesien_US
dc.description.abstractImplementing computational and statistical intelligence allows understanding variations to make knowledgeable decisions in agriculture and land use. In this study, using the interpretation capacity of functional precision models against the lower-level mechanistic models has been given priority and advanced regression algorithms were used for this purpose. For exploring the relationships between electrical conductivity (EC) which is the most critical indicator for salinity and irrigation and soil parameters (texture, chemical concentrations) a comparative assessment based on supervised learning algorithms has been conducted and the outcomes have been interpreted by statistical learning. Both linear and non-linear statistical approaches have been used to analyze EC since it is a heterogeneous natural feature in topsoil. The implementations showed that the non-linear MARS model has provided the best testing accuracy. In addition to precision, relationships between EC and indicator variables, major modelling components and measure of the parameter effects have been exhibited by estimated probabilities and partial dependence measures. The main drivers for EC assessment in topsoil, specifically pH in water, CaCl2, and nitrogen concentration, have been discovered. The benchmarking results revealed that different from the conventional mechanistic models, interpretable machine learning provides additional interpretation, meta-data and transparency for sustainable soil management and environment.en_US
dc.description.sponsorshipThe author would like to extend his appreciation to the European Soil Data Center for the permission of the data sets.en_US
dc.description.sponsorshipThe author would like to extend his appreciation to the European Soil Data Center for the permission of the data sets.en_US
dc.identifier.doi10.1007/s40808-023-01878-0
dc.identifier.endpage1881en_US
dc.identifier.issn2363-6203
dc.identifier.issn2363-6211
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-85173690826en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage1869en_US
dc.identifier.urihttps://doi.org/10.1007/s40808-023-01878-0
dc.identifier.urihttps://hdl.handle.net/11616/101613
dc.identifier.volume10en_US
dc.identifier.wosWOS:001080572000001en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Heidelbergen_US
dc.relation.ispartofModeling Earth Systems and Environmenten_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectSoilen_US
dc.subjectElectrical conductivityen_US
dc.subjectInterpretable machine learningen_US
dc.subjectPartial dependence ploten_US
dc.titleIdentifying electrical conductivity in topsoil by interpretable machine learningen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu