Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia

The paper introduces a method of digital mapping of spatial distribution of soil typological units. It implements fuzzy k-means to classify the soil profile data (study area from the Považský Inovec Mountains, Slovakia) and regression-kriging with the selected digital terrain and remote sensing data...

Full description

Bibliographic Details
Main Authors: Juraj Balkovič, Gabriela Čemanová, Jozef Kollár, Miroslav Kromka, Katarína Harnová
Format: Article
Language:English
Published: Czech Academy of Agricultural Sciences 2007-12-01
Series:Soil and Water Research
Subjects:
Online Access:https://swr.agriculturejournals.cz/artkey/swr-200704-0002_mapping-soils-using-the-fuzzy-approach-and-regression-kriging-case-study-from-the-povazsky-inovec-mountains-sl.php
_version_ 1797897854281318400
author Juraj Balkovič
Gabriela Čemanová
Jozef Kollár
Miroslav Kromka
Katarína Harnová
author_facet Juraj Balkovič
Gabriela Čemanová
Jozef Kollár
Miroslav Kromka
Katarína Harnová
author_sort Juraj Balkovič
collection DOAJ
description The paper introduces a method of digital mapping of spatial distribution of soil typological units. It implements fuzzy k-means to classify the soil profile data (study area from the Považský Inovec Mountains, Slovakia) and regression-kriging with the selected digital terrain and remote sensing data to draw membership maps of soil typological units. Totally three soil typological units were identified: Haplic Cambisols (Skeletic, Dystric), Albic Stagnic Luvisols, and Haplic Stagnosols (Albic, Dystric). We analysed the membership values to these units with respect to terrain and remote sensing data. The membership values appeared as spatially smoothly dependant on the terrain gradients (linearly or exponentially) whereas the residua showed spatial autocorrelation. Based on regression and kriging analyses, the regression-kriging model was successfully deployed to draw raster membership maps. These maps yield coefficients of determination between R2 = 56% (Albic Stagnic Luvisols) to R2= 79% (Haplic Cambisols (Skeletic, Dystric)) when evaluated by cross validation. The grid-based continuous soil map represents an alternative to the classical polygon soil maps and can offer a wide range of interpretations for landscape studies.
first_indexed 2024-04-10T08:04:58Z
format Article
id doaj.art-2f5d5689217e4ff3a104f497ead4eb27
institution Directory Open Access Journal
issn 1801-5395
1805-9384
language English
last_indexed 2024-04-10T08:04:58Z
publishDate 2007-12-01
publisher Czech Academy of Agricultural Sciences
record_format Article
series Soil and Water Research
spelling doaj.art-2f5d5689217e4ff3a104f497ead4eb272023-02-23T03:48:05ZengCzech Academy of Agricultural SciencesSoil and Water Research1801-53951805-93842007-12-012412313410.17221/2112-SWRswr-200704-0002Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, SlovakiaJuraj Balkovič0Gabriela Čemanová1Jozef Kollár2Miroslav Kromka3Katarína Harnová4Department of Soil Science, Faculty of Natural Science, Comenius University in Bratislava, Bratislava, Slovak RepublicDepartment of Soil Science, Faculty of Natural Science, Comenius University in Bratislava, Bratislava, Slovak RepublicInstitute of Landscape Ecology, Slovak Academy of Sciences, Bratislava, Slovak RepublicDepartment of Soil Science, Faculty of Natural Science, Comenius University in Bratislava, Bratislava, Slovak RepublicDepartment of Soil Science, Faculty of Natural Science, Comenius University in Bratislava, Bratislava, Slovak RepublicThe paper introduces a method of digital mapping of spatial distribution of soil typological units. It implements fuzzy k-means to classify the soil profile data (study area from the Považský Inovec Mountains, Slovakia) and regression-kriging with the selected digital terrain and remote sensing data to draw membership maps of soil typological units. Totally three soil typological units were identified: Haplic Cambisols (Skeletic, Dystric), Albic Stagnic Luvisols, and Haplic Stagnosols (Albic, Dystric). We analysed the membership values to these units with respect to terrain and remote sensing data. The membership values appeared as spatially smoothly dependant on the terrain gradients (linearly or exponentially) whereas the residua showed spatial autocorrelation. Based on regression and kriging analyses, the regression-kriging model was successfully deployed to draw raster membership maps. These maps yield coefficients of determination between R2 = 56% (Albic Stagnic Luvisols) to R2= 79% (Haplic Cambisols (Skeletic, Dystric)) when evaluated by cross validation. The grid-based continuous soil map represents an alternative to the classical polygon soil maps and can offer a wide range of interpretations for landscape studies.https://swr.agriculturejournals.cz/artkey/swr-200704-0002_mapping-soils-using-the-fuzzy-approach-and-regression-kriging-case-study-from-the-povazsky-inovec-mountains-sl.phpfuzzy k-meansregression-krigingdigital landscape datagrid interpretationspatial distributionsoil classification
spellingShingle Juraj Balkovič
Gabriela Čemanová
Jozef Kollár
Miroslav Kromka
Katarína Harnová
Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
Soil and Water Research
fuzzy k-means
regression-kriging
digital landscape data
grid interpretation
spatial distribution
soil classification
title Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
title_full Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
title_fullStr Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
title_full_unstemmed Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
title_short Mapping soils using the fuzzy approach and regression-kriging case study from the Považský Inovec Mountains, Slovakia
title_sort mapping soils using the fuzzy approach and regression kriging case study from the povazsky inovec mountains slovakia
topic fuzzy k-means
regression-kriging
digital landscape data
grid interpretation
spatial distribution
soil classification
url https://swr.agriculturejournals.cz/artkey/swr-200704-0002_mapping-soils-using-the-fuzzy-approach-and-regression-kriging-case-study-from-the-povazsky-inovec-mountains-sl.php
work_keys_str_mv AT jurajbalkovic mappingsoilsusingthefuzzyapproachandregressionkrigingcasestudyfromthepovazskyinovecmountainsslovakia
AT gabrielacemanova mappingsoilsusingthefuzzyapproachandregressionkrigingcasestudyfromthepovazskyinovecmountainsslovakia
AT jozefkollar mappingsoilsusingthefuzzyapproachandregressionkrigingcasestudyfromthepovazskyinovecmountainsslovakia
AT miroslavkromka mappingsoilsusingthefuzzyapproachandregressionkrigingcasestudyfromthepovazskyinovecmountainsslovakia
AT katarinaharnova mappingsoilsusingthefuzzyapproachandregressionkrigingcasestudyfromthepovazskyinovecmountainsslovakia