Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression

In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Smit, I.E. [verfasserIn] Van Zijl, G.M. [verfasserIn] Riddell, E.S. [verfasserIn] Van Tol, J.J. [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	Hydropedology K-means clustering Digital soil mapping SMOTE

Übergeordnetes Werk:	Enthalten in: Geoderma - Amsterdam [u.a.] : Elsevier Science, 1967, 436
Übergeordnetes Werk:	volume:436

DOI / URN:	10.1016/j.geoderma.2023.116568

Katalog-ID:	ELV010564977

Internformat


LEADER	01000naa a22002652 4500
001	ELV010564977
003	DE-627
005	20230620073008.0
007	cr uuu---uuuuu
008	230620s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1016/j.geoderma.2023.116568 \|2 doi
035			\|a (DE-627)ELV010564977
035			\|a (ELSEVIER)S0016-7061(23)00245-8
040			\|a DE-627 \|b ger \|c DE-627 \|e rda
041			\|a eng
082	0	4	\|a 550 \|a 910 \|q VZ
084			\|a 38.60 \|2 bkl
100	1		\|a Smit, I.E. \|e verfasserin \|0 (orcid)0000-0003-1513-4493 \|4 aut
245	1	0	\|a Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
264		1	\|c 2023
336			\|a nicht spezifiziert \|b zzz \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.
650		4	\|a Hydropedology
650		4	\|a K-means clustering
650		4	\|a Digital soil mapping
650		4	\|a SMOTE
700	1		\|a Van Zijl, G.M. \|e verfasserin \|4 aut
700	1		\|a Riddell, E.S. \|e verfasserin \|4 aut
700	1		\|a Van Tol, J.J. \|e verfasserin \|4 aut
773	0	8	\|i Enthalten in \|t Geoderma \|d Amsterdam [u.a.] : Elsevier Science, 1967 \|g 436 \|h Online-Ressource \|w (DE-627)320414493 \|w (DE-600)2001729-7 \|w (DE-576)099603853 \|x 1872-6259 \|7 nnns
773	1	8	\|g volume:436
912			\|a GBV_USEFLAG_U
912			\|a SYSFLAG_U
912			\|a GBV_ELV
912			\|a SSG-OPC-GGO
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_150
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2004
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2336
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
936	b	k	\|a 38.60 \|j Bodenkunde: Allgemeines \|x Geowissenschaften \|q VZ
951			\|a AR
952			\|d 436

Indexfelder

author_variant	i s is z g v zg zgv e r er t j v tj tjv
matchkey_str	article:18726259:2023----::onclnlgcsiifrainohdooiasimpigsnmli
hierarchy_sort_str	2023
bklnumber	38.60
publishDate	2023
allfields	10.1016/j.geoderma.2023.116568 doi (DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8 DE-627 ger DE-627 rda eng 550 910 VZ 38.60 bkl Smit, I.E. verfasserin (orcid)0000-0003-1513-4493 aut Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Hydropedology K-means clustering Digital soil mapping SMOTE Van Zijl, G.M. verfasserin aut Riddell, E.S. verfasserin aut Van Tol, J.J. verfasserin aut Enthalten in Geoderma Amsterdam [u.a.] : Elsevier Science, 1967 436 Online-Ressource (DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853 1872-6259 nnns volume:436 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.60 Bodenkunde: Allgemeines Geowissenschaften VZ AR 436
spelling	10.1016/j.geoderma.2023.116568 doi (DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8 DE-627 ger DE-627 rda eng 550 910 VZ 38.60 bkl Smit, I.E. verfasserin (orcid)0000-0003-1513-4493 aut Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Hydropedology K-means clustering Digital soil mapping SMOTE Van Zijl, G.M. verfasserin aut Riddell, E.S. verfasserin aut Van Tol, J.J. verfasserin aut Enthalten in Geoderma Amsterdam [u.a.] : Elsevier Science, 1967 436 Online-Ressource (DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853 1872-6259 nnns volume:436 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.60 Bodenkunde: Allgemeines Geowissenschaften VZ AR 436
allfields_unstemmed	10.1016/j.geoderma.2023.116568 doi (DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8 DE-627 ger DE-627 rda eng 550 910 VZ 38.60 bkl Smit, I.E. verfasserin (orcid)0000-0003-1513-4493 aut Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Hydropedology K-means clustering Digital soil mapping SMOTE Van Zijl, G.M. verfasserin aut Riddell, E.S. verfasserin aut Van Tol, J.J. verfasserin aut Enthalten in Geoderma Amsterdam [u.a.] : Elsevier Science, 1967 436 Online-Ressource (DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853 1872-6259 nnns volume:436 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.60 Bodenkunde: Allgemeines Geowissenschaften VZ AR 436
allfieldsGer	10.1016/j.geoderma.2023.116568 doi (DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8 DE-627 ger DE-627 rda eng 550 910 VZ 38.60 bkl Smit, I.E. verfasserin (orcid)0000-0003-1513-4493 aut Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Hydropedology K-means clustering Digital soil mapping SMOTE Van Zijl, G.M. verfasserin aut Riddell, E.S. verfasserin aut Van Tol, J.J. verfasserin aut Enthalten in Geoderma Amsterdam [u.a.] : Elsevier Science, 1967 436 Online-Ressource (DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853 1872-6259 nnns volume:436 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.60 Bodenkunde: Allgemeines Geowissenschaften VZ AR 436
allfieldsSound	10.1016/j.geoderma.2023.116568 doi (DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8 DE-627 ger DE-627 rda eng 550 910 VZ 38.60 bkl Smit, I.E. verfasserin (orcid)0000-0003-1513-4493 aut Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR. Hydropedology K-means clustering Digital soil mapping SMOTE Van Zijl, G.M. verfasserin aut Riddell, E.S. verfasserin aut Van Tol, J.J. verfasserin aut Enthalten in Geoderma Amsterdam [u.a.] : Elsevier Science, 1967 436 Online-Ressource (DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853 1872-6259 nnns volume:436 GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 38.60 Bodenkunde: Allgemeines Geowissenschaften VZ AR 436
language	English
source	Enthalten in Geoderma 436 volume:436
sourceStr	Enthalten in Geoderma 436 volume:436
format_phy_str_mv	Article
bklname	Bodenkunde: Allgemeines
institution	findex.gbv.de
topic_facet	Hydropedology K-means clustering Digital soil mapping SMOTE
dewey-raw	550
isfreeaccess_bool	false
container_title	Geoderma
authorswithroles_txt_mv	Smit, I.E. @@aut@@ Van Zijl, G.M. @@aut@@ Riddell, E.S. @@aut@@ Van Tol, J.J. @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	320414493
dewey-sort	3550
id	ELV010564977
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">ELV010564977</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230620073008.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230620s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.geoderma.2023.116568</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV010564977</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0016-7061(23)00245-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="a">910</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.60</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Smit, I.E.</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-1513-4493</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hydropedology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">K-means clustering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Digital soil mapping</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SMOTE</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Zijl, G.M.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Riddell, E.S.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Tol, J.J.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Geoderma</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1967</subfield><subfield code="g">436</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)320414493</subfield><subfield code="w">(DE-600)2001729-7</subfield><subfield code="w">(DE-576)099603853</subfield><subfield code="x">1872-6259</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:436</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.60</subfield><subfield code="j">Bodenkunde: Allgemeines</subfield><subfield code="x">Geowissenschaften</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">436</subfield></datafield></record></collection>
author	Smit, I.E.
spellingShingle	Smit, I.E. ddc 550 bkl 38.60 misc Hydropedology misc K-means clustering misc Digital soil mapping misc SMOTE Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
authorStr	Smit, I.E.
ppnlink_with_tag_str_mv	@@773@@(DE-627)320414493
format	electronic Article
dewey-ones	550 - Earth sciences 910 - Geography & travel
delete_txt_mv	keep
author_role	aut aut aut aut
collection	elsevier
remote_str	true
illustrated	Not Illustrated
issn	1872-6259
topic_title	550 910 VZ 38.60 bkl Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression Hydropedology K-means clustering Digital soil mapping SMOTE
topic	ddc 550 bkl 38.60 misc Hydropedology misc K-means clustering misc Digital soil mapping misc SMOTE
topic_unstemmed	ddc 550 bkl 38.60 misc Hydropedology misc K-means clustering misc Digital soil mapping misc SMOTE
topic_browse	ddc 550 bkl 38.60 misc Hydropedology misc K-means clustering misc Digital soil mapping misc SMOTE
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Geoderma
hierarchy_parent_id	320414493
dewey-tens	550 - Earth sciences & geology 910 - Geography & travel
hierarchy_top_title	Geoderma
isfreeaccess_txt	false
familylinks_str_mv	(DE-627)320414493 (DE-600)2001729-7 (DE-576)099603853
title	Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
ctrlnum	(DE-627)ELV010564977 (ELSEVIER)S0016-7061(23)00245-8
title_full	Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
author_sort	Smit, I.E.
journal	Geoderma
journalStr	Geoderma
lang_code	eng
isOA_bool	false
dewey-hundreds	500 - Science 900 - History & geography
recordtype	marc
publishDateSort	2023
contenttype_str_mv	zzz
author_browse	Smit, I.E. Van Zijl, G.M. Riddell, E.S. Van Tol, J.J.
container_volume	436
class	550 910 VZ 38.60 bkl
format_se	Elektronische Aufsätze
author-letter	Smit, I.E.
doi_str_mv	10.1016/j.geoderma.2023.116568
normlink	(ORCID)0000-0003-1513-4493
normlink_prefix_str_mv	(orcid)0000-0003-1513-4493
dewey-full	550 910
author2-role	verfasserin
title_sort	downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
title_auth	Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
abstract	In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.
abstractGer	In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.
abstract_unstemmed	In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.
collection_details	GBV_USEFLAG_U SYSFLAG_U GBV_ELV SSG-OPC-GGO GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2004 GBV_ILN_2014 GBV_ILN_2336 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression
remote_bool	true
author2	Van Zijl, G.M. Riddell, E.S. Van Tol, J.J.
author2Str	Van Zijl, G.M. Riddell, E.S. Van Tol, J.J.
ppnlink	320414493
mediatype_str_mv	c
isOA_txt	false
hochschulschrift_bool	false
doi_str	10.1016/j.geoderma.2023.116568
up_date	2024-07-06T18:26:19.969Z
_version_	1803855205468471296
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">ELV010564977</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230620073008.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230620s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.geoderma.2023.116568</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV010564977</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0016-7061(23)00245-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">550</subfield><subfield code="a">910</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">38.60</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Smit, I.E.</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0003-1513-4493</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In South Africa, there is a growing demand for large scale detailed hydrological soil maps for modelling and management purposes. However, imbalanced legacy soil information often impedes the accurate creation of such maps by not being representative of the environmental complexity of large-scale catchments and containing imbalanced soil class distributions, often resulting in the loss of minority soil classes, which are often of great hydrological importance (e.g., wetland and riparian soils). In this study, we proposed a new downscaling approach to handle spatially localised legacy soil data within a larger low resolution legacy soil dataset to create an accurate hydrological soil map of the macro-scale (5790 km2) Sabie-Sand catchment using multinomial logistic regression (MNLR). The spatially localised legacy data was downscaled using k-means clustering and added to the broader legacy dataset. Five levels of legacy soil data were analysed in their representation of environmental covariates using QQ-plots and a Welsh’s t-test and their mapping accuracy using confusion matrix’s and Kappa coefficient statistics. However, MNLR also requires balanced soil classes. The value of the best performing legacy soil dataset was also compared to using all available soil information after both had their soil class distributions fully balanced using Synthetic Minority Oversampling Technique (SMOTE). The 500 ha/observation-SMOTE dataset resulted in the most accurate hydrological soil map with a validation point accuracy of 73% and a Kappa coefficient of 0.60, substantially outperforming the other downscaled soil maps as well as the SMOTE balanced dataset using all available soil information. This was due to the decreased variation between observations and catchment means, where the 500 ha/observation dataset yielded the least variation between soil observation and catchment datasets and well as reducing the class imbalance within the legacy soil data. Downscaling spatially localised legacy soil data for environmental representation is an effective tool to improve digital soil mapping accuracy using MNLR.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hydropedology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">K-means clustering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Digital soil mapping</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SMOTE</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Zijl, G.M.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Riddell, E.S.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Van Tol, J.J.</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Geoderma</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1967</subfield><subfield code="g">436</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)320414493</subfield><subfield code="w">(DE-600)2001729-7</subfield><subfield code="w">(DE-576)099603853</subfield><subfield code="x">1872-6259</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:436</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">38.60</subfield><subfield code="j">Bodenkunde: Allgemeines</subfield><subfield code="x">Geowissenschaften</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">436</subfield></datafield></record></collection>
score	7.402439

Nicht das Richtige dabei?

Schreiben Sie uns!

Downscaling legacy soil information for hydrological soil mapping using multinomial logistic regression

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?