Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Standard

Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives. / Beucher, Amélie; Adhikari, Kabindra; Breuning-Madsen, Henrik; Greve, Mette Balslev; Österholm, P.; Fröjdö, S.; Nielsen, N.H.; Greve, Mogens Humlekrog.

I: Geoderma, Bind 308, 2017, s. 363-372.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

Harvard

Beucher, A, Adhikari, K, Breuning-Madsen, H, Greve, MB, Österholm, P, Fröjdö, S, Nielsen, NH & Greve, MH 2017, 'Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives', Geoderma, bind 308, s. 363-372. https://doi.org/10.1016/j.geoderma.2016.06.001

APA

CBE

MLA

Vancouver

Author

Beucher, Amélie ; Adhikari, Kabindra ; Breuning-Madsen, Henrik ; Greve, Mette Balslev ; Österholm, P. ; Fröjdö, S. ; Nielsen, N.H. ; Greve, Mogens Humlekrog. / Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives. I: Geoderma. 2017 ; Bind 308. s. 363-372.

Bibtex

@article{156b589fc4414b668892df3de4e2f90e,
title = "Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives",
abstract = "Leaching large amounts of acidity and metals into recipient watercourses and estuaries, acid sulfate (a.s.) soilsconstitute a substantial environmental issue worldwide. Mapping of these soils enables measures to be takento prevent pollution in high risk areas. In Denmark, legislation prohibits drainage of areas classified as potentiala.s. soilswithout prior permission fromenvironmental authorities. Themapping of these soils was first conductedin the 1980’s.Wetlands, inwhich Danish potential a.s. soils mostly occur,were targeted and the soilswere surveyedthrough conventional mapping. In this study, a probability map for potential a.s. soil occurrence wasconstructed for thewetlands located in Jutland, Denmark (c. 6500 km2), using the digital soilmapping (DSM) approach.Among the variety of available DSM techniques, artificial neural networks (ANNs) were selected. Morethan 8000 existing soil observations and 16 environmental variables, including geology, landscape type, landuse and terrain parameters,were available as input datawithin themodeling. Predictionmodels based on variousnetwork topologieswere assessed for different selections of soil observations and combinations of environmentalvariables. The overall prediction accuracy based on a 30{\%} hold-back validation data reached 70{\%}. Furthermore,the conventional map indicated 32{\%} of the study area (c. 2100 km2) as having a high frequency for potentiala.s. soils while the digital map displayed about 46{\%} (c. 3000 km2) as high probability areas for potential a.s.soil occurrence. ANNs, thus, demonstrated promising predictive classification abilities for themapping of potentiala.s. soils on a large extent.",
author = "Am{\'e}lie Beucher and Kabindra Adhikari and Henrik Breuning-Madsen and Greve, {Mette Balslev} and P. {\"O}sterholm and S. Fr{\"o}jd{\"o} and N.H. Nielsen and Greve, {Mogens Humlekrog}",
year = "2017",
doi = "10.1016/j.geoderma.2016.06.001",
language = "English",
volume = "308",
pages = "363--372",
journal = "Geoderma",
issn = "0016-7061",
publisher = "Elsevier BV",

}

RIS

TY - JOUR

T1 - Mapping potential acid sulfate soils in Denmark using legacy data and LiDAR-based derivatives

AU - Beucher, Amélie

AU - Adhikari, Kabindra

AU - Breuning-Madsen, Henrik

AU - Greve, Mette Balslev

AU - Österholm, P.

AU - Fröjdö, S.

AU - Nielsen, N.H.

AU - Greve, Mogens Humlekrog

PY - 2017

Y1 - 2017

N2 - Leaching large amounts of acidity and metals into recipient watercourses and estuaries, acid sulfate (a.s.) soilsconstitute a substantial environmental issue worldwide. Mapping of these soils enables measures to be takento prevent pollution in high risk areas. In Denmark, legislation prohibits drainage of areas classified as potentiala.s. soilswithout prior permission fromenvironmental authorities. Themapping of these soils was first conductedin the 1980’s.Wetlands, inwhich Danish potential a.s. soils mostly occur,were targeted and the soilswere surveyedthrough conventional mapping. In this study, a probability map for potential a.s. soil occurrence wasconstructed for thewetlands located in Jutland, Denmark (c. 6500 km2), using the digital soilmapping (DSM) approach.Among the variety of available DSM techniques, artificial neural networks (ANNs) were selected. Morethan 8000 existing soil observations and 16 environmental variables, including geology, landscape type, landuse and terrain parameters,were available as input datawithin themodeling. Predictionmodels based on variousnetwork topologieswere assessed for different selections of soil observations and combinations of environmentalvariables. The overall prediction accuracy based on a 30% hold-back validation data reached 70%. Furthermore,the conventional map indicated 32% of the study area (c. 2100 km2) as having a high frequency for potentiala.s. soils while the digital map displayed about 46% (c. 3000 km2) as high probability areas for potential a.s.soil occurrence. ANNs, thus, demonstrated promising predictive classification abilities for themapping of potentiala.s. soils on a large extent.

AB - Leaching large amounts of acidity and metals into recipient watercourses and estuaries, acid sulfate (a.s.) soilsconstitute a substantial environmental issue worldwide. Mapping of these soils enables measures to be takento prevent pollution in high risk areas. In Denmark, legislation prohibits drainage of areas classified as potentiala.s. soilswithout prior permission fromenvironmental authorities. Themapping of these soils was first conductedin the 1980’s.Wetlands, inwhich Danish potential a.s. soils mostly occur,were targeted and the soilswere surveyedthrough conventional mapping. In this study, a probability map for potential a.s. soil occurrence wasconstructed for thewetlands located in Jutland, Denmark (c. 6500 km2), using the digital soilmapping (DSM) approach.Among the variety of available DSM techniques, artificial neural networks (ANNs) were selected. Morethan 8000 existing soil observations and 16 environmental variables, including geology, landscape type, landuse and terrain parameters,were available as input datawithin themodeling. Predictionmodels based on variousnetwork topologieswere assessed for different selections of soil observations and combinations of environmentalvariables. The overall prediction accuracy based on a 30% hold-back validation data reached 70%. Furthermore,the conventional map indicated 32% of the study area (c. 2100 km2) as having a high frequency for potentiala.s. soils while the digital map displayed about 46% (c. 3000 km2) as high probability areas for potential a.s.soil occurrence. ANNs, thus, demonstrated promising predictive classification abilities for themapping of potentiala.s. soils on a large extent.

U2 - 10.1016/j.geoderma.2016.06.001

DO - 10.1016/j.geoderma.2016.06.001

M3 - Journal article

VL - 308

SP - 363

EP - 372

JO - Geoderma

JF - Geoderma

SN - 0016-7061

ER -