Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps

Matthew Cracknell, Alison Cowood

    Research output: Contribution to journalArticle

    5 Citations (Scopus)

    Abstract

    The Hydrogeological Landscape (HGL) framework divides geographic space into regions with similar landscape characteristics. HGL regions or units are used to facilitate appropriate management actions tailored to individual HGL units for specific applications such as dryland salinity and climate-change hazard assessment. HGL units are typically constructed by integrating data including geology, regolith, soils, rainfall, vegetation and landscape morphology, and manually defining boundaries in a GIS environment. In this study, we automatically construct spatially contiguous regions from standard HGL data using Self-Organising Maps (SOM), an unsupervised statistical learning algorithm. We compare the resulting SOM-HGL units with manually interpreted HGL units in terms of their spatial distributions and attribute characteristics. Our results show that multiple SOM-HGL units successfully emulate the spatial distributions of individual HGL units. SOM-HGL units are shown to define subregions of larger HGL units, indicating subtle variations in attribute characteristics and representing landscape complexities not mapped during manual interpretation. We also show that SOM-HGL units with similar attributes can be selected using Boolean logic. Selected SOM-HGL units form regions that closely conform to multiple HGL units not necessarily connected in geographic space. These SOM-HGL units can be used to establish generalised land management strategies for areas with common physical characteristics. The use of SOM for the construction of HGL units reduces the subjectivity with which these units are defined and will be especially useful over large and/or inaccessible regions, where conducting field-based validation is either logistically or economically impractical. The methodology presented here has the potential to contribute significantly to land-management decision-support systems based on the HGL framework.

    Original languageEnglish
    Pages (from-to)328-345
    Number of pages18
    JournalSoil Research
    Volume54
    Issue number3
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    analysis
    land management
    spatial distribution
    decision support systems
    decision support system
    regolith
    geology
    hazard assessment
    arid lands
    learning
    GIS
    climate change
    salinity
    rain
    rainfall
    vegetation
    methodology
    attribute
    soil

    Cite this

    Cracknell, Matthew ; Cowood, Alison. / Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps. In: Soil Research. 2016 ; Vol. 54, No. 3. pp. 328-345.
    @article{a466f3937f8347069b1c0a5780342fb7,
    title = "Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps",
    abstract = "The Hydrogeological Landscape (HGL) framework divides geographic space into regions with similar landscape characteristics. HGL regions or units are used to facilitate appropriate management actions tailored to individual HGL units for specific applications such as dryland salinity and climate-change hazard assessment. HGL units are typically constructed by integrating data including geology, regolith, soils, rainfall, vegetation and landscape morphology, and manually defining boundaries in a GIS environment. In this study, we automatically construct spatially contiguous regions from standard HGL data using Self-Organising Maps (SOM), an unsupervised statistical learning algorithm. We compare the resulting SOM-HGL units with manually interpreted HGL units in terms of their spatial distributions and attribute characteristics. Our results show that multiple SOM-HGL units successfully emulate the spatial distributions of individual HGL units. SOM-HGL units are shown to define subregions of larger HGL units, indicating subtle variations in attribute characteristics and representing landscape complexities not mapped during manual interpretation. We also show that SOM-HGL units with similar attributes can be selected using Boolean logic. Selected SOM-HGL units form regions that closely conform to multiple HGL units not necessarily connected in geographic space. These SOM-HGL units can be used to establish generalised land management strategies for areas with common physical characteristics. The use of SOM for the construction of HGL units reduces the subjectivity with which these units are defined and will be especially useful over large and/or inaccessible regions, where conducting field-based validation is either logistically or economically impractical. The methodology presented here has the potential to contribute significantly to land-management decision-support systems based on the HGL framework.",
    keywords = "Hydrogeological landscape framework, Self-organising maps, clustering, spatial analysis, unsupervised statistical learning.",
    author = "Matthew Cracknell and Alison Cowood",
    year = "2016",
    doi = "10.1071/SR15016",
    language = "English",
    volume = "54",
    pages = "328--345",
    journal = "Australian Journal of Soil Research",
    issn = "0004-9573",
    publisher = "CSIRO",
    number = "3",

    }

    Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps. / Cracknell, Matthew; Cowood, Alison.

    In: Soil Research, Vol. 54, No. 3, 2016, p. 328-345.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps

    AU - Cracknell, Matthew

    AU - Cowood, Alison

    PY - 2016

    Y1 - 2016

    N2 - The Hydrogeological Landscape (HGL) framework divides geographic space into regions with similar landscape characteristics. HGL regions or units are used to facilitate appropriate management actions tailored to individual HGL units for specific applications such as dryland salinity and climate-change hazard assessment. HGL units are typically constructed by integrating data including geology, regolith, soils, rainfall, vegetation and landscape morphology, and manually defining boundaries in a GIS environment. In this study, we automatically construct spatially contiguous regions from standard HGL data using Self-Organising Maps (SOM), an unsupervised statistical learning algorithm. We compare the resulting SOM-HGL units with manually interpreted HGL units in terms of their spatial distributions and attribute characteristics. Our results show that multiple SOM-HGL units successfully emulate the spatial distributions of individual HGL units. SOM-HGL units are shown to define subregions of larger HGL units, indicating subtle variations in attribute characteristics and representing landscape complexities not mapped during manual interpretation. We also show that SOM-HGL units with similar attributes can be selected using Boolean logic. Selected SOM-HGL units form regions that closely conform to multiple HGL units not necessarily connected in geographic space. These SOM-HGL units can be used to establish generalised land management strategies for areas with common physical characteristics. The use of SOM for the construction of HGL units reduces the subjectivity with which these units are defined and will be especially useful over large and/or inaccessible regions, where conducting field-based validation is either logistically or economically impractical. The methodology presented here has the potential to contribute significantly to land-management decision-support systems based on the HGL framework.

    AB - The Hydrogeological Landscape (HGL) framework divides geographic space into regions with similar landscape characteristics. HGL regions or units are used to facilitate appropriate management actions tailored to individual HGL units for specific applications such as dryland salinity and climate-change hazard assessment. HGL units are typically constructed by integrating data including geology, regolith, soils, rainfall, vegetation and landscape morphology, and manually defining boundaries in a GIS environment. In this study, we automatically construct spatially contiguous regions from standard HGL data using Self-Organising Maps (SOM), an unsupervised statistical learning algorithm. We compare the resulting SOM-HGL units with manually interpreted HGL units in terms of their spatial distributions and attribute characteristics. Our results show that multiple SOM-HGL units successfully emulate the spatial distributions of individual HGL units. SOM-HGL units are shown to define subregions of larger HGL units, indicating subtle variations in attribute characteristics and representing landscape complexities not mapped during manual interpretation. We also show that SOM-HGL units with similar attributes can be selected using Boolean logic. Selected SOM-HGL units form regions that closely conform to multiple HGL units not necessarily connected in geographic space. These SOM-HGL units can be used to establish generalised land management strategies for areas with common physical characteristics. The use of SOM for the construction of HGL units reduces the subjectivity with which these units are defined and will be especially useful over large and/or inaccessible regions, where conducting field-based validation is either logistically or economically impractical. The methodology presented here has the potential to contribute significantly to land-management decision-support systems based on the HGL framework.

    KW - Hydrogeological landscape framework

    KW - Self-organising maps

    KW - clustering

    KW - spatial analysis

    KW - unsupervised statistical learning.

    UR - http://www.scopus.com/inward/record.url?scp=84966628856&partnerID=8YFLogxK

    UR - http://www.mendeley.com/research/construction-analysis-hydrogeological-landscape-units-using-selforganising-maps

    U2 - 10.1071/SR15016

    DO - 10.1071/SR15016

    M3 - Article

    VL - 54

    SP - 328

    EP - 345

    JO - Australian Journal of Soil Research

    JF - Australian Journal of Soil Research

    SN - 0004-9573

    IS - 3

    ER -