Construction and analysis of Hydrogeological Landscape units using Self-Organising Maps
M. J. Cracknell A B E and A. L. Cowood C D
+ Author Affiliations
- Author Affiliations
A School of Physical Sciences (Earth Sciences), University of Tasmania, Private Bag 79, Hobart, Tas. 7001 Australia.
B Centre of Excellence in Ore Deposits (CODES), University of Tasmania, Private Bag 79, Hobart Tas. 7001, Australia; Current address: ARC Research Hub for Transforming the Mining Value Chain, University of Tasmania, Private Bag 79, Hobart, Tas. 7001, Australia.
C Dryland Salinity Hazard Mitigation Program, University of Canberra, ACT 2601, Australia.
D Institute for Applied Ecology, University of Canberra, ACT 2601, Australia.
E Corresponding author. Email: m.j.cracknell@utas.edu.au
Soil Research 54(3) 328-345 https://doi.org/10.1071/SR15016
Submitted: 20 January 2015 Accepted: 17 June 2015 Published: 19 April 2016
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.
Additional keywords: clustering, Hydrogeological landscape framework, Self-organising maps, spatial analysis, unsupervised statistical learning.
References
Bação F, Lobo V, Painho M (2008) Introduction: What is a self-organzing map. In ‘Applications of different self-organizing map variants to geographical information science problems’. (Eds A Skupin, P Agarwal) pp. 21–44. (John Wiley & Sons Ltd.: Chichester, UK)Bedini E (2009) Mapping lithology of the Sarfartoq carbonatite complex, southern West Greenland, using HyMap imaging spectrometer data. Remote Sensing of Environment 113, 1208–1219.
| Mapping lithology of the Sarfartoq carbonatite complex, southern West Greenland, using HyMap imaging spectrometer data.Crossref | GoogleScholarGoogle Scholar |
Bedini E (2012) Mapping alteration minerals at Malmbjerg molybdenum deposit, central East Greenland, by Kohonen Self-Organizing Maps and matched filter analysis of HyMap data. International Journal of Remote Sensing 33, 939–961.
| Mapping alteration minerals at Malmbjerg molybdenum deposit, central East Greenland, by Kohonen Self-Organizing Maps and matched filter analysis of HyMap data.Crossref | GoogleScholarGoogle Scholar |
Bierlein FP, Fraser SJ, Brown WM, Lees T (2008) Advanced methodologies for the analysis of databases of mineral deposits and major faults. Australian Journal of Earth Sciences 55, 79–99.
| Advanced methodologies for the analysis of databases of mineral deposits and major faults.Crossref | GoogleScholarGoogle Scholar |
Boudaillier E, Hebrail G (1998) Interactive interpretation of hierarchical clustering. Intelligent Data Analysis 2, 229–244.
| Interactive interpretation of hierarchical clustering.Crossref | GoogleScholarGoogle Scholar |
Carneiro CC, Fraser SJ, Croacutesta AP, Silva AM, Barros CEM (2012) Semiautomated geologic mapping using self-organizing maps and airborne geophysics in the Brazilian Amazon. Geophysics 77, K17–K24.
| Semiautomated geologic mapping using self-organizing maps and airborne geophysics in the Brazilian Amazon.Crossref | GoogleScholarGoogle Scholar |
Coram J (1998) ‘National classification of catchments for land and river salinity control: A catalogue of groundwater systems responsible for dryland salinity in Australia.’ Publication No. 98/78. (Rural Industries Research and Development Corporation: Canberra, ACT)
Coram JE, Dyson PR, Evans WR (2001) An evaluation framework for dryland salinity. A report prepared for the National Land and Water Resources Audit Dryland Salinity Project, Bureau of Rural Sciences, Canberra, ACT.
Cottrell M, Verleysen M (2006) Special Issue: Advances in Self-Organizing Maps-WSOM’05. Neural Networks 19, 721–722.
| Special Issue: Advances in Self-Organizing Maps-WSOM’05.Crossref | GoogleScholarGoogle Scholar |
Cowood AL, Moore CL, Nicholson A, Hazell D (2014) Wetland conservation in the face of climate change: Summary report. NSW Office of Environment and Heritage, Sydney.
Davies DL, Bouldin DW (1979) A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-1, 224–227.
| A cluster separation measure.Crossref | GoogleScholarGoogle Scholar |
Dowling T, Summerell GK, Walker J (2003) Soil wetness as an indicator of stream salinity: a landscape position index approach. Applying Computer Research to Environmental Problems 18, 587–593.
| Soil wetness as an indicator of stream salinity: a landscape position index approach.Crossref | GoogleScholarGoogle Scholar |
Dowling T, Dawes W, Evans R, Dyson P, Walker G (2004) Prioritising upland catchments in the Murray–Darling Basin with respect to salinity benefits from afforestation. CSIRO Land and Water Technical Report No. 15/04. CSIRO, Canberra.
Environmental Systems Research Institute (2008) ‘ArcGIS Desktop: Release 9.3.’ (Environmental Systems Research Institute: Redlands, CA, USA)
Environmental Systems Research Institute (2012) ‘ArcGIS Desktop: Release 10.1.’ (Environmental Systems Research Institute: Redlands, CA, USA)
Ferentinou MD, Sakellariou MG (2005) Assessing landslide hazard on medium and large scales, using SOM. In ‘Landslide risk management’. (Eds O Hungr, R Fell, R Couture, E Eberhardt) pp. 639–648. (Taylor & Francis Group: London)
Ferentinou MD, Sakellariou MG (2007) Computational intelligence tools for the prediction of slope performance. Computers and Geotechnics Special Issue on Biologically Inspired and Other Novel Computing Techniques in Geomechanics 34, 362–384.
| Computational intelligence tools for the prediction of slope performance. Computers and Geotechnics Crossref | GoogleScholarGoogle Scholar |
Ferentinou M, Karymbalis E, Charou E, Sakellariou M (2008) Using self organising maps in applied geomorphology. In ‘Self-organising maps: Applications in geographic information science’. (Eds A Skupin, P Agarwal) pp. 273–298. (Wiley: Chichester, UK)
Fraser SJ, Dickson BL (2007) A new method for data integration and integrated data interpretation: Self-organising maps. In ‘5th Decennial International Conference on Mineral Exploration’. Expanded Abstracts, pp. 907–910. (Decennial Mineral Exploration Conferences) Available at: www.dmec.ca/ex07-dvd/E07/pdfs/67.pdf
Gallant J, Austin J (2012) Topographic wetness index (3ʹ resolution) derived from 1ʹ SRTM DEM-H. v1. CSIRO Data Collection. Available at: https://data.csiro.au/dap/landingpage?pid=csiro%3A5588
Gallant JC, Dowling TI (2003) A multiresolution index of valley bottom flatness for mapping depositional areas. Water Resources Research 39, 1347
| A multiresolution index of valley bottom flatness for mapping depositional areas.Crossref | GoogleScholarGoogle Scholar |
Gellie NJH (2005) Native vegetation of the Southern Forests: South-east Highlands, Australian Alps, South-west Slopes, and SE Corner bioregions. Cunninghamia 9, 219–254.
Goodchild MF, Chih-Chang L, Leung Y (1994) Visualizing fuzzy maps. In ‘Visualization in GIS’. (Eds HM Hearnshaw, DJ Unwin) pp. 158–167. (Wiley: New York)
Isbell RF (1996) ‘The Australian Soil Classification.’ 1st edn (CSIRO Publishing: Melbourne)
Jenkins BR (1996) Soil landscapes of the Braidwood 1 : 100,000 sheet map and report. NSW Department of Land and Water Conservation, Sydney. Available at: www.environment.nsw.gov.au/soils/braidwood.htm
Jenkins BR, Nicholson A, Moore CL, Harvey K, Cook W, Wooldridge A, Shoemark V, Nowakowski A, Muller R, Winkler M (2010) Hydrogeological landscapes for the Southern Rivers Catchment Management Authority, Braidwood 1 : 100,000 map sheet. NSW Department of Environment, Climate Change and Water, Sydney.
Kalteh AM, Hjorth P, Berndtsson R (2008) Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application. Environmental Modelling & Software 23, 835–845.
| Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application.Crossref | GoogleScholarGoogle Scholar |
Keith DA, Simpson CC (2010) Vegetation formations of NSW (version 3.0): A seamless map for modelling fire spread and behaviour. Report to the Rural Fire Service. Version 2 data: NSWmap_v2_p1750_VIS_3846 & NSWmap_v2_ext_VIS_3847. NSW Department of Environment & Climate Change, Sydney.
Klose C (2006) Self-organizing maps for geoscientific data analysis: geological interpretation of multidimensional geophysical data. Computational Geosciences 10, 265–277.
| Self-organizing maps for geoscientific data analysis: geological interpretation of multidimensional geophysical data.Crossref | GoogleScholarGoogle Scholar |
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69.
| Self-organized formation of topologically correct feature maps.Crossref | GoogleScholarGoogle Scholar |
Kohonen T (2001) ‘Self-organizing maps.’ (Springer: Berlin)
Ley R, Casper MC, Hellebrand H, Merz R (2011) Catchment classification by runoff behaviour with self-organizing maps (SOM). Hydrology and Earth System Sciences 15, 2947–2962.
| Catchment classification by runoff behaviour with self-organizing maps (SOM).Crossref | GoogleScholarGoogle Scholar |
Lin G-F, Chen L-H (2006) Identification of homogeneous regions for regional frequency analysis using the self-organizing map. Journal of Hydrology 324, 1–9.
| Identification of homogeneous regions for regional frequency analysis using the self-organizing map.Crossref | GoogleScholarGoogle Scholar |
Mokarram M, Seif A, Sathyamoorthy D (2014) Use of morphometric analysis and self-organizing maps for alluvial fan classification: case study on Ostorankooh altitudes, Iran. In ‘IOP Conference Series: Earth and Environmental Science’. Kuala Lumpur. 012003. (IOP Publishing) Available at: http://iopscience.iop.org/1755-1315/20/1/012003
Muller R, Jenkins BR, Cook W, Littleboy M, Nicholson A, Moore CL, Wooldridge A, Winkler M (2012) Salinity Hazard for Catchment Action Plan (CAP) Updates, Murrumbidgee Catchment Management Authority Area. NSW Department of Primary Industries/NSW Office of Environment and Heritage, Department of Premier and Cabinet, Wagga Wagga, NSW.
Muller R, Nicholson A, Wooldridge A, Jenkins BR, Winkler M, Cook W, Grant S, Moore L (2015) Hydrogeological Landscapes for the Murray Catchment Management Authority: Eastern Murray Catchment. NSW Office of Environment and Heritage, Sydney. Available at: www.environment.nsw.gov.au/publications/salinity/150240-HGL-Eastern-Murray.htm
National Committee on Soil and Terrain (2009) ‘Australian soil and land survey field handbook.’ (CSIRO Publishing: Melbourne)
National Land and Water Resources Audit (2001) ‘Australian Dryland Salinity Assessment 2000. Extent, impacts, processes, monitoring and management options.’ (Land & Water Australia: Canberra, ACT)
National Resource Information Centre (1991) The Digital Atlas of Australian Soils – scanned tracings. ASRIS, CSIRO. Available at: www.asris.csiro.au/themes/Atlas.html
Nicholson A, Cook W, Nowakowski A, Littleboy M, Ji F, Wightley J (2011a) Dubbo Urban Landscape Interpretation Project Final Report. Dubbo City Council Central West Catchment Management Authority. NSW Department of Environment, Climate Change and Water, Sydney.
Nicholson A, Pavan N, Winkler M, Taylor L, Cull V, Copley S, Muller R, Jenkins BR, Cook W, Shoemark V, Nowakowski A, Marchand A, Moore CL (2011b) Hydrogeological Landscapes for the Sydney Metropolitan Catchment Management Authority, Western Study Area. NSW Department of Environment, Climate Change and Water, Sydney.
Nicholson A, Cowood A, Muller R, Wooldridge A, Cook W (2014) Impact of regional corridor plantings on water quality—South East Local Land Services. NSW Department of Primary Industries, Sydney.
Northcote KH, Beckmann GG, Bettenay E, Churchward HM, van Dijk DC, Dimmock GM, Hubble GD, Isbell RF, McArthur WM, Murtha GG, Nicolls KD, Paton TR, Thompson CH, Webb AA, Wright MJ (1960) ‘Atlas of Australian Soils, Sheets 1 to 10 with explanatory data.’ (CSIRO Australia and Melbourne University Press: Melbourne)
Office of Environment and Heritage (2009) BIOCLIM annual precipitation (digital dataset). Department of Premier and Cabinet, Canberra, ACT.
Office of Environment and Heritage (2011) DEM 30 m (digital dataset). Department of Premier and Cabinet, Canberra, ACT.
Office of Environment and Heritage (2013) Slope 30 m (degrees) (digital dataset). Department of Premier and Cabinet, Canberra, ACT.
Office of Environment and Heritage NSW (2011) Landuse. Department of Environment, Climate Change and Water, Sydney. Available at: www.agriculture.gov.au/abares/aclump/land-use/data-download
Peeters L, Lobo V, Dassargues A (2007) Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen’s Self-Organizing Map. Hydrology and Earth System Sciences 11, 1309–1321.
| Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen’s Self-Organizing Map.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD2sXht1ersbbI&md5=bf3485a8722f5f247b47a275120eca21CAS |
R Core Team (2015) ‘R: A Language and Environment for Statistical Computing.’ (R Foundation for Statistical Computing: Vienna, Austria) Available at: www.R-project.org/
Raymond OL, Retter AJ (2010) Surface geology of Australia 1 : 1,000,000 scale, 2010 edn (digital dataset). Geoscience Australia, Commonwealth of Australia, Canberra, ACT. Available at: www.ga.gov.au
Ripley BD (1996) ‘Pattern recognition and neural networks.’ (Cambridge University Press: Cambridge, UK)
Siponen M, Vesanto J, Simula O, Vasara P (2001) An approach to automated interpretation of SOM. In ‘Advances in self-organising maps’. (Eds N Allinson, H Yin, L Allinson, J Slack) pp. 89–94. (Springer: London)
Summerell GK, Dowling TI, Wild JA, Beale G (2004) FLAG UPNESS and its application for mapping seasonally wet to waterlogged soils. Soil Research 42, 155–162.
| FLAG UPNESS and its application for mapping seasonally wet to waterlogged soils.Crossref | GoogleScholarGoogle Scholar |
Summerell GK, Vaze J, Tuteja NK, Grayson RB, Beale G, Dowling TI (2005) Delineating the major landforms of catchments using an objective hydrological terrain analysis method. Water Resources Research 41, W12416
| Delineating the major landforms of catchments using an objective hydrological terrain analysis method.Crossref | GoogleScholarGoogle Scholar |
Tozer MG, Turner K, Keith DA, Tindall D, Pennay C, Simpson CC, MacKenzie B, Beukers P, Cox S (2010) Native vegetation of southeast NSW: a revised classification and map for the coast and eastern tablelands. Cunninghamia 11, 359–406.
Tulau MJ (1994) Soil landscapes of the Cooma 1 : 100,000 Sheet map and report. Department of Conservation and Land Management, Sydney. Available at: www.environment.nsw.gov.au/soils/cooma.htm
Vesanto J, Alhoniemi E (2000) Clustering of the self-organizing map. IEEE Transactions on Neural Networks 11, 586–600.
| Clustering of the self-organizing map.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BD1c%2FptFGgtA%3D%3D&md5=9f06224e2774454d15e5ed2be8b026b4CAS | 18249787PubMed |
Walker G, Gilfedder M, Evans R, Dyson P, Stuaffacher M (2003) Groundwater flow systems framework—essential tools for planning salinity management. Summary Report, Murray Darling Basin Commission. Land and Water Australia, Canberra, ACT. Available at: http://lwa.gov.au/products/pk030627
Ward JH (1963) Hierarchical grouping to optimize an objective function. Journal of the American Statistical Association 58, 236–244.
| Hierarchical grouping to optimize an objective function.Crossref | GoogleScholarGoogle Scholar |
Wehrens R, Buydens LMC (2007) Self- and super-organising maps in R: the kohonen package. Journal of Statistical Software 21, 1–19.
Wilford J (2012) A weathering intensity index for the Australian continent using airborne gamma-ray spectrometry and digital terrain analysis. Geoderma 183–184, 124–142.
| A weathering intensity index for the Australian continent using airborne gamma-ray spectrometry and digital terrain analysis.Crossref | GoogleScholarGoogle Scholar |
Winter TC (2001) The concept of hydrologic landscapes. Journal of the American Water Resources Association 37, 335–349.
| The concept of hydrologic landscapes.Crossref | GoogleScholarGoogle Scholar |
Wolock DM, Winter TC, McMahon G (2004) Delineation and evaluation of hydrologic-landscape regions in the United States using geographic information system tools and multivariate statistical analyses. Environmental Management 34, S71–S88.
| Delineation and evaluation of hydrologic-landscape regions in the United States using geographic information system tools and multivariate statistical analyses.Crossref | GoogleScholarGoogle Scholar | 16044554PubMed |
Wooldridge A, Nicholson A, Muller R, Jenkins BR, Wilford J, Winkler M (2015) Guidelines for managing salinity in rural areas. NSW Office of Environment and Heritage, Sydney. Available at: www.environment.nsw.gov.au/publications/salinity/150241-HGL-salinity-rural.htm
Xu T, Hutchinson M (2011) ‘ANUCLIM version 6.1 user guide.’ (Fenner School of Environment and Society, Australian National University: Canberra, ACT)
