Register      Login
Soil Research Soil Research Society
Soil, land care and environmental research
RESEARCH ARTICLE

Knowledge-based soil type classification using terrain segmentation

Andrei Dornik A B , Lucian Drăguţ A and Petru Urdea A
+ Author Affiliations
- Author Affiliations

A Department of Geography, West University of Timişoara, Blvd. V. Pârvan 4, Timişoara 300223, Timiş, Romania.

B Corresponding author. Email: andrei.dornik@e-uvt.ro

Soil Research 54(7) 809-823 https://doi.org/10.1071/SR15210
Submitted: 31 July 2015  Accepted: 26 February 2016   Published: 5 September 2016

Abstract

Soil information covering regional, continental, or even global scales is needed for modelling, prediction, or estimation of environmental risks, crop yield estimation, carbon stock estimation, or research on climate change. This study aims to evaluate the extent to which geographic object-based image analysis and expert-knowledge, using digital maps of climate, topography, vegetation, and geology as soil covariates (GEOBIA approach), might model and reproduce a conventional soil map at a scale 1 : 1 000 000 in the south-west of Romania. The environmental variables were segmented with a region-growing algorithm, the resulting objects being subsequently classified into soil types using expert-knowledge fuzzy classification rules. To assess the geographical support of classification for the modelling of a conventional soil map, we quantitatively evaluated a pixel-based soil map produced using the same expert-knowledge classification rules, as an alternative to an object-based approach. To evaluate the source of soil information, we quantitatively assessed the map of the World Reference Base soil groups produced by the data-driven global soil information system, SoilGrids, as an alternative to expert-knowledge rules. The digital soil maps were quantitatively compared with the conventional soil map. Evidence was provided that the similarity of soil types with the conventional soil map was higher when the modelling was conducted through GEOBIA approach (general similarity of 65% and fuzzy kappa index of 0.58) than the pixel-based approach and SoilGrids. Furthermore, the results showed that the SoilGrids map achieved higher similarity to conventional soil map than the pixel-based soil map. When tested in another area, without modification to the knowledge-based methodologies, the same conclusions could be drawn, although the two maps recorded lower similarity values. The overall reduction in similarity values is explained by a high variability of some soil types under different environmental conditions.

Additional keywords: expert-knowledge, landscape stratification, object, Romania.


References

Adhikari K, Minasny B, Greve MB, Greve MH (2014) Constructing a soil class map of Denmark based on the FAO legend using digital techniques. Geoderma 214–215, 101–113.
Constructing a soil class map of Denmark based on the FAO legend using digital techniques.Crossref | GoogleScholarGoogle Scholar |

Ashtekar JM, Owens PR (2014) Remembering knowledge: an expert knowledge based approach to digital soil mapping. Soil Horizons 54, 1–6.
Remembering knowledge: an expert knowledge based approach to digital soil mapping.Crossref | GoogleScholarGoogle Scholar |

Baatz M, Schäpe A (2000) Multiresolution segmentation: an optimization approach for high quality multi-scale image segmentation. In ‘Angewandte geographische informationsverarbeitung’. (Eds J Strobl, T Blaschke, G Griesebner) pp. 12–23. (Wichmann-Verlag: Heidelberg)

Behrens T, Zhu AX, Schmidt K, Scholten T (2010) Multi-scale digital terrain analysis and feature selection for digital soil mapping. Geoderma 155, 175–185.
Multi-scale digital terrain analysis and feature selection for digital soil mapping.Crossref | GoogleScholarGoogle Scholar |

Blaschke T, Strobl J (2001) What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS. GIS–Zeitschrift für Geoinformationssysteme 14, 12–17.

Blaschke T, Hay GJ, Kelly M, Lang S, Hofmann P, Addink E, Feitosa RQ, van der Meer F, van der Werff H, van Coillie F, Tiede D (2014) Geographic object-based image analysis – towards a new paradigm. ISPRS Journal of Photogrammetry and Remote Sensing 87, 180–191.
Geographic object-based image analysis – towards a new paradigm.Crossref | GoogleScholarGoogle Scholar | 24623958PubMed |

Böhner J, Köthe R, Conrad O, Gross J, Ringeler A, Selige T (2002) Soil regionalisation by means of terrain analysis and process parameterisation. In ‘Soil classification’. (Eds E Micheli, F Nachtergaele, L Montanarella) pp. 213–222. Research Report No. 7, EUR 20398 EN. (European Soil Bureau: Luxembourg)

Brus D, Hengeveld G, Walvoort D, Goedhart P, Heidema A, Nabuurs G, Gunia K (2012) Statistical mapping of tree species over Europe. European Journal of Forest Research 131, 145–157.
Statistical mapping of tree species over Europe.Crossref | GoogleScholarGoogle Scholar |

Burt J, Zhu AX, Harrower M (2008) Depicting fuzzy soil class uncertainty using perception-based color models. In ‘Proceedings of the 11th World Congress of International Fuzzy Systems Association (IFSA2005): Fuzzy Logic, Soft Computing and Computational Intelligence’, 28–31 July 2005, Beijing, China. (Eds Y Liu, G Chen, M Ying) pp. 112–117. (Tsinghua University Press: Beijing China and Springer)

Dehni A, Lounis M (2012) Remote sensing techniques for salt affected soil mapping: application to the Oran region of Algeria. Procedia Engineering 33, 188–198.
Remote sensing techniques for salt affected soil mapping: application to the Oran region of Algeria.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC38XptFeis74%3D&md5=7e9212e3cfc58decf41e802e7ec7a2abCAS |

Drăguţ L, Blaschke T (2006) Automated classification of landform elements using object-based image analysis. Geomorphology 81, 330–344.
Automated classification of landform elements using object-based image analysis.Crossref | GoogleScholarGoogle Scholar |

Drăguţ L, Eisank C, Strasser T (2011) Local variance for multi-scale analysis in geomorphometry. Geomorphology 130, 162–172.
Local variance for multi-scale analysis in geomorphometry.Crossref | GoogleScholarGoogle Scholar | 21779138PubMed |

Drăguţ L, Schauppenlehner T, Muhar A, Strobl J, Blaschke T (2009) Optimization of scale and parametrization for terrain segmentation: An application to soil-landscape modeling. Computers & Geosciences 35, 1875–1883.
Optimization of scale and parametrization for terrain segmentation: An application to soil-landscape modeling.Crossref | GoogleScholarGoogle Scholar |

Drăguţ L, Tiede D, Levick SR (2010) ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. International Journal of Geographical Information Science 24, 859–871.
ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data.Crossref | GoogleScholarGoogle Scholar |

Florea N, Munteanu I (2012) ‘Sistemul român de taxonomie a solurilor (SRTS-2012).’ (Editura Sitech: Craiova)

Florea N, Conea A, Munteanu I (1971). Harta Solurilor României la sc. 1 : 500,000. Inst. Geol. Bucureşti.

Gallant JC, Wilson JP (2000) Primary topographic attributes. In ‘Terrain analysis: principles and applications’. (Eds JP Wilson, JC Gallant) pp. 51–86. (Wiley: New York, NY)

Gruber S, Peckham S (2009) Land-surface parameters and objects in hydrology. In ‘Geomorphometry: Concepts, Software, Applications’. (Eds T Hengl, HI Reuter) pp. 171–195. (Elsevier: Amsterdam)

Hagen-Zanker A, Straatman B, Uljee I (2005) Further developments of a fuzzy set map comparison approach. International Journal of Geographical Information Science 19, 769–785.
Further developments of a fuzzy set map comparison approach.Crossref | GoogleScholarGoogle Scholar |

Häring T, Schröder B (2010) Sampling optimization using image segmentation. In ‘4th International Workshop on Digital Soil Mapping’, 24–26 May 2010, Rome. (Agricultural Research Council, Research Centre for Soil-Plant System)

Hay GJ, Castilla G (2008) Geographic object-based image analysis (GEOBIA): a new name for a new discipline. In ‘Object based image analysis’. (Eds T Blaschke, S Lang, GJ Hay) pp. 93–112. (Springer: Heidelberg)

Hengl T, Toomanian N, Reuter HI, Malakouti MJ (2007) Methods to interpolate soil categorical variables from profile observations: Lessons from Iran. Geoderma 140, 417–427.
Methods to interpolate soil categorical variables from profile observations: Lessons from Iran.Crossref | GoogleScholarGoogle Scholar |

Hengl T, de Jesus JM, MacMillan RA, Batjes NH, Heuvelink GB, Ribeiro E, Samuel-Rosa A, Kempen B, Leenaars JG, Walsh MG (2014) SoilGrids1km—global soil information based on automated mapping. PLoS One 9, e105992
SoilGrids1km—global soil information based on automated mapping.Crossref | GoogleScholarGoogle Scholar | 25171179PubMed |

Hudson BD (1992) The soil survey as paradigm-based science. Soil Science Society of America Journal 56, 836–841.
The soil survey as paradigm-based science.Crossref | GoogleScholarGoogle Scholar |

Ianoş G, Puşcă I, Goian M (1997) ‘Solurile Banatului: condiţii naturale şi fertilitate’ (Mirton: Timişoara). [In Romanian]

Ianoş G, Puşcă I (1998) ‘Solurile Banatului: Prezentare cartografică a solurilor agricole’ (Mirton: Timișoara). [In Romanian]

IUSS Working Group WRB 2006. World reference base for soil resources 2006. World Soil Resources Reports No. 103. FAO, Rome.

Jenny H (1941) ‘Factors of soil formation’ (McGraw-Hill: New York, NY)

Kringer K, Tusch M, Geitner C, Rutzinger M, Wiegand C, Meißl G (2009) Geomorphometric analyses of LiDAR digital terrain models as input for digital soil mapping. In ‘Proceedings of Geomorphometry 2009’, 31 August–2 September 2009, Zurich, Switzerland. (Eds R Purves, S Gruber, R Straumann, T Hengl) pp. 74–81. (University of Zurich: Zurich)

Lagacherie P, Legros J, Burfough P (1995) A soil survey procedure using the knowledge of soil pattern established on a previously mapped reference area. Geoderma 65, 283–301.
A soil survey procedure using the knowledge of soil pattern established on a previously mapped reference area.Crossref | GoogleScholarGoogle Scholar |

MacMillan RA (2008) Experiences with applied DSM: protocol, availability, quality and capacity building. In ‘Digital soil mapping with limited data’. (Eds AE Hartemink, A Mcbratney, ML Mendonca-Santos) pp. 113–135. (Springer: Rio de Janeiro, Brazil)

MacMillan RA, Pettapiece WW, Nolan SC, Goddard TW (2000) A generic procedure for automatically segmenting landforms into landform elements using DEMs, heuristic rules and fuzzy logic. Fuzzy Sets and Systems 113, 81–109.
A generic procedure for automatically segmenting landforms into landform elements using DEMs, heuristic rules and fuzzy logic.Crossref | GoogleScholarGoogle Scholar |

McKay J, Grunwald S, Shi X, Long R (2010) Evaluation of the transferability of a knowledge-based soil-landscape model. In ‘Digital soil mapping bridging research, environmental application, and operation’. (Eds AK Stum, JL Boettinger, MA White, RD Ramsey) pp. 165–178. (Springer: London)

McKenzie NJ, Ryan PJ (1999) Spatial prediction of soil properties using environmental correlation. Geoderma 89, 67–94.
Spatial prediction of soil properties using environmental correlation.Crossref | GoogleScholarGoogle Scholar |

Miller BA (2014) Semantic calibration of digital terrain analysis scale. Cartography and Geographic Information Science 41, 166–176.
Semantic calibration of digital terrain analysis scale.Crossref | GoogleScholarGoogle Scholar |

Möller M, Volk M, Friedrich K, Lymburner L (2008) Placing soil-genesis and transport processes into a landscape context: A multiscale terrain-analysis approach. Journal of Plant Nutrition and Soil Science 171, 419–430.
Placing soil-genesis and transport processes into a landscape context: A multiscale terrain-analysis approach.Crossref | GoogleScholarGoogle Scholar |

Möller M, Koschitzki T, Hartmann KJ 2009. Terrain-related Revision of Existing Soil Maps. In ‘Proceedings of Geomorphometry 2009’, 31 August–2 September 2009, Zurich, Switzerland. (Eds R Purves, S Gruber, R Straumann, T Hengl) pp. 82–89. (University of Zurich: Zurich)

Möller M, Koschitzki T, Hartmann KJ, Jahn R (2012) Plausibility test of conceptual soil maps using relief parameters. Catena 88, 57–67.
Plausibility test of conceptual soil maps using relief parameters.Crossref | GoogleScholarGoogle Scholar |

Puşcă I (2002) ‘Câmpia Banatului.’ (Fundaţia Naţională “Satul românesc”: Bucureşti). [In Romanian]

Qi F, Zhu AX (2003) Knowledge discovery from soil maps using inductive learning. International Journal of Geographical Information Science 17, 771–795.
Knowledge discovery from soil maps using inductive learning.Crossref | GoogleScholarGoogle Scholar |

Qi F, Zhu AX, Harrower M, Burt JE (2006) Fuzzy soil mapping based on prototype category theory. Geoderma 136, 774–787.
Fuzzy soil mapping based on prototype category theory.Crossref | GoogleScholarGoogle Scholar |

R Core Team (2015) R: A language and environment for statistical computing. (R Foundation for Statistical Computing: Vienna). Available at http://www.R-project.org/.

Riley SJ, DeGloria SD, Elliot R (1999) A terrain ruggedness index that quantifies topographic heterogeneity. Intermountain Journal of Sciences 5, 23–27.

Roecker S, Thompson J (2010) Scale effects on terrain attribute calculation and their use as environmental covariates for digital soil mapping. In ‘Digital soil mapping bridging research, environmental application, and operation’. (Eds AK Stum, JL Boettinger, MA White, RD Ramsey) pp. 55–66. (Springer: London)

Rossiter DG (2004) Digital soil resource inventories: status and prospects. Soil Use and Management 20, 296–301.
Digital soil resource inventories: status and prospects.Crossref | GoogleScholarGoogle Scholar |

Rouse J, Haas R, Schell J, Deering D (1974) Monitoring vegetation systems in the Great Plains with ERTS. NASA Special Publication 351, 309

Shi X, Long R, Dekett R, Philippe J (2009) Integrating different types of knowledge for digital soil mapping. Soil Science Society of America Journal 73, 1682–1692.
Integrating different types of knowledge for digital soil mapping.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD1MXhtFSqu7rF&md5=c46dfb2a5eaac58914a9d7ac3925beedCAS |

Skidmore AK, Watford F, Luckananurug P, Ryan P (1996) An operational GIS expert system for mapping forest soils. Photogrammetric Engineering and Remote Sensing 62, 501–511.

Soil Survey Staff (1993) ‘Soil survey manual.’ (U.S. Department of Agriculture Handbook No. 18, U.S. Government Printing Office: Washington, DC)

Trimble (2013) ‘eCognition Developer 8.9 User Guide.’ (Trimble: Munchen, Germany)

van Niekerk A (2010) A comparison of land unit delineation techniques for land evaluation in the Western Cape, South Africa. Land Use Policy 27, 937–945.
A comparison of land unit delineation techniques for land evaluation in the Western Cape, South Africa.Crossref | GoogleScholarGoogle Scholar |

van Zijl G, Bouwer D, van Tol J, le Roux P (2014) Functional digital soil mapping: A case study from Namarroi, Mozambique. Geoderma 219–220, 155–161.
Functional digital soil mapping: A case study from Namarroi, Mozambique.Crossref | GoogleScholarGoogle Scholar |

Visser H, De Nijs T (2006) The map comparison kit. Environmental Modelling & Software 21, 346–358.
The map comparison kit.Crossref | GoogleScholarGoogle Scholar |

Wilson JP, Gallant JC (2000) Secondary topographic attributes. In ‘Terrain analysis—principles and applications’. (Eds JP Wilson, JC Gallant) pp. 87–132. (Wiley: New York, NY)

Wilson P, Gregory L, Herklots A, Starkey A (2014) Mapping soil digitally with object based image analysis to improve soil map inputs to Digital Soil Mapping. In ‘GlobalSoilMap: basis of the global spatial soil information system’. (Eds D Arrouays, N Mckenzie, J Hempel, AC Richer De Forges, A Mcbratney) pp. 301–306. (CRC Press: London)

Zhan Q, Molenaar M, Tempfli K, Shi W (2005) Quality assessment for geo‐spatial objects derived from remotely sensed data. International Journal of Remote Sensing 26, 2953–2974.
Quality assessment for geo‐spatial objects derived from remotely sensed data.Crossref | GoogleScholarGoogle Scholar |

Zhu AX (1997) A similarity model for representing soil spatial information. Geoderma 77, 217–242.
A similarity model for representing soil spatial information.Crossref | GoogleScholarGoogle Scholar |

Zhu AX, Band LE (1994) A knowledge-based approach to data integration for soil mapping. Canadian Journal of Remote Sensing 20, 408–418.
A knowledge-based approach to data integration for soil mapping.Crossref | GoogleScholarGoogle Scholar |

Zhu AX, Band L, Dutton B, Nimlos T (1996) Automated soil inference under fuzzy logic. Ecological Modelling 90, 123–145.
Automated soil inference under fuzzy logic.Crossref | GoogleScholarGoogle Scholar |

Zhu AX, Hudson B, Burt J, Lubich K, Simonson D (2001) Soil mapping using GIS, expert knowledge, and fuzzy logic. Soil Science Society of America Journal 65, 1463–1472.
Soil mapping using GIS, expert knowledge, and fuzzy logic.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD38XptlWn&md5=a1a3447df086b171bbb8b1230c92be32CAS |