Abstract
The need for improved soil inventory information in the province of British Columbia (BC), Canada, was addressed using a random forest (RF) classifier that was informed using legacy soil data. RF models were prepared for 110 ecodistrict subdivisions of BC, and predictions were subsequently assembled into a final soil parent material map mosaic covering the entire province. The ecodistricts are part of a framework for ecosystem classification in BC and in Canada, and delineate areas with relatively homogeneous biophysical and climatic conditions. Training areas for predicting soil parent materials were identified using single-component polygons from legacy terrain, soil, and ecosystem maps. For parent material mapping, we intersected training points amalgamated from all legacy surveys with a suite of 18 topographic covariates derived from a 100-m digital elevation model (DEM). For each ecodistrict, two versions of the resulting training dataset were submitted to the RF classifier. A ‘balanced’ dataset contained equal numbers of training data points for all parent material classes representing all legacy data derived from single-component polygons. A ‘constrained’ dataset was also derived where conditions were imposed on selected topographic attributes of the training points to reflect known geomorphic processes and to ensure consistent mapping criteria were applied across multiple legacy soil survey projects. RF predictions of soil parent material resulted in 100-m gridded class maps for BC that incorporate expert knowledge extracted from legacy soil inventories.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- BC:
-
British Columbia
- BEC:
-
biogeoclimatic ecosystem classification
- DEM:
-
digital elevation model
- MDA:
-
mean decrease accuracy
- MDG:
-
mean decrease in gini
- OOB:
-
out-of-bag error
- RF:
-
random forest
References
Anderson DW, and Smith CAS (2011) A history of soil classification and soil survey in Canada: Personal perspectives. Can. J. Soil Sci.:91:675-694.
Bui EN, and Moran CJ (2003) A strategy to fill gaps in soil survey over large spatial extents: an example from the Murray–Darling basin of Australia. Geoderma 111:21–44.
Church M, and Ryder J (2010) Physiography of British Columbia. In RG Pike et al 2010. A compendium of forest hydrology. Land Management Handbook 66. BC Min. Forests. Available on the internet at www.for.gov.bc.ca/hfd/pubs/Docs/Lmh/Lmh66.htm (viewed 2014.09).
Ecological Stratification Working Group (1996). A National Ecological Framework for Canada. Agriculture and Agri-Food Canada, Research Branch and Environment Canada, State of Environment Directorate. Ottawa 125p.
Häring T, Dietz E, Osenstetter S, Koschitski T, and Schroeder B (2012) Spatial disaggregation of complex soil map units: A decision-tree based approach in Bavarian forest soils. Geoderma 185-186:37-47.
Heung B, Bulmer CE, and Schmidt MG (2014) Predictive soil parent material mapping at a regional-scale: A Random Forest approach. Geoderma 214-215:141-154.
Hengl T, de Jesus JM, MacMillan RA, Batjes NH, Heuvelink GBM, et al. (2014) SoilGrids1 km — Global soil information based on automated mapping. PLoS ONE 9(8): e105992. doi:10.1371/journal.pone.0105992.
Kelley CC, and Spilsbury RH (1939) Soil survey of the lower Fraser Valley. Technical Bulletin 20. Canada Department of Agriculture, Ottawa. Available on the internet at www.sis.agr.gc.ca/cansis/publications/surveys/bc/bc1/index.html (viewed 2014.09).
Luttmerding HA, (1980) Soils of the Langley-Vancouver map area. Report No. 15. British Columbia Soil Survey. Victoria. Available on the internet at www.sis.agr.gc.ca/cansis/publications/surveys/bc/bc15/index.html (viewed 2014.09).
MacMillan RA, Moon DE, and Coupé RA (2007) Automated predictive ecological mapping in a Forest Region of B.C., Canada, 2001–2005. Geoderma 140:353-373.
Meidinger DV and Pojar J (1991) Ecosystems of British Columbia. BC Ministry of Forests, Special Report No. 6. Victoria. Available on the internet at www.for.gov.bc.ca/hfd/pubs/Docs/Srs/Srs06.htm (viewed 2014.09).
Province of BC (2010) Field Manual for Describing Ecosystems in the Field. Land management handbook No. 25 - 2nd edition. BC Ministry of Forests and Range, Victoria. Available on the internet at www.for.gov.bc.ca/hfd/pubs/docs/Lmh/Lmh25-2.htm (viewed 2014.09).
Sarmento EC, Giasson E, Weber E, Flores CA, and Hasenack H (2012) Prediction of soil orders with high spatial resolution: response of different classifiers to sampling density. Pesquisa Agropecuária Brasileira 47(9): 1395-1403. Available on the internet at www.scielo.br/scielo.php?pid=S0100-204X2012000900025&script=sci_arttext (viewed 2014.09).
Schut P, Smith S, Fraser W, Geng X, and Kroetsch D (2011) Soil Landscapes of Canada: Building a National Framework for Environmental Information. Geomatica 65(3):293-309.
Smith CAS, Daneshfar B, Frank G, Flager E, and Bulmer C (2012) Use of weights of evidence statistics to define inference rules to disaggregate soil survey maps. p 215-220 In Digital Soil Assessments and Beyond – Minasny, Malone & McBratney (eds) CRC Press, Leiden, The Netherlands. 466 pp.
Sondheim M, and Suttie K (1983) User Manual for the British Columbia Soil Information System, 1. BC Ministry of Forests Publication R28-82053, Victoria, BC.
Sprout PN, and Kelley CC (1964) Soil survey of the Kettle River Valley. Report No. 9. British Columbia Soil Survey, Victoria. Available on the internet at www.sis.agr.gc.ca/cansis/publications/surveys/bc/bc9/index.html (viewed 2014.09).
Stum AK, Boettinger JL, White MA, and Ramsey RD (2010) Random forests applied as a soil predictive model in Utah. In Digital Soil Mapping: Bridging Research, Environmental Application, and Operations. Progress in Soil Science 2, Springer.
Subberayalu SK, and Slater BK (2013) Soil series mapping by knowledge discovery from an Ohio County soil map. Soil Sci. Soc. Am. J. 77:1254-1268.
Valentine KWG, Sprout PN, Baker TE, and Lavkulich LM (1978) The Soil Landscapes of British Columbia. BC Ministry of Environment, Victoria. Available on the internet at www.env.gov.bc.ca/soils/landscape/index.html (viewed 2014.09).
Acknowledgements
This study is supported by British Columbia’s Forest Science Program, and research programs within BC Ministry of Forests Lands and Natural Resource Operations, BC Ministry of Environment, and Agriculture and Agri-Food Canada. Simon Fraser University provided ongoing support for graduate students working on this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this chapter
Cite this chapter
Bulmer, C. et al. (2016). Improved Soil Mapping in British Columbia, Canada, with Legacy Soil Data and Random Forest. In: Zhang, GL., Brus, D., Liu, F., Song, XD., Lagacherie, P. (eds) Digital Soil Mapping Across Paradigms, Scales and Boundaries. Springer Environmental Science and Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-10-0415-5_24
Download citation
DOI: https://doi.org/10.1007/978-981-10-0415-5_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0414-8
Online ISBN: 978-981-10-0415-5
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)