Improved Soil Mapping in British Columbia, Canada, with Legacy Soil Data and Random Forest
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
- PDF / 927,708 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 80 Downloads / 225 Views
Improved Soil Mapping in British Columbia, Canada, with Legacy Soil Data and Random Forest C. Bulmer, M.G. Schmidt, B. Heung, C. Scarpone, J. Zhang, D. Filatow, M. Finvers, S. Berch and S. Smith 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
C. Bulmer (&) BC Ministry of Forests Lands and Natural Resource Operations, 3401 Reservoir Road, Vernon, BC, CanadaV1B2C7 e-mail: [email protected] M.G. Schmidt B. Heung C. Scarpone J. Zhang Department of Geography, Simon Fraser University, Burnaby, BC, Canada M. Finvers S. Berch BC Ministry of Environment, Victoria, BC, Canada S. Smith Agriculture and Agri-Food Canada, Summerland, BC, Canada D. Filatow BC Ministry of Environment, Kelowna, BC, Canada © Springer Science+Business Media Singapore 2016 G.-L. Zhang et al. (eds.), Digital Soil Mapping Across Paradigms, Scales and Boundaries, Springer Environmental Science and Engineering, DOI 10.1007/978-981-10-0415-5_24
291
292
C. Bulmer et al.
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.
Keywords Random forest Soil parent materials Soil development Legacy soil data List of Abbreviations BC BEC DEM MDA MDG OOB RF
British Columbia biogeoclimatic ecosystem classification digital elevation model mean decrease accuracy mean decrease in gini out-of-bag error random forest
24.1
Introduction
There is a need for improved soil survey information in the Canadian province of British Columbia (BC). Existing soil databases were derived from soil surveys that were carried out at various levels of detail over a period of more than 75 years, but
Data Loading...
