Ließ, M.; Schmidt, J. & Glaser, B. (2016): <b>Improving the spatial prediction of soil organic carbon stocks in a complex tropical mountain landscape by methodological specifications in machine learning approaches</b>. <i>PLOS ONE</i> <b>11</b>(4), 1-22.
Resource Description
Title:
Improving the spatial prediction of soil organic carbon stocks in a complex tropical mountain landscape by methodological specifications in machine learning approaches
FOR816dw ID:
1465
Publication Date:
2016-04-29
License and Usage Rights:
Ließ, M., Schmidt, J., Glaser, B. (2016). Improving the spatial prediction of soil organic carbon stocks in a complex tropical mountain landscape by methodological specifications in machine learning approaches. PLOS ONE,11(4):e0153673. doi:10.1371/journal.pone.0153673
Resource Owner(s):
Individual:
Mareike Ließ
Contact:
email:
mareike.liess <at> ufz.de
Helmholtz Centre for Environmental Research - UFZ
Department of Soil Physics
D-06120 Halle (Saale), Theodor-Lieser-Str. 4
Germany
Tropical forests are significant carbon sinks and their soils’ carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of Tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks,<br/>
multivariate adaptive regression splines, boosted regression trees and support<br/>
vector machines were trained and tuned to predict SOC stocks from predictors derived<br/>
from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms—including the model tuning and predictor selection—were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models’ predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours Forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction.
Keywords:
| soil organic carbon | digital soil mapping |
Literature type specific fields:
ARTICLE
Journal:
PLOS ONE
Volume:
11
Issue:
4
Page Range:
1-22
Metadata Provider:
Individual:
Mareike Ließ
Contact:
email:
mareike.liess <at> ufz.de
Helmholtz Centre for Environmental Research - UFZ
Department of Soil Physics
D-06120 Halle (Saale), Theodor-Lieser-Str. 4
Germany
