![Hier klicken, um den Treffer aus der Auswahl zu entfernen](images/unchecked.gif) |
Titel |
Using random forests to explore the effects of site attributes and soil properties on near-saturated and saturated hydraulic conductivity |
VerfasserIn |
Helena Jorda, John Koestel, Nicholas Jarvis |
Konferenz |
EGU General Assembly 2014
|
Medientyp |
Artikel
|
Sprache |
Englisch
|
Digitales Dokument |
PDF |
Erschienen |
In: GRA - Volume 16 (2014) |
Datensatznummer |
250095326
|
Publikation (Nr.) |
EGU/EGU2014-10774.pdf |
|
|
|
Zusammenfassung |
Knowledge of the near-saturated and saturated hydraulic conductivity of soil is fundamental
for understanding important processes like groundwater contamination risks or runoff and
soil erosion. Hydraulic conductivities are however difficult and time-consuming to determine
by direct measurements, especially at the field scale or larger. So far, pedotransfer functions
do not offer an especially reliable alternative since published approaches exhibit poor
prediction performances. In our study we aimed at building pedotransfer functions by
growing random forests (a statistical learning approach) on 486 datasets from the
meta-database on tension-disk infiltrometer measurements collected from peer-reviewed
literature and recently presented by Jarvis et al. (2013, Influence of soil, land use and
climatic factors on the hydraulic conductivity of soil. Hydrol. Earth Syst. Sci. 17(12),
5185-5195).
When some data from a specific source publication were allowed to enter the training set
whereas others were used for validation, the results of a 10-fold cross-validation showed
reasonable coefficients of determination of 0.53 for hydraulic conductivity at 10 cm tension,
K10, and 0.41 for saturated conductivity, Ks. The estimated average annual temperature and
precipitation at the site were the most important predictors for K10, while bulk density and
estimated average annual temperature were most important for Ks prediction. The soil
organic carbon content and the diameter of the disk infiltrometer were also important for the
prediction of both K10 and Ks.
However, coefficients of determination were around zero when all datasets of a specific
source publication were excluded from the training set and exclusively used for validation.
This may indicate experimenter bias, or that better predictors have to be found or that a larger
dataset has to be used to infer meaningful pedotransfer functions for saturated and
near-saturated hydraulic conductivities. More research is in progress to further elucidate this
question. |
|
|
|
|
|