 |
| Titel |
The R package "sperrorest" : Parallelized spatial error estimation and variable importance assessment for geospatial machine learning |
| VerfasserIn |
Patrick Schratz, Tobias Herrmann, Alexander Brenning |
| Konferenz |
EGU General Assembly 2017
|
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| Digitales Dokument |
PDF |
| Erschienen |
In: GRA - Volume 19 (2017) |
| Datensatznummer |
250139934
|
| Publikation (Nr.) |
 EGU/EGU2017-3256.pdf |
|
|
|
|
|
| Zusammenfassung |
| Computational and statistical prediction methods such as the support vector machine have
gained popularity in remote-sensing applications in recent years and are often compared to
more traditional approaches like maximum-likelihood classification.
However, the accuracy assessment of such predictive models in a spatial context needs to
account for the presence of spatial autocorrelation in geospatial data by using spatial
cross-validation and bootstrap strategies instead of their now more widely used non-spatial
equivalent. The R package sperrorest by A. Brenning [IEEE International Geoscience and
Remote Sensing Symposium, 1, 374 (2012)] provides a generic interface for performing
(spatial) cross-validation of any statistical or machine-learning technique available in
R.
Since spatial statistical models as well as flexible machine-learning algorithms can be
computationally expensive, parallel computing strategies are required to perform
cross-validation efficiently. The most recent major release of sperrorest therefore comes
with two new features (aside from improved documentation): The first one is the
parallelized version of sperrorest(), parsperrorest(). This function features two parallel
modes to greatly speed up cross-validation runs. Both parallel modes are platform
independent and provide progress information. par.mode = 1 relies on the pbapply
package and calls interactively (depending on the platform) parallel::mclapply() or
parallel::parApply() in the background. While forking is used on Unix-Systems,
Windows systems use a cluster approach for parallel execution. par.mode = 2 uses the
foreach package to perform parallelization. This method uses a different way of
cluster parallelization than the parallel package does. In summary, the robustness of
parsperrorest() is increased with the implementation of two independent parallel
modes.
A new way of partitioning the data in sperrorest is provided by partition.factor.cv(). This
function gives the user the possibility to perform cross-validation at the level of some
grouping structure. As an example, in remote sensing of agricultural land uses, pixels from
the same field contain nearly identical information and will thus be jointly placed in either the
test set or the training set. Other spatial sampling resampling strategies are already available
and can be extended by the user. |
|
|
|
|
|
|