dsmartr-package: dsmartr: An R implementation of the DSMART algorithm

In obrl-soil/dsmartr: dsmartr: An R implementation of the DSMART algorithm

dsmartr: An R implementation of the DSMART algorithm

Description

dsmartr is an approach to the DSMART model (Odgers, 2014), which attempts increase the level of detail in legacy soil maps. Relationships between these maps and various environmental datasets are used to build a classification tree model. The model is used to map the map components as a fine-scaled raster. This process is repeated multiple times, with variation introduced around sample location and soil class proportions to vary the outputs somewhat. The model realisations are then processed to give a 'most likely' soils map. Refer to the package vignette for more detail.

Author(s)

Maintainer: Lauren O'Brien [e-mail]

Other contributors:

• Nathan Odgers [e-mail] [contributor]

• Brendan Malone [e-mail] [contributor]

References

Odgers, N.P., Sun, W., McBratney, A.B., Minasny, B., Clifford, D., (2014) Disaggregating and harmonising soil map units through resampled classification trees. Geoderma, 214-215: 91-100.

See Also

Useful links:

• https://github.com/obrl-soil/dsmartr

• Report bugs at https://github.com/obrl-soil/dsmartr/issues

obrl-soil/dsmartr documentation built on Feb. 1, 2024, 10:57 p.m.