maipo: Fruit-tree crop classification: the Maipo dataset

In sperrorest: Perform Spatial Error Estimation and Variable Importance Assessment

Fruit-tree crop classification: the Maipo dataset

Description

This dataset is from a case study on fruit-tree crop classification using a satellite image time series. The dataset should be cited as Pena & Brenning (2015), reference below. There are 7713 grid cells from 400 fields in this dataset, which makes it necessary to apply spatial cross-validation at the field level for model assessment (see partition_factor_cv()).

Format

a data.frame with point samples (grid cells) of crop type and Landsat-derived remote sensing features (spectral bands and vegetation indices). In addition, UTM x/y coordinates and a factor variable indicating which field a grid cell belongs to. Spectral bands are coded as bij where i represents the image date (early to late season, dates see paper), and j is the band number.

References

Pena, M.A., Brenning, A. (2015). Assessing fruit-tree crop classification from Landsat-8 time series for the Maipo Valley, Chile. Remote Sensing of Environment, 171: 234-244.

sperrorest documentation built on Oct. 16, 2022, 5:05 p.m.