On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping

By Koreen Millard, Murray Richardson. Remote Sensing, 2015

556 citations recorded by the source corpus.

Random Forest (RF) is a widely used algorithm for classification of remotely sensed data. Through a case study in peatland classification using LiDAR derivatives, we present an analysis of the effects of input data characteristics on RF classifications (including RF out-of-bag error, independent classification accuracy and class proportion error). Training data selection and specific input variables (i.e., image channels) have a large impact on the overall accuracy of the image classification. High-dimension datasets should be reduced so that only uncorrelated important variables are used in classifications. Despite the fact that RF is an ensemble approach, independent error assessments should be used to evaluate RF results, and iterative classifications are recommended to assess the stability of predicted classes. Results are also shown to be highly sensitive to the size of the training data set. In addition to being as large as possible, the training data sets used in RF classification should also be (a) randomly distributed or created in a manner that allows for the class proportions of the training data to be representative of actual class proportions in the landscape; and (b) should have minimal spatial autocorrelation to improve classification results and to mitigate inflated estimates of RF out-of-bag classification accuracy.

Subfields: Ecology, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/c995ada07a0a2c90727a9d756e9976c2e7056e35

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

Citations in the corpus

Land cover 2.0 (2018, background): “…(e.g. Janssen et al. 1994; Foody 2002, Stehman 2009; Stehman 2013) with increased emphasis on calibration data needs relative to speci ﬁ c data inputs (i.e. time series, Pelletier et al. 2017) and classi ﬁ cation approaches (e.g. Millard and Richardson 2015; Mellor et al. 2015; Scott et al. 2017).”
Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis (2018, methodology): “Previous studies have also reported that RF achieves less accurate re-sults when a small number of training samples is used (Millard and Richardson, 2015; Valero et al., 2016).”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, background): “The large volume of RS data [14], the complexity of the landscapeinastudyarea[21]–[23],aswellaslimitedandusually imbalancedtrainingdata[24],[25],maketheclassiﬁcationa challengingtask.”