Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance

By Elizabeth A. Freeman, Gretchen G. Moisen, John W. Coulston, B. Wilson. 2016

203 citations recorded by the source corpus.

As part of the development of the 2011 National Land Cover Database (NLCD) tree canopy cover layer, a pilot project was launched to test the use of high-resolution photography coupled with extensive ancillary data to map the distribution of tree canopy cover over four study regions in the conterminous US. Two stochastic modeling techniques, random forests (RF) and stochastic gradient boosting (SGB), are compared. The objectives of this study were first to explore the sensitivity of RF and SGB to choices in tuning parameters and, second, to compare the performance of the two final models by assessing the importance of, and interaction between, predictor variables, the global accuracy metrics derived from an independent test set, as well as the visual quality of the resultant maps of tree canopy cover. The predictive accuracy of RF and SGB was remarkably similar on all four of our pilot regions. In all four study regions, the independent test set mean squared error (MSE) was identical to three decimal place...

Subfields: Ecology, Environmental Engineering, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/0c88ee721a210a49141c2ef278112205b1de8425

How researchers see this paper

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

In Global and Planetary Change

1. Ralf Wieland
2. Claas Nendel
3. Tobia Lakes

Citations in the corpus

• A new generation of the United States National Land Cover Database: Requirements, research priorities, design, and implementation strategies (2018, methodology): “Random forests regression was used as the modeling framework and has been found to produce better results than other methods tested (Freeman et al., 2016).”
• Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China (2021, methodology): “SHAP values show the extent to which a given feature has changed the prediction and allows the model builder to decompose any prediction into the sum of the effects of each feature value and explain – in our case – the predicted NGD probability for each pixel (see Fig.”