A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
In this paper we present ControlBurn, a feature selection algorithm that uses a weighted LASSO-based feature selection method to prune unnecessary features from tree ensembles, just as low-intensity fire ... We show that ControlBurn performs substantially better than feature selection methods with comparable computational costs on datasets with correlated features. ... We fit a random forest classifier on the features selected by ControlBurn and the features selected by our random forest baseline and compare the difference in test performance. ...doi:10.1145/3447548.3467387 arXiv:2107.00219v1 fatcat:7p6wcawdunb37ko7dlfbdgdgpq
ControlBurn is a Python package to construct feature-sparse tree ensembles that support nonlinear feature selection and interpretable machine learning. ... The package includes visualizations to analyze the features selected by the ensemble and their impact on predictions. ... As a result, ControlBurn will select either all or none of the features; there is no feature-sparse subforest (except the empty forest). ...arXiv:2207.03935v1 fatcat:47rjod4m7zdvnmeemgujcphwqi
Blocks of approximately one square mile in size were selected for sampling based upon their history of forest fires. ... in or under the ground litter when this fire occurred might have escaped being killedo Pre-burn samples were taken during 1951 in four plots in Austin Cary Forest a few days before a tract was controlburned ...doi:10.13016/m2md1r fatcat:4y3rujoe7jb7voljccujcmza4e