About this document

How Performance Metric Choice Influences Individual Tree Mortality Model Selection by rodri.pg1993 is a document available to read on EtoBox.

This study investigates how the choice of performance metrics affects the selection of individual tree mortality models, highlighting the importance of appropriate evaluation standards in forestry applications. It compares seven metrics, finding that metrics like the area under the precision-recall curve (AUCPR) and Cohen’s Kappa coefficient (K) provide more reliable assessments for imbalanced datasets than traditional metrics like accuracy and AUC. The findings emphasize that model performance can vary sig

Author

rodri.pg1993

Language

EN