Articles | Volume 12, issue 3
https://doi.org/10.5194/esurf-12-765-2024
https://doi.org/10.5194/esurf-12-765-2024
Research article
 | 
17 May 2024
Research article |  | 17 May 2024

Evaluating the accuracy of binary classifiers for geomorphic applications

Matthew William Rossi

Data sets

United States Geological Survey 2010 Channel Islands Lidar Collection https://doi.org/10.5069/G95D8PS7

Snow-on and snow-off Lidar point cloud data and digital elevation models for study of topography, snow, ecosystems and environmental change at Boulder Creek Critical Zone Observatory S. P. Anderson et al. https://doi.org/10.5069/G93R0QR0

Merced, CA: Origin and evolution of the Mima mounds, National Center for Airborne Laser Mapping S. Reed https://doi.org/10.5069/G93B5X3Q

Evaluating the accuracy of binary classifiers for geomorphic applications by Rossi (2024) - Accuracy assessment software and figure generation Matthew William Rossi https://doi.org/10.6084/m9.figshare.23796024.v1

Model code and software

Evaluating the accuracy of binary classifiers for geomorphic applications by Rossi (2024) - Accuracy assessment software and figure generation Matthew William Rossi https://doi.org/10.6084/m9.figshare.23796024.v1

Download
Short summary
Accurately identifying the presence and absence of landforms is important to inferring processes and testing numerical models of landscape evolution. Using synthetic scenarios, I show that the Matthews correlation coefficient (MCC) should be favored over the F1 score when comparing accuracy across scenes where landform abundances vary. Despite the resilience of MCC to imbalanced data, strong sensitivity to the size and shape of features can still occur when truth and model data are misaligned.