Classification of Firn Data via Topological Features
This work addresses the incremental challenge of improving classification for glaciology researchers by applying topological data analysis to firn microCT images.
The paper tackled the problem of classifying firn image data by depth using topological features, finding that no single method dominated across all scenarios and revealing trade-offs between accuracy, interpretability, and generalizability.
In this paper we evaluate the performance of topological features for generalizable and robust classification of firn image data, with the broader goal of understanding the advantages, pitfalls, and trade-offs in topological featurization. Firn refers to layers of granular snow within glaciers that haven't been compressed into ice. This compactification process imposes distinct topological and geometric structure on firn that varies with depth within the firn column, making topological data analysis (TDA) a natural choice for understanding the connection between depth and structure. We use two classes of topological features, sublevel set features and distance transform features, together with persistence curves, to predict sample depth from microCT images. A range of challenging training-test scenarios reveals that no one choice of method dominates in all categories, and uncoveres a web of trade-offs between accuracy, interpretability, and generalizability.