Topo2vec: Topography Embedding Using the Fractal Effect

TL;DR

This paper introduces Topo2vec, a self-supervised embedding method leveraging the fractal effect in topographic images, enabling scale-invariant classification and representation of elevation data with minimal supervision.

Contribution

It presents the first generic topography embedding technique using the fractal effect, tailored for remote sensing data and scale-invariant topographic analysis.

Findings

Effective in classifying topographic features across scales

Demonstrates the first use of fractal effect in topography embedding

Improves detection of similar classes in elevation data

Abstract

Recent advances in deep learning have transformed many fields by introducing generic embedding spaces, capable of achieving great predictive performance with minimal labeling effort. The geology field has not yet met such success. In this work, we introduce an extension for self-supervised learning techniques tailored for exploiting the fractal-effect in remote-sensing images. The fractal-effect assumes that the same structures (for example rivers, peaks and saddles) will appear in all scales. We demonstrate our method's effectiveness on elevation data, we also use the effect in inference. We perform an extensive analysis on several classification tasks and emphasize its effectiveness in detecting the same class on different scales. To the best of our knowledge, it is the first attempt to build a generic representation for topographic images.