DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic Monitoring

2026-10-07

AI Summary

This study addresses the challenge of organizing surface activities into meaningful process types in terrain monitoring by proposing an unsupervised classification framework based on 4D point clouds. The framework introduces a novel GeoMorphogram representation to capture spatiotemporal evolution, integrating a convolutional autoencoder with hierarchical deep clustering to enable interpretable, data-driven automatic derivation of hierarchical surface processes. Evaluated on a sandy beach dataset acquired via permanent laser scanning, the proposed method achieves an F1 score of 0.78 and a matching accuracy of 0.92. These results demonstrate superior performance over conventional approaches, effectively distinguishing between erosion and deposition activities.

Abstract

4D point clouds acquired by permanent laser scanning (PLS) enable accurate high-frequency monitoring of surface change in dynamic topographic environments. However, existing methods remain limited in organizing detected surface activities into meaningful process types. We propose DeepTopoClustering (DTC), an unsupervised framework for deriving a hierarchical process taxonomy from object-based surface activities, so-called 4D objects-by-change (4D-OBCs). We transform each 4D-OBC into a GeoMorphogram, a distributional sequence representing the temporal evolution of topographic change within a spatially bounded surface activity. A convolutional autoencoder learns latent embeddings from GeoMorphograms, which are jointly optimized using a hierarchical deep clustering objective to organize surface activities into a hierarchy. We evaluate the learned hierarchy using expert annotations on two 4D datasets of sandy beach sites and their combination. DTC with GeoMorphograms achieves the highest agreement with expert judgment at the taxonomy level comprising eight major process types ($F_1=0.78$, match accuracy $=0.92$), outperforming dimensionality reduction and conventional flat clustering. The learned taxonomy separates major erosion- and deposition-dominated activities and distinguishes finer subtypes based on change magnitude, duration, compactness, and temporal evolution. DTC thus provides a scalable and interpretable route from 4D change detection to a data-driven, expert-supported surface process taxonomy, advancing automated knowledge derivation for understanding surface dynamics in topographic monitoring.

Problem

• 4D point clouds
• topographic monitoring
• surface process taxonomy
• unsupervised clustering
• 4D objects-by-change

Innovation

• 4D point clouds
• unsupervised deep clustering
• GeoMorphogram
• convolutional autoencoder
• surface process taxonomy