Explainable Clustering Applied to the Definition of Terrestrial Biomes

Sidoumou, M., Kim, A., Walton, J., Kelley, D., Parker, R. and Swaminathan, R. ORCID: https://orcid.org/0000-0001-5853-2673 (2022) Explainable Clustering Applied to the Definition of Terrestrial Biomes. In: Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - ICPRAM, 3-5 FEB 2022, Online, pp. 586-595. doi: 10.5220/0010842400003122

Abstract/Summary

We present an explainable clustering approach for use with 3D tensor data and use it to define terrestrial biomes from observations in an automatic, data-driven fashion. Our approach allows us to use a larger number of features than is feasible for current empirical methods for defining biomes, which typically rely on expert knowledge and are inherently more subjective than our approach. The data consists of 2D maps of geophysical observation variables, which are rescaled and stacked to form a 3D tensor. We adapt an image segmentation algorithm to divide the tensor into homogeneous regions before partitioning the data using the k-means algo- rithm. We add explainability to the classification by approximating the clusters with a compact decision tree whose size is limited. Preliminary results show that, with a few exceptions, each cluster represents a biome which can be defined with a single decision rule.

Item Type	Conference or Workshop Item (Paper)
URI	https://reading-clone.eprints-hosting.org/id/eprint/103900
Identification Number/DOI	10.5220/0010842400003122
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > National Centre for Earth Observation (NCEO) Science > School of Mathematical, Physical and Computational Sciences > Department of Meteorology
Download/View statistics	View download statistics for this item