Explainable Clustering Applied to the Definition of Terrestrial Biomes

Mohamed Sidoumou, Alisa Kim, Jeremy Walton, Douglas Kelley, Robert Parker, Ranjini Swaminathan

2022

Abstract

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 algorithm. 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.

Paper Citation

in Harvard Style

Sidoumou M., Kim A., Walton J., Kelley D., Parker R. and Swaminathan R. (2022). Explainable Clustering Applied to the Definition of Terrestrial Biomes. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 586-595. DOI: 10.5220/0010842400003122

in Bibtex Style

@conference{icpram22,
author={Mohamed Sidoumou and Alisa Kim and Jeremy Walton and Douglas Kelley and Robert Parker and Ranjini Swaminathan},
title={Explainable Clustering Applied to the Definition of Terrestrial Biomes},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={586-595},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010842400003122},
isbn={978-989-758-549-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Explainable Clustering Applied to the Definition of Terrestrial Biomes
SN - 978-989-758-549-4
AU - Sidoumou M.
AU - Kim A.
AU - Walton J.
AU - Kelley D.
AU - Parker R.
AU - Swaminathan R.
PY - 2022
SP - 586
EP - 595
DO - 10.5220/0010842400003122