Preprints
https://doi.org/10.5194/egusphere-2026-6800
https://doi.org/10.5194/egusphere-2026-6800
17 Nov 2026
 | 17 Nov 2026

Information-theoretic modeling of landslide susceptibility using mostly categorical spatial data

David Percy, Scott Burns, Adam M. Booth, and Martin Zwick

Abstract. Landslide susceptibility mapping with machine learning should make full use of inherently informative categorical layers such as lithology, soil type, and land use, yet these variables usually enter models in a diminished, encoded form. Reconstructability Analysis (RA), an information-theoretic method based on Shannon entropy, uses categorical data directly and produces transparent, interpretable models. We applied RA to two contiguous Oregon Coast Range (USA) watersheds (3,500 km²) rated Very High Risk for landslides by the Federal Emergency Management Agency, using ~9,000 landslide deposits mapped mostly from LiDAR by the Oregon Department of Geology and Mineral Industries (DOGAMI), with DOGAMI lithology, Soil Survey, and National Land Cover Database layers; terrain variables were discretized into optimized bins. Variable importance analysis led to stratification into volcanic and sedimentary lithologies, with landslide rates of 44 % and 60 %. The best RA models reached 75 % (volcanic) and 71 % (sedimentary) test accuracy, nearly as good as Random Forest, while remaining interpretable in terms of named soil, landform, and rock units. Their probability tables give landslide likelihood for specific combinations of landform, geology, and elevation; in the sedimentary stratum, two andic soil subgroups emerged as most landslide-prone, consistent with high water retention. The tables are provided as a supplement.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
David Percy, Scott Burns, Adam M. Booth, and Martin Zwick

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
David Percy, Scott Burns, Adam M. Booth, and Martin Zwick

Data sets

Landslide susceptibility probability tables and sample points from Reconstructability Analysis, Wilson-Trask-Nestucca and Siletz-Yaquina watersheds, Oregon Coast Range, USA D. Percy et al. https://doi.org/10.5281/zenodo.23910138

Model code and software

PyOccam: Python bindings for OCCAM Reconstructability Analysis (v0.9.5) D. Percy and M. Zwick https://doi.org/10.5281/zenodo.20352230

David Percy, Scott Burns, Adam M. Booth, and Martin Zwick
Metrics will be available soon.
Latest update: 17 Nov 2026
Download
Short summary
Landslide susceptibility maps are usually built with machine-learning methods that are accurate but hard to interpret, and that handle descriptive data such as soil and rock type poorly. We applied Reconstructability Analysis, which uses such data directly, to two landslide-prone watersheds in Oregon’s Coast Range. The models were nearly as accurate as Random Forest and produced plain probability tables naming the soils, rock units, and elevations most prone to landslides.
Share