A review of statistically-based landslide susceptibility models
Citation
Reichenbach, P., Rossi, M., Malamud, B.D., Mihir, M., Guzzetti, F. (2018). A review of statistically-based landslide susceptibility models. Earth-Science Reviews, 180: 60-91. Link to paper
Abstract
The authors systematically reviewed 565 peer-review articles from 1983 to 2016, examining statistically-based landslide susceptibility assessment methods. The most common statistical methods include logistic regression, neural network analysis, data-overlay, index-based and weight of evidence analyses, with an increasing preference towards machine learning methods in recent years. Although an increasing number of studies have assessed model performance in terms of model fit and prediction performance, only a handful evaluated model uncertainty. There's a clear geographical bias with many studies in China, India, Italy and Turkey, and only a few in Africa, South America and Oceania. The quality of published models has improved over the years, but top-quality assessments remain rare.