Abstract
In this study, a new tool for quantitative, data-driven susceptibility zoning (SZ) is presented. The SZ plugin has been implemented as a QGIS plugin to maximize its operational use within the geoscientific community. QGIS is in fact a commonly used open-source geographic information system. We have scripted the plugin in Python, and developed it as a collection of functions that allow one to pre-process the input data, calculate the susceptibility, and then estimate the quality of the classification results. The susceptibility zoning can be carried out via a number of classifiers including weight of evidence, frequency ratio, logistic regression, random forest, support vector machine, and decision tree. The plugin allows one to use any kind of mapping units, to fit the model, to test it via a k-fold cross-validation, and to visualize the relative receiving operating characteristic (ROC) curves. Moreover, a new classification method of the susceptibility index (SI) has been implemented in the SZ plugin. A typical workflow of the SZ plugin is described, and its application for landslide susceptibility zoning in Northeast India is reported. The data of the predisposing factors used are open, and the analysis has been carried out using a logistic regression and weight of evidence models. The corresponding area under the curve of the relative ROC curves reflects an optimal model prediction capacity. The user-friendly graphical interface of the plugin has allowed us to perform the analysis efficiently in few steps.
Highlights
The measure of how much a specific area is prone to natural hazards is called susceptibility
This study describes in detail the susceptibility zoning (SZ) plugin graphical user interface together with all its functions and provides a sample application to landslide susceptibility in Northeast India
We reported additional references about the predisposing factors and landslide inventory as follows: lithology, land cover, peak ground acceleration (PGA), annual precipitation from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), and Normalized Difference Vegetation Index (NDVI) from Landsat Seven Collection 1 Tier 1 composites for 32-day period provided by U.S Geological Survey, landslide inventory
Summary
The measure of how much a specific area is prone to natural hazards is called susceptibility. The susceptibility is the estimation of the likelihood of spatial occurrence of natural hazard evaluated on the basis of terrain and environmental conditions (Brabb, 1985). In most cases, this likelihood can be obtained via rigorous probabilistic models, other tools are able to convey similar information without relying on complex multivariate statistics (e.g., Ciurleo et al, 2017; Lombardo et al, 2020a). The way a classifier works is to weigh the contribution of each predisposing factor to the occurrence of natural hazards, Mapping Susceptibility With Open-Source Tools taking into account the presence/absence proportion of past records, given other predisposing factors in the model. The current version (v1.0) is available in the following GitHub repository CNR-IRPI-Padova/SZ
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
