A Global Debris Flow Susceptibility Map Based on a Comparative Analysis of a Single Global Model Versus a Continent-by-continent Approach

Debris flows, and landslides in general, are worldwide catastrophic phenomena. As world population and urbanization grow in magnitude and geographic coverage, the need exists to extend focus, research, and modeling to a continental and global scale.Although debris flow behavior and parameters are local phenomena, sound generalizations can be applied to debris flow susceptibility analyses at larger geographic extents based on these criteria. The focus of this research is to develop a global debris flow susceptibility map by modeling at both a continental scale for all continents and by a single global model and determine whether a global model adequately represents each continent. Probability Density, Conditional Probability, Certainty Factor, Frequency Ratio, and Maximum Entropy statistical models were developed and evaluated for best model performance using fourteen environmental factors generally accepted as the most appropriate debris flow predisposing factors. Global models and models for each continent were then developed and evaluated against verification data. The comparative analysis demonstrates that a single global model performs comparably or better than individual continental models for a majority of the continents, resulting in a debris flow susceptibility map of the world useful in international planning, and future debris flow susceptibility modeling for determining societal impacts.

Preliminary Study of Landslide Susceptibility Modeling with Random Forest Algorithm Using R (Case Study: the Cisangkuy Sub-watershed)

Landslide susceptibility mapping is an initial measure in the landslide hazard mitigation. This study aims to evaluate landslide susceptibility in the Cisangkuy Sub-watershed, a part of Bandung Basin. Twenty-seven landslide variables were involved in this modeling derived from various data sources. As a target, 25 landslide polygons obtained through a visual interpretation of Google Earth timeseries images and 33 landslide points obtained from a field survey and an official landslide report, were used as landslide inventory data. All spatial data were prepared in the same cell size referring to the highest spatial resolution of data involved in this modeling, i.e., 8.34 m. Fifty-eight (58) landslide locations covering an area of 0.87 Ha are equivalent to 1040 cells in the raster format. In total, 2040 samples consisting of landslides and non-landslides with the same ratio, were trained using random forest algorithm. Non-landslides were sampled randomly from landslide-free cells. This modeling was executed using R environment. In this study, the result was two labels, susceptible and non-susceptible. This model provided an excellent performance, its accuracy reached 98.56%. This research needs an improvement to provide a probability that has a range of 0 to 1 to show the level of landslide susceptibility.

Implementation of Landslide Susceptibility Model Using Machine Learning for Semi Detailed Map Scale in Mountainous Region of Java Island

Landslide susceptibility modeling using neural network (ANN) are applied to semi detailed volcanic-sedimentary water catchment. Annually landslide occurred in catchment area frequently in unconsolidated and weathered material combined with uncertainty in rainfall pattern that complicated landslide occurrence. Data used for analysis including landslide inventory, geology, digital elevation related data, distance to stream, and several other available data. Results show that machine learning method yield fair result data based on evaluation on Area under Curve (AUC). Thus, it can be suggested that machine learning methods for landslide susceptibility model could still be develop to produce robust prediction model with different characterization of parameter data and machine learning parameters.

Integrating Multivariate (GeoDetector) and Bivariate (IV) Statistics for Hybrid Landslide Susceptibility Modeling: A Case of the Vicinity of Pinios Artificial Lake, Ilia, Greece

Over the last few years, landslides have occurred more and more frequently worldwide, causing severe effects on both natural and human environments. Given that landslide susceptibility (LS) assessments and mapping can spatially determine the potential for landslides in a region, it constitutes a basic step in effective risk management and disaster response. Nowadays, several LS models are available, with each one having its advantages and disadvantages. In order to enhance the benefits and overcome the weaknesses of individual modeling, the present study proposes a hybrid LS model based on the integration of two different statistical analysis models, the multivariate Geographical Detector (GeoDetector) and the bivariate information value (IV). In a GIS-based framework, the hybrid model named GeoDIV was tested to generate a reliable LS map for the vicinity of the Pinios artificial lake (Ilia, Greece), a Greek wetland. A landslide inventory of 60 past landslides and 14 conditioning (morphological, hydro-lithological and anthropogenic) factors was prepared to compose the spatial database. An LS map was derived from the GeoDIV model, presenting the different zones of potential landslides (probability) for the study area. This map was then validated by success and prediction rates—which translate to the accuracy and prediction ability of the model, respectively. The findings confirmed that hybrid modeling can outperform individual modeling, as the proposed GeoDIV model presented better validation results than the IV model.