GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms

In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar remote sensing data and geographic information system(GIS), for landslide susceptibility mapping(LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory(70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party(ILWP), Forestry, Rangeland and Watershed Organisation(FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve(AUC), frequency ratio(FR) and seed cell area index(SCAI).Normalised difference vegetation index, land use/land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models(AUC = 0.912(91.2%) and 0.907(90.7%), respectively) had high predictive accuracy than the LNRF model alone(AUC = 0.855(85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping.

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3%of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.

Modelling of piping collapses and gully headcut landforms: Evaluating topographic variables from different types of DEM

The geomorphic studies are extremely dependent on the quality and spatial resolution of digital elevation model(DEM)data.The unique terrain characteristics of a particular landscape are derived from DEM,which are responsible for initiation and development of ephemeral gullies.As the topographic features of an area significantly influences on the erosive power of the water flow,it is an important task the extraction of terrain features from DEM to properly research gully erosion.Alongside,topography is highly correlated with other geo-environmental factors i.e.geology,climate,soil types,vegetation density and floristic composition,runoff generation,which ultimately influences on gully occurrences.Therefore,terrain morphometric attributes derived from DEM data are used in spatial prediction of gully erosion susceptibility(GES)mapping.In this study,remote sensing-Geographic information system(GIS)techniques coupled with machine learning(ML)methods has been used for GES mapping in the parts of Semnan province,Iran.Current research focuses on the comparison of predicted GES result by using three types of DEM i.e.Advanced Land Observation satellite(ALOS),ALOS World 3D-30 m(AW3D30)and Advanced Space borne Thermal Emission and Reflection Radiometer(ASTER)in different resolutions.For further progress of our research work,here we have used thirteen suitable geo-environmental gully erosion conditioning factors(GECFs)based on the multi-collinearity analysis.ML methods of conditional inference forests(Cforest),Cubist model and Elastic net model have been chosen for modelling GES accordingly.Variable’s importance of GECFs was measured through sensitivity analysis and result show that elevation is the most important factor for occurrences of gullies in the three aforementioned ML methods(Cforest=21.4,Cubist=19.65 and Elastic net=17.08),followed by lithology and slope.Validation of the model’s result was performed through area under curve(AUC)and other statistical indices.The validation result of AUC has shown that Cforest is the most appropriate model for predicting the GES assessment in three different DEMs(AUC value of Cforest in ALOS DEM is 0.994,AW3D30 DEM is 0.989 and ASTER DEM is 0.982)used in this study,followed by elastic net and cubist model.The output result of GES maps will be used by decision-makers for sustainable development of degraded land in this study area.