Flood-prone area mapping using machine learning techniques: a case study of Quang Binh province,Vietnam

Natural Hazards - Vietnam’s central coastal region is the most vulnerable and always at flood risk, severely affecting people’s livelihoods and socio-economic development. In...     

Flash-flood potential assessment and mapping by integrating the weights-of-evidence and frequency ratio statistical methods in GIS environment – case study: Bâsca Chiojdului River catchment (Romania)

Given the significant worldwide human and economic losses caused due to floods annually, reducing the negative consequences of these hazards is a major concern in development strategies at different spatial scales. A basic step in flood risk management is identifying areas susceptible to flood occurrences. This paper proposes a methodology allowing the identification of areas with high potential of accelerated surface run-off and consequently, of flash-flood occurrences. The methodology involves assessment and mapping in GIS environment of flash flood potential index (FFPI), by integrating two statistical methods: frequency ratio and weights-of-evidence. The methodology was applied for Bâsca Chiojdului River catchment (340 \(\hbox {km}^{2}\)), located in the Carpathians Curvature region (Romania). Firstly, the areas with torrential phenomena were identified and the main factors controlling the surface run-off were selected (in this study nine geographical factors were considered). Based on the features of the considered factors, many classes were set for each of them. In the next step, the weights of each class/category of the considered factors were determined, by identifying their spatial relationships with the presence or absence of torrential phenomena. Finally, the weights for each class/category of geographical factors were summarized in GIS, resulting the FFPI values for each of the two statistical methods. These values were divided into five classes of intensity and were mapped. The final results were used to estimate the flash-flood potential and also to identify the most susceptible areas to this phenomenon. Thus, the high and very high values of FFPI characterize more than one-third of the study catchment. The result validation was performed by (i) quantifying the rate of the number of pixels corresponding to the torrential phenomena considered for the study (training area) and for the results’ testing (validating area) and (ii) plotting the ROC (receiver operating characteristics) curve.     

GIS-based landslide susceptibility modeling: A comparison between fuzzy multi-criteria and machine learning algorithms

Hazards and disasters have always negative impacts on the way of life.Landslide is an overwhelming natural as well as man-made disaster that causes loss of natural resources and human properties throughout theworld.The present study aimed to assess and compare the prediction efficiency of different models in landslide susceptibility in the Kysuca river basin,Slovakia.In this regard,the fuzzy decision-making trial and evaluation laboratory combining with the analytic network process(FDEMATEL-ANP),Na?ve Bayes(NB)classifier,and random forest(RF)classifier were considered.Initially,a landslide inventory map was produced with 2000 landslide and nonlandslide points by randomly dividedwith a ratio of 70%:30%for training and testing,respectively.The geospatial database for assessing the landslide susceptibility was generated with the help of 16 landslide conditioning factors by allowing for topographical,hydrological,lithological,and land cover factors.The ReliefF methodwas considered for determining the significance of selected conditioning factors and inclusion in the model building.Consequently,the landslide susceptibility maps(LSMs)were generated using the FDEMATEL-ANP,Na?ve Bayes(NB)classifier,and random forest(RF)classifier models.Finally,the area under curve(AUC)and different arithmetic evaluation were used for validating and comparing the results and models.The results revealed that random forest(RF)classifier is a promising and optimum model for landslide susceptibility in the study area with a very high value of area under curve(AUC=0.954),lower value of mean absolute error(MAE=0.1238)and root mean square error(RMSE=0.2555),and higher value of Kappa index(K=0.8435)and overall accuracy(OAC=92.2%).     

Estimation of Ground Vibration Intensity Induced by Mine Blasting using a State-of-the-Art Hybrid Autoencoder Neural Network and Support Vector Regression Model

Natural Resources Research - In surface mining, blasting is an indispensable method for fragmenting rock masses. Nevertheless, it can inherently induce many side effects like ground vibrations. At...     

Toward state-of-the-art techniques in predicting and controlling slope stability in open-pit mines based on limit equilibrium analysis,radial basis function neural network,and brainstorm optimization

Acta Geotechnica - This study aims to propose state-of-the-art techniques in predicting and controlling slope stability in open-pit mines based on limit equilibrium analysis, artificial neural...     

Assessment of surface runoff depth changes in Sǎrǎţel River basin,Romania using GIS techniques

Sǎrǎ?el River basin, which is located in Curvature Subcarpahian area, has been facing an obvious increase in frequency of hydrological risk phenomena, associated with torrential events, during the last years. This trend is highly related to the increase in frequency of the extreme climatic phenomena and to the land use changes. The present study is aimed to highlight the spatial and quantitative changes occurred in surface runoff depth in Sǎrǎ?el catchment, between 1990–2006. This purpose was reached by estimating the surface runoff depth assignable to the average annual rainfall, by means of SCS-CN method, which was integrated into the GIS environment through the ArcCN-Runoff extension, for ArcGIS 10.1. In order to compute the surface runoff depth, by CN method, the land cover and the hydrological soil classes were introduced as vector (polygon data), while the curve number and the average annual rainfall were introduced as tables. After spatially modeling the surface runoff depth for the two years, the 1990 raster dataset was subtracted from the 2006 raster dataset, in order to highlight the changes in surface runoff depth.