Search

Abstract In river research, forecasting flow velocity accurately in vegetated channels is a significant challenge. The forecasting performance of various independent and hybrid machine learning (ML) models are thus quantified for the first time in this work. Utilizing flow velocity measurements in both natural and laboratory flume experiments, we assess the efficacy of four distinct standalone machine learning techniques—Kstar, M5P, reduced error pruning tree (REPT) and random forest (RF) models. In addition, we also test for eight types of hybrid ML algorithms trained with an Additive Regression (AR) and Bagging (BA) (AR-Kstar, AR-M5P, AR-REPT, AR-RF, BA-Kstar, BA-M5P, BA-REPT and BA-RF). Findings from a comparison of their predictive capabilities, along with a sensitivity analysis of the influencing factors, indicated: (1) Vegetation height emerged as the most sensitive parameter for determining the flow velocity; (2) all ML models displayed outperforming empirical equations; (3) nearly all ML algorithms worked optimal when the model was built using all of the input parameters. Overall, the findings showed that hybrid ML algorithms outperform regular ML algorithms and empirical equations at forecasting flow velocity. AR-M5P (R2 = 0.954, R = 0.977, NSE = 0.954, MAE = 0.042, MSE = 0.003, and PBias = 1.466) turned out to be the optimal model for forecasting of flow velocity in vegetated-rivers.

Accurate prediction of daily river flow (Qt) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Qt as well as one- and two-day-ahead river flow forecasts (i.e. Qt+1 and Qt+2). The predictive performance of M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), and Rotation Forest (ROF) were comprehensively evaluated. The proposed models were applied to a case study data in Tuolumne County, US, using a dataset comprising measured precipitation (Pt), evaporation (Et), and Qt. A wide range of input scenarios were explored for predicting Qt, Qt+1, and Qt+2. Results indicate that Pt and Qt significantly influence prediction accuracy. Notably, relying solely on the most correlated variable (e.g., Qt-1) does not guarantee robust prediction of Qt. However, extending the forecast horizon mitigates the influence of low-correlation input variables on model accuracy. Performance metrics indicate that the DA-M5P model achieves superior results, with Nash-Sutcliff Efficiency of 0.916 and root mean square error of 23 m3/s, followed by ROF-M5P, BA-M5P, AR-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, and the standalone M5P model. The ensemble M5P modeling framework enhanced the predictive capability of the stand-alone M5P algorithm by 1.2 %–22.6 %, underscoring its efficacy and potential for advancing hydrological forecasting.

In this study, three novel machine learning algorithms of additive regression-random forest (AR-RF), Iterative Classifier Optimizer (ICO-AR-RF), and multi-scheme (MS-RF) were explored for carbon dioxide (CO2) flux rate prediction from three agricultural fields. To build the dataset, 401 samples were collected from two fields in Prince Edward Island (PEI) and 122 samples from the New Brunswick (NB), Canada. In addition, soil moisture (SM), temperature (ST), and electrical conductivity (EC), alongside eight climatic variables including wind speed (WS), solar radiation (SR), relative humidity (RH), precipitation (PCP), air temperature (AT), dew point (DP), vapour pressure difference (VPD) and reference evapotranspiration (ETo) were also collected. Greedy stepwise (GS) approach was implemented for feature selection. Finally, different qualitative (scatter plot, line graph, Taylor diagram, box plot, and Rug plot), and quantitative (uncertainty analysis, root mean square error (RMSE), percent of BIAS (PBIAS), Nash Sutcliff efficiency (NSE) and RMSE-observations standard deviation ratio (RSR)) techniques were used for model evaluation and comparison. Results of feature selection approaches revealed that DP, AT, SM, and ST are the four most effective variables at CO2 prediction in PEI, while AT, RH, DP, and ST are the most effective in the NB study area. For optimum input scenario, the GS algorithm was applied, and results showed that a combination of DP, AT, ST, SM, and ETo was the best for the PEI study area, while for NB, all input variables should be involved. Our analysis, for prediction of CO2 fluxes, confirmed that the ICO-AR-RF model performed the best at both PEI (RMSE=0.70, NSE=0.76, PBIAS=-5.11, RSR=0.48) and NB (RMSE=0.74, NSE=0.75, PBIAS=3.23, RSR=0.50), followed by MS-RF and AR-RF. Uncertainty analysis showed that CO2 prediction is more sensitive to input scenario selection than models in both study areas. Results revealed that climatic variables are more effective in CO2 prediction than soil characteristics and the developed hybrid model ICO-AR-RF can be a promising tool for decision-makers and beneficial for stakeholders.

The potential of advanced tree-based models and optimized deep learning algorithms to predict fluvial bedload transport was explored, identifying the most flexible and accurate algorithm, and the optimum set of readily available and reliable inputs. Using 926 datasets for 20 rivers, the performance of three groups of models was tested: (1) standalone tree-based models Alternating Model Tree (AMT) and Dual Perturb and Combine Tree (DPCT); (2) ensemble tree-based models Iterative Absolute Error Regression (IAER), ensembled with AMT and DPCT; and (3) optimized deep learning models Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) ensembled with Grey Wolf Optimizer. Comparison of the predictive performance of the models with that of commonly used empirical equations and sensitivity analysis of the driving variables revealed that: (i) the coarse grain-size percentile D90 was the most effective variable in bedload transport prediction (where Dx is the xth percentile of the bed surface grain size distribution), followed by D84, D50, flow discharge, D16, and channel slope and width; (ii) all tree-based models and optimized deep learning algorithms displayed ‘very good’ or ‘good’ performance, outperforming empirical equations; and (iii) all algorithms performed best when all input parameters were used. Thus, a range of different input variable combinations must be considered in the optimization of these models. Overall, ensemble algorithms provided more accurate predictions of bedload transport than their standalone counterpart. In particular, the ensemble tree-based model IAER-AMT performed most strongly, displaying great potential to produce robust predictions of bedload transport in coarse-grained rivers based on a few readily available flow and channel variables.

Abstract The Google Earth Engine (GEE) was used to investigate the performance of the Global Land Data Assimilation System (GLDAS) soil temperature (ST) data against observed ST from 13 synoptic stations over a semiarid region in Iran. Three‐hourly ST data were collected and analyzed in two depths (0–10 cm; 40–100 cm) and 5 years. In each depth, GLDAS‐Noah ST data were evaluated for daily minimum, maximum, and average ST (i.e., Tmin, Tmax, and Tavg). Based on the correlation coefficient, Kling–Gupta Efficiency, and Nash–Sutcliffe Efficiency the overall performance of the GLDAS‐Noah is 0.96, 0.66, and 0.79 for Tmin; 0.97, 0.84, and 0.89 for Tavg; and 0.95, 0.89, and 0.89 for Tmax, respectively in the first layer. Likewise, 0.97, 0.85, and 0.86 for Tmin; 0.97, 0.77, and 0.80 for Tavg; and 0.97, 0.69, and 0.69 for Tmax are obtained in the second layer. However, there is a significant negative bias which tends to underestimate ST in the two investigated layers, given by an average bias over all the stations analyzed of −24%, −12%, and −5% for Tmin, Tavg, and Tmax in the first layer, and average bias of −8%, −13%, and −17% for Tmin, Tavg, and Tmax in the second layer. This study reveals that GLDAS‐Noah‐derived ST can be used in arid regions where little or no observation data is available. Moreover, GEE performed as an advanced geospatial processing tool in regional scale analysis of ST in different layers.

Abstract Flooding is one of the most serious and frequent natural hazards affecting human life, property, and the environment. This study develops and tests a deep learning approach for large‐scale spatial flood modeling, using Convolutional Neural Network (CNN) and optimized versions combined with the Gray Wolf Optimizer (GWO) or the Imperialist Competitive Algorithm (ICA). With Sweden as an application case for nation‐wide flood susceptibility mapping, this modeling approach considers ten geo‐environmental input factors (slope, elevation, aspect, plan curvature, length of slope, topographic wetness index, distance from river, distance from wetland, rainfall, and land use). The GWO and ICA optimization improves model prediction by 12% and 8%, respectively, compared with the standalone CNN model performance. The results show 40% of the land area, 45% of the railroad, and 43% of the road network of Sweden to have high or very high flood susceptibility. They also show the aspect to have the highest input factor impact on flood susceptibility prediction while, for example, rainfall ranks only seven of the total 10 considered geo‐environmental input factors. In general, accurate nation‐wide flood susceptibility prediction is essential for guiding flood management and mitigation efforts. This study's approach to such prediction has emerged as well‐performing and cost‐effective for the case of Sweden, calling for further application and testing in other world regions.

This study examines the relations of structures and shapes of streambed evolution after dam break floods. A flume was used to simulate dam-break floods with variations of initial upstream water levels and variance, from uniform to graded, of the bed sediments. Detailed measurements of the evolution and composition were made during these experiments. The data indicate that intense scour occurred immediately downstream of the “dam break” in both uniform and graded sediments. The resulting bed surfaces of graded sediments showed coarse-fine-coarse structures in the areas with the lowest scour and highest deposition and various type of cluster (i.e. line and heap). This pattern was not observed in beds of uniform sediment. The scour hole changes from circular to oval-shaped in both uniform and graded sediments with increasing bed slopes. Keywords: Dam break, Experimental, Bed-surface composition, Graded and uniform sediment, Scour.

Study region: Sixteen different sites from two provinces (Lorestan and Illam) in the western part of Iran were considered for the field data measurement of cumulative infiltration, infiltration rate, and other effective variables that affect infiltration process. Study focus: Soil infiltration is recognized as a fundamental process of the hydrologic cycle affecting surface runoff, soil erosion, and groundwater recharge. Hence, accurate prediction of the infiltration process is one of the most important tasks in hydrological science. As direct measurement is difficult and costly, and empirical models are inaccurate, the current study proposed a standalone, and optimized deep learning algorithm of a convolutional neural network (CNN) using gray wolf optimization (GWO), a genetic algorithm (GA), and an independent component analysis (ICA) for cumulative infiltration and infiltration rate prediction. First, 154 raw datasets were collected including the time of measuring; sand, clay, and silt percent; bulk density; soil moisture percent; infiltration rate; and cumulative infiltration using field survey. Next, 70 % of the dataset were used for model building and the remaining 30 % was used for model validation. Then, based on the correlation coefficient between input variables and outputs, different input combinations were constructed. Finally, the prediction power of each developed algorithm was evaluated using different visually-based (scatter plot, box plot and Taylor diagram) and quantitatively-based [root mean square error (RMSE), mean absolute error (MAE), the Nash-Sutcliffe efficiency (NSE), and percentage of bias (PBIAS)] metrics. New Hydrological Insights for the Region: Finding revealed that the time of measurement is more important for cumulative infiltration, while soil characteristics (i.e. silt content) are more significant in infiltration rate prediction. This shows that in the study area, silt parameter, which is the dominant constituent parameter, can control infiltration process more effectively. Effectiveness of the variables in the present study, in the order of importance are time, silt, clay, moisture content, sand, and bulk density. This can be related to the fact that most of study area is rangeland and thus, overgrazing leads to compaction of the silt soil that can lead to a slow infiltration process. Soil moisture content and bulk density are not highly effective in our study because these two factors do not significantly change across the study area. Findings demonstrated that the optimum input variable combination, is the one in which all input variables are considered. The results illustrated that CNN algorithms have a very high performance, while a metaheuristic algorithm enhanced the performance of a standalone CNN algorithm (from 7% to 28 %). The results also showed that a CNN-GWO algorithm outperformed the other algorithms, followed by CNN-ICA, CNN-GA, and CNN for both cumulative infiltration and infiltration rate prediction. All developed algorithms underestimated cumulative infiltration, while overestimating infiltration rates.

Flood can be having devastating effects on watersheds and human life, so, recognize of flood prone areas have a high influences on flood management. The aim of this study is to assessment of flood susceptibility at Talar watershed with an area of 2067 square kilometers. For this purpose some flood conditioning factor such as elevation, land slope, curvature, topographic wetness index, stream power index, average rainfall, distance to the river, hydrologic group of soil, maximum depth of soil, and land-use have been used. Flood conditioning factor have been prepared using related software and then converted to raster format. In the next step the 135 flood location in the study area were determined. These flood location were divided into two groups consisting of 93 locations for calibration and 42 locations, for validation. Then with comparatively analysis between previous floods coordinates and impressive environmental parameters on flood occurrence the probability of flooding for each class of each parameter was calculated. Faunally was obtained the flood risk map of the study area. Based on the flood risk map, the territory was divided to 5 class sensitivity, very high, high, medium, low and very little. The results have been showed that the frequency ratio method with 80% accuracy have high performance in determination of flood prone areas in Talar watershed.

This study aimed to evaluate the temporal change and accuracy of interpolation techniquesused for spatial zonation of two groundwater quantity parameters including water table anddepth to water table over 11 years. The study was conducted based on the data collectedfrom piezometric wells of Sari-Neka Plain in Mazandaran Province, Iran. The investigatedmethods included a set of geostatistical approaches involving simple Kriging, ordinaryKriging, Radial Basis Function (RBF), and a deterministic interpolation method calledInverse Distance Weighting (IDW) with powers of 1 and 5. Subsequent to quality controland data normalization, the most appropriate variogram was chosen based on low RSS andhigh r2 while the most suitable interpolation technique was determined regarding the crossvalidation, Mean Absolute Error (MAE), and Mean Bias Error (MBE). The resultsdemonstrated that Simple Kriging was the most suitable method for zoning the depth togroundwater over the years 2001, 2006, and 2012. Meanwhile, the most suitable methodsfor zoning the water table included IDW with a power of 1for the year 2001, RBF for theyear 2006, and IDW with a power of 5 for the year 2012. The important finding was thatthe interpolation methods showed a lower error for estimating water table than estimatingdepth to groundwater. This study also revealed a drop in water table in the study area overthe 11 years’ period. Meanwhile, new water table classes have been added and extendedbetween the years 2006 and 2012 that had not existed five years earlier. The highest watertable losses were observed in three points at 13m depth to water table in the middle andnorthern parts of the study area.

Drought is known as one of the environmental phenomena, and in fact an integral part of climate change that can occur in any geographic area (Mofidipoor et al., 2012 .( This phenomenon reveals its effects slowly and gradually, and its effects remain for long time and this is the feature that distinct it from other phenomena such as floods (Dai, 2010). Many indices have been offered to study drought such as Palmer index (Palmer, 1965), deciles method (Gibbs and Maher, 1967) and Standardized Precipitation Index (McKee et al., 1993). In general, the main objective of this study was to investigate the drought status in Sari-Neka plain using four indices including Rainfall Anomaly Index (RAI), Z-Score (Z), China Z-Index (CZI) and Percent of Normal precipitation Index (PNPI), as well as choosing the most suitable method among different interpolation methods and providing an appropriate model for drought zoning in the study area

Human activities are deeply connected with groundwater reservoirs, so protecting them from pollution has become a priority in many regions of the world. Nitrate is considered the main groundwater pollutant since it is directly linked to many human activities. Agricultural activities and domestic wastewater have been identified as the main sources of nitrate in groundwater. Nevertheless, there are some natural processes that can mitigate nitrate pollution. Together with dilution processes, the degradation of nitrate through denitrification has been acknowledge as a process that can potentially reduce nitrogen loads, in both deep and shallow aquifers. Usually these processes were not properly quantified in vulnerability assessment methods, until the introduction of LOS indices. In this study, the application of the LOS indices on 4 agricultural areas is discussed, highlighting how the LOS indices can identify portions of the landscape with higher potential denitrification and how they directly enhance the groundwater vulnerability assessment. Previous studies have shown that LOS indices are a valuable tool for proper vulnerability assessment to nitrate, however they need to be coupled with other parameters that also describe nitrate behavior in groundwater. The SINTACS-SVN and DRASTIC-PA methods that include the LOS indices, were applied for the first time in the Epanomi coastal area to evaluate the reliably of the assessment and, despite the different classes range and the weights applied, similar groundwater vulnerability assessment maps were obtained. The nitrate vulnerability maps were comparable with the observed nitrate concentrations and were found to be highly comparable with original LOS maps. Nevertheless, it should be kept in mind that vulnerability methods are only screening tools and groundwater quality observations are pivotal information for environmental management.

Mapping flood-prone areas is a key activity in flood disaster management. In this paper, we propose a new flood susceptibility mapping technique. We employ new ensemble models based on bagging as a meta-classifier and K-Nearest Neighbor (KNN) coarse, cosine, cubic, and weighted base classifiers to spatially forecast flooding in the Haraz watershed in northern Iran. We identified flood-prone areas using data from Sentinel-1 sensor. We then selected 10 conditioning factors to spatially predict floods and assess their predictive power using the Relief Attribute Evaluation (RFAE) method. Model validation was performed using two statistical error indices and the area under the curve (AUC). Our results show that the Bagging−Cubic−KNN ensemble model outperformed other ensemble models. It decreased the overfitting and variance problems in the training dataset and enhanced the prediction accuracy of the Cubic−KNN model (AUC=0.660). We therefore recommend that the Bagging−Cubic−KNN model be more widely applied for the sustainable management of flood-prone areas.

The most dangerous landslide disasters always cause serious economic losses and human deaths. The contribution of this work is to present an integrated landslide modelling framework, in which an adaptive neuro-fuzzy inference system (ANFIS) is combined with the two optimization algorithms of whale optimization algorithm (WOA) and grey wolf optimizer (GWO) at Anyuan County, China. It means that WOA and GWO are used as two meta-heuristic algorithms to improve the prediction performance of the ANFIS-based methods. In addition, the step-wise weight assessment ratio analysis (SWARA) method is used to obtain the initial weight of each class of landslide influencing factors. To validate the effectiveness of the proposed framework, 315 landslide events in history were selected for our experiments and were randomly divided into the training and verification sets. To perform landslide susceptibility mapping, fifteen geological, hydrological, geomorphological, land cover, and other factors are considered for the modelling construction. The landslide susceptibility maps by SWARA, SWARA-ANFIS, SWARA-ANFIS-PSO, SWARA-ANFIS-WOA, and SWARA-ANFIS-GWO models are assessed using the measures of the receiver operating characteristic (ROC) curve and root-mean-square error (RMSE). The experiments demonstrated that the obtained results of modelling process from the SWARA to the SAWRA-ANFIS-GWO model were more accurate and that the proposed methods have satisfactory prediction ability. Specifically, prediction accuracy by area under the curve (AUC) of SWARA, SWARA-ANFIS, SWARA-ANFIS-PSO, SWARA-ANFIS-GWO, and SWARA-ANFIS-WOA models were 0.831, 0.831, 0.850, 0.856, and 0.869, respectively. Due to adaptability and usability, the proposed prediction methods can be applied to other areas for landslide management and mitigation as well as prevention throughout the world.

Since it is not possible to determine the exact time of a natural disaster’s occurrence and the amount of physical and financial damage on humans or the environment resulting from their event, decision-makers need to identify areas with potential vulnerability in order to reduce future losses. In this paper, a GIS-based open source software entitled Seismic-Related Vulnerability Calculation Software (SEVUCAS), based on the Step-wise Weight Assessment Ratio Analysis (SWARA) method and geographic information system, has been developed to assess seismic vulnerability by considering four groups of criteria (i.e., geotechnical, structural, socio-economic, and physical distance to needed facilities and away from dangerous facilities). The software was developed in C# language using ArcGIS Engine functions, which provide enhanced visualization as well as user-friendly and automatic software for the seismic vulnerability assessment of buildings. Weighting of the criteria (indicators) and alternatives (sub-indicators) was done using SWARA. Also, two interpolation methods based on a radial basis function (RBF) and teaching−learning-based optimization (TLBO) were used to optimize the weights of the criteria and the classes of each alternative as well. After weighing the criteria and alternatives, the weighted overlay analysis was used to determine the final vulnerability map in the form of contours and statistical data. The difference between this software and similar ones is that people with a low level of knowledge in the area of earthquake crisis management can use it to determine and estimate the seismic vulnerabilities of their houses. This visualized operational forecasting software provides an applicable tool for both government and people to make quick and correct decisions to determine higher priority structures for seismic retrofitting implementation.

Floods are some of the most dangerous and most frequent natural disasters occurring in the northern region of Iran. Flooding in this area frequently leads to major urban, financial, anthropogenic, and environmental impacts. Therefore, the development of flood susceptibility maps used to identify flood zones in the catchment is necessary for improved flood management and decision making. The main objective of this study was to evaluate the performance of an Evidential Belief Function (EBF) model, both as an individual model and in combination with Logistic Regression (LR) methods, in preparing flood susceptibility maps for the Haraz Catchment in the Mazandaran Province, Iran. The spatial database created consisted of a flood inventory, altitude, slope angle, plan curvature, Topographic Wetness Index (TWI), Stream Power Index (SPI), distance from river, rainfall, geology, land use, and Normalized Difference Vegetation Index (NDVI) for the region. After obtaining the required information from various sources, 151 of 211 recorded flooding points were used for model training and preparation of the flood susceptibility maps. For validation, the results of the models were compared to the 60 remaining flooding points. The Receiver Operating Characteristic (ROC) curve was drawn, and the Area Under the Curve (AUC) was calculated to obtain the accuracy of the flood susceptibility maps prepared through success rates (using training data) and prediction rates (using validation data). The AUC results indicated that the EBF, EBF from LR, EBF-LR (enter), and EBF-LR (stepwise) success rates were 94.61%, 67.94%, 86.45%, and 56.31%, respectively, and the prediction rates were 94.55%, 66.41%, 83.19%, and 52.98%, respectively. The results showed that the EBF model had the highest accuracy in predicting flood susceptibility within the catchment, in which 15% of the total areas were located in high and very high susceptibility classes, and 62% were located in low and very low susceptibility classes. These results can be used for the planning and management of areas vulnerable to floods in order to prevent flood-induced damage; the results may also be useful for natural disaster assessment.

We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in the Sarkhoon watershed, Iran. We developed a new ensemble model which is a combination of a functional algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD model to predict the landslides. The model incorporates 20 landslide conditioning factors, which we ranked using the least-square support vector machine (LSSVM) technique. For the modeling, we considered 98 landslide locations, of which 70% (79) were used for training and 30% (19) for validation processes. Model validation was performed using sensitivity, specificity, accuracy, the root mean square error (RMSE) and the area under the receiver operatic characteristic (AUC) curve. We also used soft computing benchmark models, including SGD, logistic regression (LR), logistic model tree (LMT) and functional tree (FT) algorithms for model validation and comparison. The selected conditioning factors were significant in landslide occurrence but distance to road was found to be the most important factor. The ABSGD model (AUC= 0.860) outperformed the LR (0.797), SGD (0.776), LMT (0.740) and FT (0.734) models. Our results confirm that the combined use of a functional algorithm and a Meta classifier prevents over-fitting, reduces noise and enhances the power prediction of the individual SGD algorithm for the spatial prediction of landslides.

Landslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for the mitigation of the associated potential risks to local economic development, land use planning, and decision makers. The main aim of this study was to present a novel hybrid approach of bagging (B)-based kernel logistic regression (KLR), named the BKLR model, for spatial prediction of landslides in the Shangnan County, China. We first selected 15 conditioning factors for landslide susceptibility modeling. Then, the prediction capability of all conditioning factors was evaluated using the least square support vector machine method. Model validation and comparison were performed based on the area under the receiver operating characteristic curve and several statistical-based indexes, including positive predictive rate, negative predictive rate, sensitivity, specificity, kappa index, and root mean square error. Results indicated that the BKLR ensemble model outperformed and outclassed the KLR and the benchmark support vector machine model. Our findings overall confirmed that a combination of the meta model with a decision tree classifier based on a functional algorithm can decrease the over-fitting and variance problems of data, which could enhance the prediction power of the landslide model. The resultant susceptibility maps could be useful for hazard mitigation in the study area and other similar landslide-prone areas.

The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas.

In this study, land subsidence susceptibility was assessed for a study area in South Korea by using four machine learning models including Bayesian Logistic Regression (BLR), Support Vector Machine (SVM), Logistic Model Tree (LMT) and Alternate Decision Tree (ADTree). Eight conditioning factors were distinguished as the most important affecting factors on land subsidence of Jeong-am area, including slope angle, distance to drift, drift density, geology, distance to lineament, lineament density, land use and rock-mass rating (RMR) were applied to modelling. About 24 previously occurred land subsidence were surveyed and used as training dataset (70% of data) and validation dataset (30% of data) in the modelling process. Each studied model generated a land subsidence susceptibility map (LSSM). The maps were verified using several appropriate tools including statistical indices, the area under the receiver operating characteristic (AUROC) and success rate (SR) and prediction rate (PR) curves. The results of this study indicated that the BLR model produced LSSM with higher acceptable accuracy and reliability compared to the other applied models, even though the other models also had reasonable results.