Kamran Chapi

A novel hybrid artificial intelligence approach for flood susceptibility assessment

Abstract A new artificial intelligence (AI) model, called Bagging-LMT - a combination of bagging ensemble and Logistic Model Tree (LMT) - is introduced for mapping flood susceptibility. A spatial database was generated for the Haraz watershed, northern Iran, that included a flood inventory map and eleven flood conditioning factors based on the Information Gain Ratio (IGR). The model was evaluated using precision, sensitivity, specificity, accuracy, Root Mean Square Error, Mean Absolute Error, Kappa and area under the receiver operating characteristic curve criteria. The model was also compared with four state-of-the-art benchmark soft computing models, including LMT, logistic regression, Bayesian logistic regression, and random forest. Results revealed that the proposed model outperformed all these models and indicate that the proposed model can be used for sustainable management of flood-prone areas.

Flash flood susceptibility analysis and its mapping using different bivariate models in Iran: a comparison between Shannon’s entropy, statistical index, and weighting factor models

Flooding is a very common worldwide natural hazard causing large-scale casualties every year; Iran is not immune to this thread as well. Comprehensive flood susceptibility mapping is very important to reduce losses of lives and properties. Thus, the aim of this study is to map susceptibility to flooding by different bivariate statistical methods including Shannon’s entropy (SE), statistical index (SI), and weighting factor (Wf). In this regard, model performance evaluation is also carried out in Haraz Watershed, Mazandaran Province, Iran. In the first step, 211 flood locations were identified by the documentary sources and field inventories, of which 70% (151 positions) were used for flood susceptibility modeling and 30% (60 positions) for evaluation and verification of the model. In the second step, ten influential factors in flooding were chosen, namely slope angle, plan curvature, altitude, topographic wetness index (TWI), stream power index (SPI), distance from river, rainfall, geology, land use, and normalized difference vegetation index (NDVI). In the next step, flood susceptibility maps were prepared by these four methods in ArcGIS. As the last step, receiver operating characteristic (ROC) curve was drawn and the area under the curve (AUC) was calculated for quantitative assessment of each model. The results showed that the best model to estimate the susceptibility to flooding in Haraz Watershed was SI model with the prediction and success rates of 99.71 and 98.72%, respectively, followed by Wf and SE models with the AUC values of 98.1 and 96.57% for the success rate, and 97.6 and 92.42% for the prediction rate, respectively. In the SI and Wf models, the highest and lowest important parameters were the distance from river and geology. Flood susceptibility maps are informative for managers and decision makers in Haraz Watershed in order to contemplate measures to reduce human and financial losses.

A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran

Floods are one of the most damaging natural hazards causing huge loss of property, infrastructure and lives. Prediction of occurrence of flash flood locations is very difficult due to sudden change in climatic condition and manmade factors. However, prior identification of flood susceptible areas can be done with the help of machine learning techniques for proper timely management of flood hazards. In this study, we tested four decision trees based machine learning models namely Logistic Model Trees (LMT), Reduced Error Pruning Trees (REPT), Naïve Bayes Trees (NBT), and Alternating Decision Trees (ADT) for flash flood susceptibility mapping at the Haraz Watershed in the northern part of Iran. For this, a spatial database was constructed with 201 present and past flood locations and eleven flood-influencing factors namely ground slope, altitude, curvature, Stream Power Index (SPI), Topographic Wetness Index (TWI), land use, rainfall, river density, distance from river, lithology, and Normalized Difference Vegetation Index (NDVI). Statistical evaluation measures, the Receiver Operating Characteristic (ROC) curve, and Freidman and Wilcoxon signed-rank tests were used to validate and compare the prediction capability of the models. Results show that the ADT model has the highest prediction capability for flash flood susceptibility assessment, followed by the NBT, the LMT, and the REPT, respectively. These techniques have proven successful in quickly determining flood susceptible areas.

Novel forecasting approaches using combination of machine learning and statistical models for flood susceptibility mapping

In this research, eight individual machine learning and statistical models are implemented and compared, and based on their results, seven ensemble models for flood susceptibility assessment are introduced. The individual models included artificial neural networks, classification and regression trees, flexible discriminant analysis, generalized linear model, generalized additive model, boosted regression trees, multivariate adaptive regression splines, and maximum entropy, and the ensemble models were Ensemble Model committee averaging (EMca), Ensemble Model confidence interval Inferior (EMciInf), Ensemble Model confidence interval Superior (EMciSup), Ensemble Model to estimate the coefficient of variation (EMcv), Ensemble Model to estimate the mean (EMmean), Ensemble Model to estimate the median (EMmedian), and Ensemble Model based on weighted mean (EMwmean). The data set covered 201 flood events in the Haraz watershed (Mazandaran province in Iran) and 10,000 randomly selected non-occurrence points. Among the individual models, the Area Under the Receiver Operating Characteristic (AUROC), which showed the highest value, belonged to boosted regression trees (0.975) and the lowest value was recorded for generalized linear model (0.642). On the other hand, the proposed EMmedian resulted in the highest accuracy (0.976) among all models. In spite of the outstanding performance of some models, nevertheless, variability among the prediction of individual models was considerable. Therefore, to reduce uncertainty, creating more generalizable, more stable, and less sensitive models, ensemble forecasting approaches and in particular the EMmedian is recommended for flood susceptibility assessment.

Land Subsidence Susceptibility Mapping in South Korea Using Machine Learning Algorithms

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.

A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment

Abstract A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC = 0.930). However, RS model (AUROC = 0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC = 0.972), MB (AUROC = 0.970) and AB (AUROC = 0.957) models, respectively.

Non-point source contribution and dynamics of soluble and particulate phosphorus from main tributaries of the Zarivar Lake watershed, Iran

The temporal variability of phosphorus (P) transport and the relationships between discharge, suspended sediment concentration and particulate (PP), and soluble (SP) phosphorus were examined. The study was conducted at the event scale in seven tributaries of the Zarivar Lake watershed in Kurdistan Province (Iran) from March 2011 to April 2012. Based on eight runoff events, 82% of the total P was the PP carried out by suspended sediment. Results showed a high variability of P transport during different runoff events. It was found that soil erosion was the source of the high P load. For all tributaries, PP was linearly related to both discharge and suspended sediment concentration. However, the relationships of SP and PP with discharge and suspended sediment concentration showed different hysteresis patterns. The relationship between PP and discharge was generally characterized by a clockwise pattern (i.e., lower part contribution of the sub-watersheds) but the patterns between SP and discharge were mainly anticlockwise (i.e., upper part contribution of the sub-watersheds or perhaps due to a subsurface flow contribution).

Mapping Groundwater Potential Using a Novel Hybrid Intelligence Approach

Identifying areas with high groundwater potential is important for groundwater resources management. The main objective of this study is to propose a novel classifier ensemble method, namely Random Forest Classifier based on Random Subspace Ensemble (RS-RF), for groundwater potential mapping (GWPM) in Qorveh-Dehgolan plain, Kurdistan province, Iran. A total of 12 conditioning factors (slope, aspect, elevation, curvature, stream power index (SPI), topographic wetness index (TWI), rainfall, lithology, land use, normalized difference vegetation index (NDVI), fault density, and river density) were selected for groundwater modeling. The least square support vector machine (LSSVM) feature selection method with a 10-fold cross-validation technique was used to validate the predictive capability of these conditioning factors for training the models. The performance of the RS-RF model was validated using the area under receiver operating characteristic curve (AUROC), success and prediction rate curves, kappa index, and several statistical index-based measures. In addition, Friedman and Wilcoxon signed-rank tests were used to assess statistically significant level among the new model with the state-of-the-art soft computing benchmark models, such as random forest (RF), logistic regression (LR) and naïve Bayes (NB). Results showed that the new hybrid model of RS-RF had a very high predictive capability for groundwater potential mapping and exhibited the best performance among other benchmark models (LR, RF, and NB). Results of the present study might be useful to water managers to make proper decisions on the optimal use of groundwater resources for future planning in the critical study area.

Novel Hybrid Evolutionary Algorithms for Spatial Prediction of Floods

Adaptive neuro-fuzzy inference system (ANFIS) includes two novel GIS-based ensemble artificial intelligence approaches called imperialistic competitive algorithm (ICA) and firefly algorithm (FA). This combination could result in ANFIS-ICA and ANFIS-FA models, which were applied to flood spatial modelling and its mapping in the Haraz watershed in Northern Province of Mazandaran, Iran. Ten influential factors including slope angle, elevation, stream power index (SPI), curvature, topographic wetness index (TWI), lithology, rainfall, land use, stream density, and the distance to river were selected for flood modelling. The validity of the models was assessed using statistical error-indices (RMSE and MSE), statistical tests (Friedman and Wilcoxon signed-rank tests), and the area under the curve (AUC) of success. The prediction accuracy of the models was compared to some new state-of-the-art sophisticated machine learning techniques that had previously been successfully tested in the study area. The results confirmed the goodness of fit and appropriate prediction accuracy of the two ensemble models. However, the ANFIS-ICA model (AUC = 0.947) had a better performance in comparison to the Bagging-LMT (AUC = 0.940), BLR (AUC = 0.936), LMT (AUC = 0.934), ANFIS-FA (AUC = 0.917), LR (AUC = 0.885) and RF (AUC = 0.806) models. Therefore, the ANFIS-ICA model can be introduced as a promising method for the sustainable management of flood-prone areas.

A Novel Integrated Approach of Relevance Vector Machine Optimized by Imperialist Competitive Algorithm for Spatial Modeling of Shallow Landslides

This research aims at proposing a new artificial intelligence approach (namely RVM-ICA) which is based on the Relevance Vector Machine (RVM) and the Imperialist Competitive Algorithm (ICA) optimization for landslide susceptibility modeling. A Geographic Information System (GIS) spatial database was generated from Lang Son city in Lang Son province (Vietnam). This GIS database includes a landslide inventory map and fourteen landslide conditioning factors. The suitability of these factors for landslide susceptibility modeling in the study area was verified by the Information Gain Ratio (IGR) technique. A landslide susceptibility prediction model based on RVM-ICA and the GIS database was established by training and prediction phases. The predictive capability of the new approach was evaluated by calculations of sensitivity, specificity, accuracy, and the area under the Receiver Operating Characteristic curve (AUC). In addition, to assess the applicability of the proposed model, two state-of-the-art soft computing techniques including the support vector machine (SVM) and logistic regression (LR) were used as benchmark methods. The results of this study show that RVM-ICA with AUC = 0.92 achieved a high goodness-of-fit based on both the training and testing datasets. The predictive capability of RVM-ICA outperformed those of SVM with AUC = 0.91 and LR with AUC = 0.87. The experimental results confirm that the newly proposed model is a very promising alternative to assist planners and decision makers in the task of managing landslide prone areas.