A Novel Hybrid Swarm Optimized Multilayer Neural Network for Spatial Prediction of Flash Floods in Tropical Areas Using Sentinel-1 SAR Imagery and Geospatial Data

Flood susceptibility mapping using Sentinel 1 and frequency ratio technique in Jinjiram River watershed, India

Assam is one of the most flood-prone states in India, and the state frequently experiences catastrophic floods that cause significant damage in terms of loss of life and property. Flood susceptibility is considered the most essential and crucial input for managing floodplains and fostering local and regional development. This study focuses on the generation of flood susceptibility maps using the Frequency Ratio (FR) technique and microwave remote sensing inputs in the Jinjiram watershed which experienced disastrous flooding in 2020. The study has been carried out by taking into consideration of different morphological, lithological, and hydrological factors. In this study the flood inventory map was created by extracting the time series SAR (Synthetic Aperture Radar) Sentinel 1 GRD (Ground Range Detected) images of flooded areas for the past 5 years, from 2016 to 2020. A total of 72 inventory samples were identified of which 70% of total flooded samples were chosen for training and 30% for model testing at random basis. Applying these FR methods, the study determines a range of flood susceptibility which was then divided into five classes, from very low to very high. The Receiver Operating Characteristics (ROC) analysis was used to evaluate the accuracy of flood susceptibility maps generated using FR models. The AUC of ROC in flood susceptibility mapping is 0.81167 achieved, corresponding to a prediction accuracy of 81.17%. The findings can be used to calculate risk, develop flood control measures and infrastructural policies, and formulate sustainable water management policies for the watershed.

Using morphometric analysis for assessment of flash flood susceptibility in the Mediterranean region of Turkey

Flash floods are one of the most severe natural disasters around the world because of their rapid and unpredictable nature. It is expected that the frequency and intensity of flood events will increase because of extreme rainfall events induced by climate change. In this context, the generation of a flood susceptibility map contributes to effective flood management in a basin. The present study aims to generate a flash flood susceptibility map for the Imali Stream Basin (ISB) situated within the Mediterranean region of Turkey. For this purpose, morphometric analysis, geographic information system (GIS), remote sensing (RS), and principal component analysis (PCA) were used in this study. ASTER GDEM (v.3) was used to delineate 9 sub-watersheds and to obtain the required morphometric parameters. To generate a flash flood susceptibility map, the original compound values ​​calculated for each sub-watershed were transformed into values ​​between 0 and 1 by using the min-max normalization method. Then, these values were divided into 3 classes called low, moderate, and high by using the equal interval classification method in ArcGIS. According to both flash flood susceptibility maps produced by using morphometric analysis and PCA, sub-watershed 5 has the highest flash flood susceptibility in the basin. The flash flood that occurred in sub-watershed 5 in 2016 contributes to these results. Therefore, flood management based on morphometric analysis can be a highly effective method for decision-makers and planners in the Mediterranean region, one of the hotspots to be affected by climate change.

Flood sensitivity assessment of super cities

In the context of global urbanization, more and more people are attracted to these cities with superior geographical conditions and strategic positions, resulting in the emergence of world super cities. However, with the increasing of urban development, the underlying surface of the city has changed, the soil originally covered with vegetation has been substituted by hardened pavement such as asphalt and cement roads. Therefore, the infiltration capacity of urban rainwater is greatly limited, and waterlogging is becoming more and more serious. In addition, the suburbs of the main urban areas of super cities are usually villages and mountains, and frequent flash floods seriously threaten the life and property safety of people in there. Flood sensitivity assessment is an effective method to predict and mitigate flood disasters. Accordingly, this study aimed at identifying the areas vulnerable to flood by using Geographic Information System (GIS) and Remote Sensing (RS) and apply Logistic Regression (LR) model to create a flood sensitivity map of Beijing. 260 flood points in history and 12 predictors [elevation, slope, aspect, distance to rivers, Topographic Wetness Index (TWI), Stream Power Index (SPI), Sediment Transport Index (STI), curvature, plan curvature, Land Use/Land Cover (LULC), soil, and rainfall] were used in this study. Even more noteworthy is that most of the previous studies discussed flash flood and waterlogging separately. However, flash flood points and waterlogging points were included together in this study. We evaluated the sensitivity of flash flood and waterlogging as a whole and obtained different results from previous studies. In addition, most of the previous studies focused on a certain river basin or small towns as the study area. Beijing is the world's ninth largest super cities, which was unusual in previous studies and has important reference significance for the flood sensitivity analysis of other super cities. The flood inventory data were randomly subdivided into training (70%) and test (30%) sets for model construction and testing using the Area Under Curve (AUC), respectively. The results turn out that: (1) elevation, slope, rainfall, LULC, soil and TWI were highly important among these elements, and were the most influential variables in the assessment of flood sensitivity. (2) The AUC of the test dataset revealed a prediction rate of 81.0%. The AUC was greater than 0.8, indicating that the model assessment accuracy was high. (3) The proportion of high risk and extremely high risk areas was 27.44%, including 69.26% of the flood events in this study, indicating that the flood distribution in these areas was relatively dense and the susceptibility was high. Super cities have a high population density, and once flood disasters occur, the losses brought by them are immeasurable. Thus, flood sensitivity map can provide meaningful information for policy makers to enact appropriate policies to reduce future damage.

Spatial Prediction of Current and Future Flood Susceptibility: Examining the Implications of Changing Climates on Flood Susceptibility Using Machine Learning Models

The main aim of this study was to predict current and future flood susceptibility under three climate change scenarios of RCP2.6 (i.e., optimistic), RCP4.5 (i.e., business as usual), and RCP8.5 (i.e., pessimistic) employing four machine learning models, including Gradient Boosting Machine (GBM), Random Forest (RF), Multilayer Perceptron Neural Network (MLP-NN), and Naïve Bayes (NB). The study was conducted for two watersheds in Canada, namely Lower Nicola River, BC and Loup, QC. Three statistical metrics were used to validate the models: Receiver Operating Characteristic Curve, Figure of Merit, and F1-score. Findings indicated that the RF model had the highest accuracy in providing the flood susceptibility maps (FSMs). Moreover, the provided FSMs indicated that flooding is more likely to occur in the Lower Nicola River watershed than the Loup watershed. Following the RCP4.5 scenario, the area percentages of the flood susceptibility classes in the Loup watershed in 2050 and 2080 have changed by the following percentages from the year 2020 and 2050, respectively: Very Low = -1.68%, Low = -5.82%, Moderate = +6.19%, High = +0.71%, and Very High = +0.6% and Very Low = -1.61%, Low = +2.98%, Moderate = -3.49%, High = +1.29%, and Very High = +0.83%. Likewise, in the Lower Nicola River watershed, the changes between the years 2020 and 2050 and between the years 2050 and 2080 were: Very Low = -0.38%, Low = -0.81%, Moderate = -0.95%, High = +1.72%, and Very High = +0.42% and Very Low = -1.31%, Low = -1.35%, Moderate = -1.81%, High = +2.37%, and Very High = +2.1%, respectively. The impact of climate changes on future flood-prone places revealed that the regions designated as highly and very highly susceptible to flooding, grow in the forecasts for both watersheds. The main contribution of this study lies in the novel insights it provides concerning the flood susceptibility of watersheds in British Columbia and Quebec over time and under various climate change scenarios.

Likelihood of Transformation to Green Infrastructure Using Ensemble Machine Learning Techniques in Jinan, China

Rapid urbanization influences green infrastructure (GI) development in cities. The government plans to optimize GI in urban areas, which requires understanding GI spatiotemporal trends in urban areas and driving forces influencing their pattern. Traditional GIS-based methods, used to determine the greening potential of vacant land in urban areas, are incapable of predicting future scenarios based on the past trend. Therefore, we propose a heterogeneous ensemble technique to determine the spatial pattern of GI development in Jinan, China, based on driving biophysical and socioeconomic factors. Data-driven artificial neural networks (ANN) and random forests (RF) are selected as base learners, while support vector machine (SVM) is used as a meta classifier. Results showed that the stacking model ANN-RF-SVM achieved the best test accuracy (AUC 0.941) compared to the individual ANN, RF, and SVM algorithms. Land surface temperature, distance to water bodies, population density, and rainfall are found to be the most influencing factors regarding vacant land conversion to GI in Jinan.

Hybrid Models Incorporating Bivariate Statistics and Machine Learning Methods for Flash Flood Susceptibility Assessment Based on Remote Sensing Datasets

Flash floods are considered to be one of the most destructive natural hazards, and they are difficult to accurately model and predict. In this study, three hybrid models were proposed, evaluated, and used for flood susceptibility prediction in the Dadu River Basin. These three hybrid models integrate a bivariate statistical method of the fuzzy membership value (FMV) and three machine learning methods of support vector machine (SVM), classification and regression trees (CART), and convolutional neural network (CNN). Firstly, a geospatial database was prepared comprising nine flood conditioning factors, 485 flood locations, and 485 non-flood locations. Then, the database was used to train and test the three hybrid models. Subsequently, the receiver operating characteristic (ROC) curve, seed cell area index (SCAI), and classification accuracy were used to evaluate the performances of the models. The results reveal the following: (1) The ROC curve highlights the fact that the CNN-FMV hybrid model had the best fitting and prediction performance, and the area under the curve (AUC) values of the success rate and the prediction rate were 0.935 and 0.912, respectively. (2) Based on the results of the three model performance evaluation methods, all three hybrid models had better prediction capabilities than their respective single machine learning models. Compared with their single machine learning models, the AUC values of the SVM-FMV, CART-FMV, and CNN-FMV were 0.032, 0.005, and 0.055 higher; their SCAI values were 0.05, 0.03, and 0.02 lower; and their classification accuracies were 4.48%, 1.38%, and 5.86% higher, respectively. (3) Based on the results of the flood susceptibility indices, between 13.21% and 22.03% of the study area was characterized by high and very high flood susceptibilities. The three hybrid models proposed in this study, especially CNN-FMV, have a high potential for application in flood susceptibility assessment in specific areas in future studies.

Synergistic Use of Geospatial Data for Water Body Extraction from Sentinel-1 Images for Operational Flood Monitoring across Southeast Asia Using Deep Neural Networks

Deep learning is a promising method for image classification, including satellite images acquired by various sensors. However, the synergistic use of geospatial data for water body extraction from Sentinel-1 data using deep learning and the applicability of existing deep learning models have not been thoroughly tested for operational flood monitoring. Here, we present a novel water body extraction model based on a deep neural network that exploits Sentinel-1 data and flood-related geospatial datasets. For the model, the U-Net was customised and optimised to utilise Sentinel-1 data and other flood-related geospatial data, including digital elevation model (DEM), Slope, Aspect, Profile Curvature (PC), Topographic Wetness Index (TWI), Terrain Ruggedness Index (TRI), and Buffer for the Southeast Asia region. Testing and validation of the water body extraction model was applied to three Sentinel-1 images for Vietnam, Myanmar, and Bangladesh. By segmenting 384 Sentinel-1 images, model performance and segmentation accuracy for all of the 128 cases that the combination of stacked layers had determined were evaluated following the types of combined input layers. Of the 128 cases, 31 cases showed improvement in Overall Accuracy (OA), and 19 cases showed improvement in both averaged intersection over union (IOU) and F1 score for the three Sentinel-1 images segmented for water body extraction. The averaged OA, IOU, and F1 scores of the ‘Sentinel-1 VV’ band are 95.77, 80.35, and 88.85, respectively, whereas those of ‘band combination VV, Slope, PC, and TRI’ are 96.73, 85.42, and 92.08, showing improvement by exploiting geospatial data. Such improvement was further verified with water body extraction results for the Chindwin river basin, and quantitative analysis of ‘band combination VV, Slope, PC, and TRI’ showed an improvement of the F1 score by 7.68 percent compared to the segmentation output of the ‘Sentinel-1 VV’ band. Through this research, it was demonstrated that the accuracy of deep learning-based water body extraction from Sentinel-1 images can be improved up to 7.68 percent by employing geospatial data. To the best of our knowledge, this is the first work of research that demonstrates the synergistic use of geospatial data in deep learning-based water body extraction over wide areas. It is anticipated that the results of this research could be a valuable reference when deep neural networks are applied for satellite image segmentation for operational flood monitoring and when geospatial layers are employed to improve the accuracy of deep learning-based image segmentation.

Flood susceptibility mapping by integrating frequency ratio and index of entropy with multilayer perceptron and classification and regression tree

Episodes of frequent flooding continue to increase, often causing serious damage and tools to identify areas affected by such disasters have become indispensable in today's society. Using the latest techniques can make very accurate flood predictions. In this study, we introduce four effective methods to evaluate the flood susceptibility of Poyang County, in China, by integrating two independent models of frequency ratio and index of entropy with multilayer perceptron and classification and regression tree models. The flood locations of the study area were identified through the flood inventory process, and 12 flood conditioning factors were used in the training and validation processes. According to the results of the linear support vector machine, elevation, slope angle, and soil have the highest predictive ability. The experimental results of the four hybrid models demonstrate that between 20% and 50% of the study area has high and very high flood susceptibility. The multilayer perceptron-probability density hybrid model is the most effective among the six comparative methods.

Automatic Impervious Surface Area Detection Using Image Texture Analysis and Neural Computing Models with Advanced Optimizers

Up-to-date information regarding impervious surface is valuable for urban planning and management. The objective of this study is to develop neural computing models used for automatic impervious surface area detection at a regional scale. To achieve this task, advanced optimizers of adaptive moment estimation (Adam), a variation of Adam called Adamax, Nesterov-accelerated adaptive moment estimation (Nadam), Adam with decoupled weight decay (AdamW), and a new exponential moving average variant (AMSGrad) are used to train the artificial neural network models employed for impervious surface detection. These advanced optimizers are benchmarked with the conventional gradient descent with momentum (GDM). Remotely sensed images collected from Sentinel-2 satellite for the study area of Da Nang city (Vietnam) are used to construct and verify the proposed approach. Moreover, texture descriptors including statistical measurements of color channels and binary gradient contour are employed to extract useful features for the neural computing model-based pattern recognition. Experimental result supported by statistical test points out that the Nadam optimizer-based neural computing model has achieved the most desired predictive accuracy for the data collected in the studied region with classification accuracy rate of 97.331%, precision = 0.961, recall = 0.984, negative predictive value = 0.985, and F1 score = 0.972. Therefore, the model developed in this study can be a helpful tool for decision-makers in the task of urban land-use planning and management.

A new hybrid equilibrium optimized SysFor based geospatial data mining for tropical storm-induced flash flood susceptible mapping

Flash flood is one of the most dangerous hydrologic and natural phenomena and is considered as the top ranking of such events among various natural disasters due to their fast onset characteristics and the proportion of individual fatalities. Mapping the probability of flash flood events remains challenges because of its complexity and rapid onset of precipitation. Thus, this study aims to propose a state-of-the-art data mining approach based on a hybrid equilibrium optimized SysFor, namely, the HE-SysFor model, for spatial prediction of flash floods. A tropical storm region located in the Northwest areas of Vietnam is selected as a case study. For this purpose, 1866 flash-flooded locations and ten indicators were used. The results show that the proposed HE-SysFor model yielded the highest predictive performance (total accuracy = 93.8%, Kappa index = 0.875, F1-score = 0.939, and AUC = 0.975) and produced the better performance than those of the C4.5 decision tree (C4.5), the radial basis function-based support vector machine (SVM-RBF), the logistic regression (LReg), and deep learning neural network (DeepLNN) models in both the training and the testing phases. Among the ten indicators, elevation, slope, and land cover are the most important. It is concluded that the proposed model provides an alternative tool and may help for effectively monitoring flash floods in tropical areas and robust policies for decision making in mitigating the flash flood impacts.

An Overview of Flood Risk Analysis Methods

Scientific papers present a wide range of methods of flood analysis and forecasting. Floods are a phenomenon with significant socio-economic implications, for which many researchers try to identify the most appropriate methodologies to analyze their temporal and spatial development. This research aims to create an overview of flood analysis and forecasting methods. The study is based on the need to select and group papers into well-defined methodological categories. The article provides an overview of recent developments in the analysis of flood methodologies and shows current research directions based on this overview. The study was performed taking into account the information included in the Web of Science Core Collection, which brought together 1326 articles. The research concludes with a discussion on the relevance, ease of application, and usefulness of the methodologies.

Predicting flood insurance claims with hydrologic and socioeconomic demographics via machine learning: Exploring the roles of topography, minority populations, and political dissimilarity

Current research on flooding risk often focuses on understanding hazards, de-emphasizing the complex pathways of exposure and vulnerability. We investigated the use of both hydrologic and social demographic data for flood exposure mapping with Random Forest (RF) regression and classification algorithms trained to predict both parcel- and tract-level flood insurance claims within New York State, US. Topographic characteristics best described flood claim frequency, but RF prediction skill was improved at both spatial scales when socioeconomic data was incorporated. Substantial improvements occurred at the tract-level when the percentage of minority residents, housing stock value and age, and the political dissimilarity index of voting precincts were used to predict insurance claims. Census tracts with higher numbers of claims and greater densities of low-lying tax parcels tended to have low proportions of minority residents, newer houses, and less political similarity to state level government. We compared this data-driven approach and a physically-based pluvial flood routing model for prediction of the spatial extents of flooding claims in two nearby catchments of differing land use. The floodplain we defined with physically based modeling agreed well with existing federal flood insurance rate maps, but underestimated the spatial extents of historical claim generating areas. In contrast, RF classification incorporating hydrologic and socioeconomic demographic data likely overestimated the flood-exposed areas. Our research indicates that quantitative incorporation of social data can improve flooding exposure estimates.

A New Hybrid Firefly–PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping

Flash flood is one of the most dangerous natural phenomena because of its high magnitudes and sudden occurrence, resulting in huge damages for people and properties. Our work aims to propose a state-of-the-art model for susceptibility mapping of the flash flood using the decision tree random subspace ensemble optimized by hybrid firefly–particle swarm optimization (HFPS), namely the HFPS-RSTree model. In this work, we used data from a flood inventory map consisting of 1866 polygons derived from Sentinel-1 C-band synthetic aperture radar (SAR) data and a field survey conducted in the northwest mountainous area of the Van Ban district, Lao Cai Province in Vietnam. A total of eleven flooding conditioning factors (soil type, geology, rainfall, river density, elevation, slope, aspect, topographic wetness index (TWI), normalized difference vegetation index (NDVI), plant curvature, and profile curvature) were used as explanatory variables. These indicators were compiled from a geological and mineral resources map, soil type map, and topographic map, ALOS PALSAR DEM 30 m, and Landsat-8 imagery. The HFPS-RSTree model was trained and verified using the inventory map and the eleven conditioning variables and then compared with four machine learning algorithms, i.e., the support vector machine (SVM), the random forests (RF), the C4.5 decision trees (C4.5 DT), and the logistic model trees (LMT) models. We employed a range of statistical standard metrics to assess the predictive performance of the proposed model. The results show that the HFPS-RSTree model had the best predictive performance and achieved better results than those of other benchmarks with the ability to predict flash flood, reaching an overall accuracy of over 90%. It can be concluded that the proposed approach provides new insights into flash flood prediction in mountainous regions.

Novel hybrid models between bivariate statistics, artificial neural networks and boosting algorithms for flood susceptibility assessment

Across the world, the flood magnitude is expected to increase as well as the damage caused by their occurrence. In this case, the prediction of areas which are highly susceptible to these phenomena becomes very important for the authorities. The present study is focused on the evaluation of flood potential within Trotuș river basin in Romania using six ensemble models created by the combination of Analytical Hierarchy Process (AHP), Certainty Factor (CF) and Weights of Evidence (WOE) on one hand, and Gradient Boosting Trees (GBT) and Multilayer Perceptron (MLP) on the other hand. A number of 12 flood predictors, 172 flood locations and 172 non-flood locations were used. A percentage of 70% of flood and non-flood locations were used as input in models. From the input data, 70% were used as training sample and 30% as validating sample. The highest accuracy was obtained by the MLP-CF model in terms of both training (0.899) and testing (0.889) samples. A percentage between 21.88% and 36.33% of study area is covered with high and very high flood potential. The results validation, performed through the ROC Curve method, highlights that the MLP-CF model provided the most accurate results.

Using GIS, Remote Sensing, and Machine Learning to Highlight the Correlation between the Land-Use/Land-Cover Changes and Flash-Flood Potential

The aim of the present study was to explore the correlation between the land-use/land cover change and the flash-flood potential changes in Zăbala catchment (Romania) between 1989 and 2019. In this regard, the efficiency of GIS, remote sensing and machine learning techniques in detecting spatial patterns of the relationship between the two variables was tested. The paper elaborated upon an answer to the increase in flash flooding frequency across the study area and across the earth due to the occurred land-use/land-cover changes, as well as due to the present climate change, which determined the multiplication of extreme meteorological phenomena. In order to reach the above-mentioned purpose, two land-uses/land-covers (for 1989 and 2019) were obtained using Landsat image processing and were included in a relative evolution indicator (total relative difference-synthetic dynamic land-use index), aggregated at a grid-cell level of 1 km2. The assessment of runoff potential was made with a multilayer perceptron (MLP) neural network, which was trained for 1989 and 2019 with the help of 10 flash-flood predictors, 127 flash-flood locations, and 127 non-flash-flood locations. For the year 1989, the high and very high surface runoff potential covered around 34% of the study area, while for 2019, the same values accounted for approximately 46%. The MLP models performed very well, the area under curve (AUC) values being higher than 0.837. Finally, the land-use/land-cover change indicator, as well as the relative evolution of the flash flood potential index, was included in a geographically weighted regression (GWR). The results of the GWR highlights that high values of the Pearson coefficient (r) occupied around 17.4% of the study area. Therefore, in these areas of the Zăbala river catchment, the land-use/land-cover changes were highly correlated with the changes that occurred in flash-flood potential.

A New Modeling Approach for Spatial Prediction of Flash Flood with Biogeography Optimized CHAID Tree Ensemble and Remote Sensing Data

Flash floods induced by torrential rainfalls are considered one of the most dangerous natural hazards, due to their sudden occurrence and high magnitudes, which may cause huge damage to people and properties. This study proposed a novel modeling approach for spatial prediction of flash floods based on the tree intelligence-based CHAID (Chi-square Automatic Interaction Detector)random subspace, optimized by biogeography-based optimization (the CHAID-RS-BBO model), using remote sensing and geospatial data. In this proposed approach, a forest of tree intelligence was constructed through the random subspace ensemble, and, then, the swarm intelligence was employed to train and optimize the model. The Luc Yen district, located in the northwest mountainous area of Vietnam, was selected as a case study. For this circumstance, a flood inventory map with 1866 polygons for the district was prepared based on Sentinel-1 synthetic aperture radar (SAR) imagery and field surveys with handheld GPS. Then, a geospatial database with ten influencing variables (land use/land cover, soil type, lithology, river density, rainfall, topographic wetness index, elevation, slope, curvature, and aspect) was prepared. Using the inventory map and the ten explanatory variables, the CHAID-RS-BBO model was trained and verified. Various statistical metrics were used to assess the prediction capability of the proposed model. The results show that the proposed CHAID-RS-BBO model yielded the highest predictive performance, with an overall accuracy of 90% in predicting flash floods, and outperformed benchmarks (i.e., the CHAID, the J48-DT, the logistic regression, and the multilayer perception neural network (MLP-NN) models). We conclude that the proposed method can accurately estimate the spatial prediction of flash floods in tropical storm areas.

A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area

This research proposes and evaluates a new approach for flash flood susceptibility mapping based on Deep Learning Neural Network (DLNN)) algorithm, with a case study at a high-frequency tropical storm area in the northwest mountainous region of Vietnam. Accordingly, a DLNN structure with 192 neurons in 3 hidden layers was proposed to construct an inference model that predicts different levels of susceptibility to flash flood. The Rectified Linear Unit (ReLU) and the sigmoid were selected as the activate function and the transfer function, respectively, whereas the Adaptive moment estimation (Adam) was used to update and optimize the weights of the DLNN. A database for the study area, which includes factors of elevation, slope, curvature, aspect, stream density, NDVI, soil type, lithology, and rainfall, was established to train and validate the proposed model. Feature selection was carried out for these factors using the Information gain ratio. The results show that the DLNN attains a good prediction accuracy with Classification Accuracy Rate = 92.05%, Positive Predictive Value = 94.55% and Negative Predictive Value = 89.55%. Compared to benchmarks, Multilayer Perceptron Neural Network and Support Vector Machine, the DLNN performs better; therefore, it could be concluded that the proposed hybridization of GIS and deep learning can be a promising tool to assist the government authorities and involving parties in flash flood mitigation and land-use planning.

Spatial prediction of flood potential using new ensembles of bivariate statistics and artificial intelligence: A case study at the Putna river catchment of Romania

Flash-flood is considered to be one of the most destructive natural hazards in the world, which is difficult to accurately model and predict. The objective of the present research is to propose new ensembles of bivariate statistics and artificial intelligences and to introduce a comprehensive methodology for predicting flood susceptibility. The Putna river catchment of Romania is selected as a case study. In this regard, a total of six ensemble models were proposed and verified: Multilayer Perceptron neural network-Frequency Ratio (MLP-FR), Multilayer Perceptron neural network -Weights of Evidence (MLP-WOE), Rotation Forest-Frequency Ratio (RF-FR), Rotation Forest-Weights of Evidence (RF-WOE), Classification and Regression Tree-Frequency Ratio (CART-FR), and Classification and Regression Tree-Weights of Evidence (CART-WOE). In a first step, a geospatial database was created for the study area. This database includes 132 flood locations and 14 conditioning factors (lithology, slope angle, plan curvature, hydrological soil group, topographic wetness index, landuse, convergence index, elevation, distance from river, profile curvature, rainfall, aspect, stream power index, and topographic position index). In the next step, the Information Gain Ratio was used to evaluate the predictive ability of these factors. Subsequently, the database was used to train and validate the six ensemble models. The Receiver operating characteristic (ROC) curve, area under the curve (AUC), and statistical measures were used to evaluate the performance of the models. The results show that the prediction capability of the proposed ensemble models varied from 86.8% (the RF-FR model) to 93.9% (the RF-WOE model). These values indicate a high prediction performance for all the models. Therefore, we can state that the proposed ensemble models are new reliable tools which can be used for flood susceptibility modelling.

A New Approach of Hybrid Bee Colony Optimized Neural Computing to Estimate the Soil Compression Coefficient for a Housing Construction Project

In the design phase of housing projects, predicting the settlement of soil layers beneath the buildings requires the estimation of the coefficient of soil compression. This study proposes a low-cost, fast, and reliable alternative for estimating this soil parameter utilizing a hybrid metaheuristic optimized neural network (NN). An integrated method of artificial bee colony (ABC) and the Levenberg–Marquardt (LM) algorithm is put forward to train the NN inference model. The model is capable of delivering the response variable of soil compression coefficient a set of physical properties of soil. A large-scale real-life urban project at Hai Phong city (Vietnam) was selected as a case study. Accordingly, a dataset of 441 samples with their corresponding testing values of the compression coefficient has been collected and prepared during the construction phase. Experimental outcomes confirm that the proposed NN model with the hybrid ABC-LM training algorithm has attained the highly accurate estimation of the soil compression coefficient with root mean square error (RMSE) = 0.008, mean absolute percentage error (MAPE) = 10.180%, and coefficient of determination (R2) = 0.864. Thus, the proposed machine learning method can be a promising tool for geotechnical engineers in the design phase of housing projects.

The Feasibility of Three Prediction Techniques of the Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System, and Hybrid Particle Swarm Optimization for Assessing the Safety Factor of Cohesive Slopes

In this paper, a neuro particle-based optimization of the artificial neural network (ANN) is investigated for slope stability calculation. The results are also compared to another artificial intelligence technique of a conventional ANN and adaptive neuro-fuzzy inference system (ANFIS) training solutions. The database used with 504 training datasets (e.g., a range of 80%) and testing dataset consists of 126 items (e.g., 20% of the whole dataset). Moreover, variables of the ANN method (for example, nodes number for each hidden layer) and the algorithm of PSO-like swarm size and inertia weight are improved by utilizing a total of 28 (i.e., for the PSO-ANN) trial and error approaches. The key properties were fed as input, which were utilized via the analysis of OptumG2 finite element modelling (FEM), containing undrained cohesion stability of the baseline soil (Cu), angle of the original slope (β), and setback distance ratio (b/B) where the target is selected factor of safety. The estimated data for datasets of ANN, ANFIS, and PSO-ANN models were examined based on three determined statistical indexes. Namely, root mean square error (RMSE) and the coefficient of determination (R2). After accomplishing the analysis of sensitivity, considering 72 trials and errors of the neurons number, the optimized architecture of 4 × 6 × 1 was determined to the structure of the ANN model. As an outcome, the employed methods presented excellent efficiency, but based on the ranking method, the PSO-ANN approach might have slightly better efficiency in comparison to the algorithms of ANN and ANFIS. According to statistics, for the proper structure of PSO-ANN, the indexes of R2 and RMSE values of 0.9996, and 0.0123, as well as 0.9994 and 0.0157, were calculated for the training and testing networks. Nevertheless, having the ANN model with six neurons for each hidden layer was formulized for further practical use. This study demonstrates the efficiency of the proposed neuro model of PSO-ANN in estimating the factor of safety compared to other conventional techniques.

Image Processing-Based Detection of Pipe Corrosion Using Texture Analysis and Metaheuristic-Optimized Machine Learning Approach

To maintain the serviceability of buildings, the owners need to be informed about the current condition of the water supply and waste disposal systems. Therefore, timely and accurate detection of corrosion on pipe surface is a crucial task. The conventional manual surveying process performed by human inspectors is notoriously time consuming and labor intensive. Hence, this study proposes an image processing-based method for automating the task of pipe corrosion detection. Image texture including statistical measurement of image colors, gray-level co-occurrence matrix, and gray-level run length is employed to extract features of pipe surface. Support vector machine optimized by differential flower pollination is then used to construct a decision boundary that can recognize corroded and intact pipe surfaces. A dataset consisting of 2000 image samples has been collected and utilized to train and test the proposed hybrid model. Experimental results supported by the Wilcoxon signed-rank test confirm that the proposed method is highly suitable for the task of interest with an accuracy rate of 92.81%. Thus, the model proposed in this study can be a promising tool to assist building maintenance agents during the phase of pipe system survey.

Flash flood susceptibility modeling using an optimized fuzzy rule based feature selection technique and tree based ensemble methods

The main objective of the present study was to provide a novel methodological approach for flash flood susceptibility modeling based on a feature selection method (FSM) and tree based ensemble methods. The FSM, used a fuzzy rule based algorithm FURIA, as attribute evaluator, whereas GA were used as the search method, in order to obtain optimal set of variables used in flood susceptibility modeling assessments. The novel FURIA-GA was combined with LogitBoost, Bagging and AdaBoost ensemble algorithms. The performance of the developed methodology was evaluated at the Bao Yen district and the Bac Ha district of Lao Cai Province in the Northeast region of Vietnam. For the case study, 654 floods and twelve geo-environmental variables were used. The predictive performance of each model was estimated through the calculation of the classification accuracy, the sensitivity, the specificity, the success and predictive rate curve and the area under the curves (AUC). The FURIA-GA FSM compared to a conventional rule based method gave more accurate predictive results. Also, the FURIA-GA based models, presented higher learning and predictive ability compared to the ensemble models that had not undergone a FSM. Based on the predictive classification accuracy, FURIA-GA-Bagging (93.37%) outperformed FURIA-GA-LogitBoost (92.35%) and FURIA-GA-AdaBoost (89.03%). FURIA-GA-Bagging showed also the highest sensitivity (96.94%) and specificity (89.80%). On the other hand, the FURIA-GA-LogitBoost showed the lowest percentage in very high susceptible zone and the highest relative flash-flood density, whereas the FURIA-GA-AdaBoost achieved the highest prediction AUC value (0.9740), based on the prediction rate curve, followed by FURIA-GA-Bagging (0.9566), and FURIA-GA-LogitBoost (0.8955). It can be concluded that the usage of different statistical metrics, provides different outcomes concerning the best prediction model, which mainly could be attributed to sites specific settings. The proposed models could be considered as a novel alternative investigation tools appropriate for flash flood susceptibility mapping.