Detection of areas prone to flood risk using state-of-the-art machine learning models

Abstract

The present study aims to evaluate the susceptibility to floods in the river basin of Buzau in Romania through the following 6 machine learning models: Support Vector Machine (SVM), J48 decision tree, Adaptive Neuro-Fuzzy Inference System (ANFIS), Random Forest (RF), Artificial Neural Network (ANN) and Alternating Decision Tree (ADT). In the first stage of the study, an inventory of the areas affected by floods was made in the study area, and a number of 205 flood points were identified. Further, 12 flood predictors were selected to be used for final susceptibility mapping. The six models' training was performed by using 70% of the total flood points that have been associated with the values of flood predictors. The highest accuracy (0.973) was obtained by the RF model, while J48 had the lowest performance (0.825). Besides, by classifying flood predictors' values in flood and non-flood pixels, the six flood susceptibility maps were made. High and very high flood susceptibility values cover between 17.71% (MLP) and 27.93% (ANFIS) of the study area. The validation of the results, performed using the ROC Curve, shows that the most accurate flood susceptibility values are also assigned to the RF model (AUC ¼ 0.996).

Spatial Analysis of Flood Hazard Zoning Map Using Novel Hybrid Machine Learning Technique in Assam, India

“…The result of the Boruta method found that fourteen factors were the most important (Rank 1) for the current study, namely, elevation, landform, soil moisture, slope, TRI, LULC, NDVI, NDFI, distance to stream, rainfall, population density, GHMTS, distance to road, and geology (Figure 4a). In contrast, SPI, TWI, and soil erosion had a moderate (Rank 2) influence on flood events, whereas drainage density, profile curvature, TPI, soil type, and aspect had the least importance (Ranks 3, 4, 5, 6, and 7) for FHZ [19].…”

“…The machine learning (ML) technique is a type of artificial intelligence where prediction is more accurate by using historical data and records. FHZ mapping can be enriched by using various machine learning models, namely, random forest [15], support vector machine [16], extreme gradient boosting [17], classification and regression tree [18], alternating decision tree [19], optimized tree [20], artificial neural network [21], naïve Bayes [22], genetic algorithm rule-set production [23], Bayesian additive regression tree [24], grid search algorithm [25], logistic regression [26], etc. Recently, the novel ensemble-based machine learning (ML) technique was utilized for parallel high computing performance of flood risk zone mapping on a real-time basis.…”

Novel Hybrid Models by Coupling Support Vector Regression (SVR) With Meta-heuristic Algorithms (WOA and GWO) for Urban Flood Risk Mapping

“…To overcome such problems, machine learning (ML) techniques (e.g., group method of data handling (GMDH), artificial neural networks (ANNs), Naïve Bayes Trees (NBT), support vector regression (SVR), and random forest (RF)) have been posed in the literature (Band et al, 2020;Costache et al, 2021;Dodangeh et al, 2020;Khoirunisa et al, 2021;Khosravi et al, 2018). However, machine learning techniques also suffer from strict parameters tuning procedure which is time-consuming for modelers (Chen et al, 2019(Chen et al, , 2017.…”

Evaluating the performance of flood susceptibility through novel hybrid machine learning approach in tropical plateau basin, India

“…As the amount of flood organization is much higher in the plains and floodplain areas, methods and statistics on flood vulnerability, risk analysis, and mapping are essential to analyze the flood susceptible character of those areas. These methods include Analytical Hierarchy Process (AHP) (Goumrasa et al 2021) as an expert knowledge-based model, Frequency ratio (FR) (Sarkar and Mondal 2020), Information value (IV) (Ul Moazzam et al 2020), Certainly factor (CF) (Cao et al 2020), Logistic regression (LR) (Fustos et al 2017), Weights ofevidence (WOE) (Tehrany et al 2017), fuzzy logic (Perera and Lahat 2015), neuro-fuzzy logic (Kambalimath and Deka 2020) as expert-based models; Artificial neural network (ANN) (Pham et al 2020), Adaptive neuro-fuzz inference system (ANFIS) (Samantaray et al 2021), Decision tree (DT) (Khosravi et al 2021), Support vector machine (SVM) (Costache et al 2021), Random Forest (RF) (Chen et al 2020) as a machine learning model. Hydraulic engineering centre-river analysis system (HEC-RAS) (Namara et al 2021) and soil water assessment tool (SWAT) (Nasir et al 2020) models are also used as hydrological models for determining flood vulnerability and risk.…”

“…ML-based models can accurately measure the nature and severity of other natural disasters, including flood susceptibility (Bui et al 2020;Rahaman et al 2019). Popular ML models for determining flood susceptibility in an area are Artificial neural network (ANN) (Pham et al 2020), Adaptive neuro-fuzz inference system (ANFIS) (Samantaray et al 2021), Decision tree (DT) (Khosravi et al 2021), Support vector machine (SVM) (Costache et al 2021), Random Forest (RF) (Chen et al 2020) and Extreme gradient boosting (XGBoost) (Ni et al 2020). These methods give an accurate idea of the future flooding of a region.…”