Towards better flood risk management: Assessing flood risk and investigating the potential mechanism based on machine learning models

A comparative study on urban waterlogging susceptibility assessment based on multiple data-driven models

Accurate identification of urban waterlogging areas and assessing waterlogging susceptibility are crucial for preventing and controlling hazards. Data-driven models are utilized to forecast waterlogging areas by establishing intricate relationships between explanatory variables and waterlogging states. This approach tackles the constraints of mechanistic models, which are frequently complex and unable to incorporate socio-economic factors. Previous research predominantly employed single-type data-driven models to predict waterlogging locations and evaluation of their effectiveness. There is a scarcity of comprehensive performance comparisons and uncertainty analyses of different types of models, as well as a lack of interpretability analysis. The chosen study area was the central area of Beijing, which is prone to waterlogging. Given the high manpower, time, and economic costs associated with collecting waterlogging information, the waterlogging point distribution map released by the Beijing Water Affairs Bureau was selected as labeled samples. Twelve factors affecting waterlogging susceptibility were chosen as explanatory variables to construct Random Forest (RF), Support Vector Machine with Radial Basis Function (SVM-RBF), Particle Swarm Optimization-Weakly Labeled Support Vector Machine (PSO-WELLSVM), and Maximum Entropy (MaxEnt). The utilization of diverse single evaluation indicators (such as F-score, Kappa, AUC, etc.) to assess the model performance may yield conflicting results. The Distance between Indices of Simulation and Observation (DISO) was chosen as a comprehensive measure to assess the model's performance in predicting waterlogging points. PSO-WELLSVM exhibited the highest performance with a DISOtest value of 0.63, outperforming MaxEnt (0.78), which excelled in identifying areas highly susceptible to waterlogging, including extremely high susceptibility zones. The SVM-RBF and RF models demonstrated suboptimal performance and exhibited overfitting. The examination of waterlogging susceptibility distribution maps predicted by the four models revealed significant spatial differences due to variations in computational principles and input parameter complexities. The integration of four WSAMs based on logistic regression has been shown to significantly decrease the uncertainty of a single data-driven model and identify the most flood-prone areas. To improve the interpretability of the data model, a geographical detector was incorporated to demonstrate the explanatory capacity of 12 variables and the process of waterlogging. Building Density (BD) exhibits the highest explanatory power in relation to explain waterlogging susceptibility (Q value = 0.202), followed by Distance to Road, Frequency of Heavy Rainstorms (FHR), DEM, etc. The interaction between BD and FHR results in a nonlinear increase in the explanatory power of waterlogging susceptibility. The presence of waterlogging susceptibility risk in the research area can be attributed to the interactions of multiple factors.

Efficiency evaluation of low impact development practices on urban flood risk

Urban flood risk assessment delivers invaluable information regarding flood management as well as preventing the associated risks in urban areas. The present study prepares a flood risk map and evaluate the practices of low-impact development (LID) intended to decrease the flood risk in Shiraz Municipal District 4, Fars province, Iran. So, this study investigate flood vulnerability using MCDM models and some indices, including population density, building age, socio-economic conditions, floor area ratio, literacy, the elderly population, and the number of building floors to. Then, the map of thematic layers affecting the urban flood hazard, including annual mean rainfall, land use, elevation, slope percentage, curve number, distance from channel, depth of groundwater, and channel density, was prepared in GIS. After conducting a multicollinearity test, data mining models were used to create the urban flood hazard map, and the urban flood risk map was produced using ArcGIS 10.8. The evaluation of vulnerability models was shown through the use of Boolean logic that TOPSIS and VIKOR models were effective in identifying urban flooding vulnerable areas. Data mining models were also evaluated using ROC and precision-recall curves, indicating the accuracy of the RF model. The importance of input variables was measured using Shapley value, which showed that curve number, land use, and elevation were more important in flood hazard modeling. According to the results, 37.8 percent of the area falls into high and very high categories in terms of flooding risk. The study used a stormwater management model (SWMM) to simulate node flooding and provide management scenarios for rainfall events with a return period ranging from 2 to 50 years and five rainstorm events. The use of LID practices in flood management was found to be effective for rainfall events with a return period of less than 10 years, particularly for two-year events. However, the effectiveness of LID practices decreases with an increase in the return period. By applying a combined approach to a region covering approximately 10 percent of the total area of Shiraz Municipal District 4, a reduction of 2-22.8 percent in node flooding was achieved. The analysis of data mining and MCDM models with a physical model revealed that more than 60% of flooded nodes were classified as "high" and "very high" risk categories in the RF-VIKOR and RF-TOPSIS risk models.

Flood economic vulnerability and risk assessment at the urban mesoscale based on land use: A case study in Changsha, China

With climate change and urbanization, flood disasters have significantly affected urban development worldwide. In this study, we developed a paradigm to assess flood economic vulnerability and risk at the urban mesoscale, focusing on urban land use. A hydrological simulation was used to evaluate flood hazards through inundation analyses, and a hazard-vulnerability matrix was applied to assess flood risk, enhancing the economic vulnerability assessment by quantifying the differing economic value and flood losses associated with different land types. The case study of Wangchengpo, Changsha, China, found average total economic losses of 126.94 USD/m2, with the highest risk in the settlement core. Residential areas had the highest flood hazard, vulnerability, and losses (61.10% of the total loss); transportation areas accounted for 27.87% of the total economic losses due to their high flooding depth. Despite low inundation, industrial land showed greater economic vulnerability due to higher overall economic value (10.52% of the total). Our findings highlight the influence of land types and industry differences on flood vulnerability and the effectiveness of land-use inclusion in urban-mesoscale analyses of spatial flood characteristics. We identify critical areas with hazard and economic vulnerability for urban land and disaster prevention management and planning, helping to offer targeted flood control strategies to enhance urban resilience.

Novel integrated modelling based on multiplicative long short-term memory (mLSTM) deep learning model and ensemble multi-criteria decision making (MCDM) models for mapping flood risk

Flood risk assessment is a key step in flood management and mitigation, and flood risk maps provide a quantitative measure of flood risk. Therefore, integration of deep learning - an updated version of machine learning techniques - and multi-criteria decision making (MCDM) models can generate high-resolution flood risk maps. In this study, a novel integrated approach has been developed based on multiplicative long short-term memory (mLSTM) deep learning models and an MCDM ensemble model to map flood risk in the Minab-Shamil plain, southern Iran. A flood hazard map generated by the mLSTM model is based on nine critical features selected by GrootCV (distance to the river, vegetation cover, variables extracted from DEM (digital elevation model) and river density) and a flood inventory map (70% and 30% data were randomly selected as training and test datasets, respectively). The values of all criteria used to assess model accuracy performance (except Cohens kappa for train dataset = 86, and for test dataset = 84) achieved values greater than 90, which indicates that the mLSTM model performed very well for the generation of a spatial flood hazard map. According to the spatial flood hazard map produced by mLSTM, the very low, low, moderate, high and very high classes cover 26%, 35.3%, 20.5%, 11.2% and 7% of the total area, respectively. Flood vulnerability maps were produced by the combinative distance-based assessment (CODAS), the evaluation based on distance from average solution (EDAS), and the multi-objective optimization on the basis of simple ratio analysis (MOOSRA), and then validated by Spearman's rank correlation coefficients (SRC). Based on the SRC, the three models CODAS, EDAS, and MOOSRA showed high-ranking correlations with each other, and all three models were then used in the ensemble process. According to the CODAS-EDAS-MOOSRA ensemble model, 21.5%, 34.2%, 23.7%, 13%, and 7.6% of the total area were classified as having a very low to very high flood vulnerability, respectively. Finally, a flood risk map was generated by the combination of flood hazard and vulnerability maps produced by the mLSTM and MCDM ensemble model. According to the flood risk map, 27.4%, 34.3%, 14.8%, 15.7%, and 7.8% of the total area were classified as having a very low, low, moderate, high, and very high flood risk, respectively. Overall, the integration of mLSTM and the MCDM ensemble is a promising tool for generating precise flood risk maps and provides a useful reference for flood risk management.

Resilient landscape pattern for reducing coastal flood susceptibility

Evaluating flood susceptibility, identifying flood-prone areas, and planning reasonable landscape patterns are important measures in promoting sustainable urban development and flood mitigation. To this end, this study evaluated the flood susceptibility using a neural network model depending on a flood inundation map created from satellite data from 2010 to 2020, and explanatory factors for flood inundation selected by Geodetector and regularized random forest. Subsequently, the landscape pattern of the coastal city was quantified based on the land cover, and key landscape pattern metrics for flood susceptibility were selected at patch and class levels using statistical approaches. Eventually, urban spatial planning strategies for flood management were proposed based on the ecological significance of key metrics. Taking Xiamen as a case study, the flood susceptibility map showed that flood-prone areas in Xiamen are mainly distributed along river banks and coastlines. Key landscape pattern metrics for flood susceptibility selected by statistical approaches showed that patch-level metrics account for more explanatory power than class-level metrics, and the classes of the landscape would affect the role of patch-level metrics. Overall, the division index of the forest, the connectance index of water, the number of core areas and the fractal dimension index of urban, and the Euclidean nearest-neighbor distance of urban and water are significantly positively related to flood susceptibility, while the core area and the proximity index of urban, the similarity index, the core area index, and the edge contrast index of the forest, and the contiguity index of forest, grass, farmland, and shrub negatively related with flood susceptibility. Based on these findings, intensive urban planning and integrative Nature-based Solutions networks should be considered as strategies for enhancing coastal flood resilience.

Determining the effect of urbanization on flood hazard zones in Kahramanmaras, Turkey, using flood hazard index and multi-criteria decision analysis

Floods are the most destructive natural hazard throughout the world. Identifying flood hazard zones is the first step in flood risk management. Land use changes, especially urbanization, is the key factor in the destructiveness of flood events and change in flood risk. Therefore, determining the effect of urbanization on the changes in flood hazard zones presents a valuable data for effective flood risk management and urban development planning. In this context, the aim of this study is to reveal the effect of urbanization on flood hazard zones in Kahramanmaras city. In this study, an index-based approach was used to identify the flood hazard zones. To calculate a flood hazard index, the susceptibility map was multiplied by the land use map by using the raster calculator tool in the ArcGIS. The susceptibility map was generated by combining the maps of flow accumulation, distance to stream, slope, and elevation parameters based on parameter weights obtained from the analytical hierarchy process (AHP) method. Two land use maps for the years 1990 and 2018 were separately overlaid with the susceptibility map to reveal the effects of urbanization on flood hazard zones. According to the results, it was found that very low, low, and moderate hazard zones decreased by 0.01%, 0.09%, and 1.2%, respectively whereas the high and very high zones increased by 3.30% and 0.58%, respectively due to urbanization. It was also determined that the main reason for the increase in the high zone was the expansion of urban areas into agricultural areas in the study area.

Evaluation Model of Regional Comprehensive Disaster Reduction Capacity under Complex Environment

In order to realize the evaluation of regional comprehensive disaster reduction capacity in a complex environment, an evaluation model of regional comprehensive disaster reduction capacity in a complex environment based on remote sensing monitoring and data image feature analysis is proposed. According to the geographical location and scale of disaster spots and the parameter analysis of the model of disaster-bearing bodies around the disaster spots, the remote sensing monitoring method is adopted to extract the geographical remote sensing images of regional disaster spots in a complex environment. The collected geographical remote sensing images of regional disaster points under the complex environmental background are filtered and preprocessed, and the texture parameters of the geographical remote sensing images of regional disaster points under the complex environmental background are recognized by combining the method of image texture feature extraction. Based on the method of tone mapping, the rapid filtering and feature analysis of the geographical remote sensing images of regional disaster points under the complex environmental background are carried out, and the time, position, damage, and so on in the geographical remote sensing images of regional disaster points under the complex environmental background are analyzed. By using the method of parameter analysis and gradient operator operation, a comparison model of geographical remote sensing images of regional disaster points under the complex environmental background is established, and the reliability evaluation of regional comprehensive disaster reduction ability under the complex environmental background is realized according to the method of contrast and detail significance enhancement. The test shows that this method has high accuracy in evaluating regional comprehensive disaster reduction capability under a complex environment, high accuracy in marking the geographical location of regional disaster points under a complex environment, and good fusion performance and reliability of regional comprehensive disaster reduction capability evaluation parameters.

A Review on Interpretable and Explainable Artificial Intelligence in Hydroclimatic Applications

This review focuses on the use of Interpretable Artificial Intelligence (IAI) and eXplainable Artificial Intelligence (XAI) models for data imputations and numerical or categorical hydroclimatic predictions from nonlinearly combined multidimensional predictors. The AI models considered in this paper involve Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Extremely Randomized Trees, and Random Forest. These AI models can transform into XAI models when they are coupled with the explanatory methods such as the Shapley additive explanations and local interpretable model-agnostic explanations. The review highlights that the IAI models are capable of unveiling the rationale behind the predictions while XAI models are capable of discovering new knowledge and justifying AI-based results, which are critical for enhanced accountability of AI-driven predictions. The review also elaborates the importance of domain knowledge and interventional IAI modeling, potential advantages and disadvantages of hybrid IAI and non-IAI predictive modeling, unequivocal importance of balanced data in categorical decisions, and the choice and performance of IAI versus physics-based modeling. The review concludes with a proposed XAI framework to enhance the interpretability and explainability of AI models for hydroclimatic applications.

Predicting Change in Adaptation Strategies of Households to Geological Hazards in the Longmenshan Area, China Using Machine Learning and GIS

Hydrological changes combined with earthquakes easily trigger secondary disasters, including geological hazards. The secondary hazard of precipitation is the main disaster type in the Longmenshan Area (China). The 2008 Wenchuan earthquake caused more than 60,000 landslides, severely affecting rural households. This study aimed to answer two questions: (1) How did households adapt to the landslide-prone post-earthquake environment? (2) How will the households’ adaptation strategies change if landslide frequency changes? Different post-disaster adaptation strategies of households in Longmenshan Town, Sichuan, China were identified through a questionnaire survey and then clustered into groups based on similarity using a K-means algorithm. Afterward, a gradient boosting decision tree (GBDT) was used to predict change in adaptation strategies if there was a change in the frequency of landslides. The results show that there are three types of landslide adaptation strategies in the study area: (1) autonomous adaptation; (2) policy-dependent adaptation; and (3) hybrid adaptation, which is a mixture of the first two types. If the frequency of landslides is increased, then around 5% of households previously under the autonomous adaptation type would be converted to policy-dependent and hybrid adaptation types. If the frequency of landslides is reduced, then around 5% of households with policy-dependent adaptation strategies would be converted to the autonomous adaptation type. This exploratory study provides a glimpse of how machine learning can be utilized to predict how adaptation strategies would be modified if hazard frequency changed. A follow-up long-term study in Longmenshan Town is needed to confirm whether the predictions are indeed correct.

Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks

Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m²h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R² - 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery efficiency.

Flood Risk Assessment under Land Use and Climate Change in Wuhan City of the Yangtze River Basin, China

Frequently occurring flood disasters caused by extreme climate and urbanization processes have become the most common natural hazard and pose a great threat to human society. Therefore, urban flood risk assessment is of great significance for disaster mitigation and prevention. In this paper, the analytic hierarchy process (AHP) was applied to quantify the spatiotemporal variations in flood risk in Wuhan during 2000–2018. A comprehensive flood risk assessment index system was constructed from the hazard, sensitivity, and vulnerability components with seven indices. The results showed that the central urban area, especially the area in the west bank of the Yangtze river, had high risk due to its high flood sensitivity that was determined by land use type and high vulnerability with dense population and per unit GDP. Specifically, the Jianghan, Qiaokou, Jiangan, and Wuchang districts had the highest flood risk, more than 60% of whose area was in medium or above-medium risk regions. During 2000–2018, the flood risk overall showed an increasing trend, with Hongshan district increasing the most, and the year of 2010 was identified as a turning point for rapid risk increase. In addition, the comparison between the risk maps and actual historical inundation point records showed good agreement, indicating that the assessment framework and method proposed in this study can be useful to assist flood mitigation and management, and relevant policy recommendations were proposed based on the assessment results.