Framework for global sensitivity analysis in a complex 1D-2D coupled hydrodynamic model: Highlighting its importance on flood management over large data-scarce regions

Synergistic assessment of multi-scenario urban waterlogging through data-driven decoupling analysis in high-density urban areas: A case study in Shenzhen, China

Extreme meteorological events and rapid urbanization have led to serious urban flooding problems. Characterizing spatial variations in flooding susceptibility and elucidating its driving factors are essential for preventing damages from urban pluvial flooding. However, conventional methods, limited by spatial heterogeneity and the intricate mechanisms of urban flooding, frequently demonstrated a deficiency in precision when assessing flooding susceptibility in dense urban areas. Therefore, this study proposed a novel framework for an integrated assessment of urban flood susceptibility, based on a comprehensive cascade modeling chain consisting of XGBoost, SHapley Additive exPlanations (SHAP), and Partial Dependence Plots (PDP) in combination with K-means. It aimed to recognize the specific influence of urban morphology and the spatial patterns of flooding risk agglomeration under different rainfall scenarios in high-density urban areas. The XGBoost model demonstrated enhanced accuracy and robustness relative to other three benchmark models: RF, SVR, and BPDNN. This superiority was effectively validated during both training and independent testing in Shenzhen. The results indicated that urban 3D morphology characteristics were the dominant factors for waterlogging magnitude, which occupied 46.02 % of relative contribution. Through PDP analysis, multi-staged trends highlighted critical thresholds and interactions between significant indicators like building congestion degree (BCD) and floor area ratio (FAR). Specifically, optimal intervals like BCD between 0 and 0.075 coupled with FAR values between 0.5 and 1 have the potential to substantially mitigate flooding risks. These findings emphasize the need for strategic building configuration within urban planning frameworks. In terms of the spatial-temporal assessment, a significant aggregation effect of high-risk areas that prone to prolonged duration or high-intensity rainfall scenarios emerged in the old urban districts. The approach in the present study provides quantitative insights into waterlogging adaptation strategies for sustainable urban planning and design.

Tool for fast assessment of stormwater flood volumes for urban catchment: A machine learning approach

Specific flood volume is an important criterion for evaluating the performance of sewer networks. Currently, mechanistic models - MCMs (e.g., SWMM) are usually used for its prediction, but they require the collection of detailed information about the characteristics of the catchment and sewer network, which can be difficult to obtain, and the process of model calibration is a complex task. This paper presents a methodology for developing simulators to predict specific flood volume using machine learning methods (DNN - Deep Neural Network, GAM - Generalized Additive Model). The results of Sobol index calculations using the GSA method were used to select the ML model as an alternative to the MCM model. It was shown that the DNN model can be used for flood prediction, for which high agreement was obtained between the results of GSA calculations for rainfall data, catchment and sewer network characteristics, and calibrated SWMM parameters describing land use and sewer retention. Regression relationships (polynomials and exponential functions) were determined between Sobol indices (retention depth of impervious area, correction factor of impervious area, Manning's roughness coefficient of sewers) and sewer network characteristics (unit density of sewers, retention factor - the downstream and upstream of retention ratio) obtaining R2 = 0. 55-0.78. The feasibility of predicting sewer network flooding and modernization with the DNN model using a limited range of input data compared to the SWMM was shown. The developed model can be applied to the management of urban catchments with limited access to data and at the stage of urban planning.

Effects analysis and probability forecast (EAPF) of real-time management on urban flooding: A novel bidirectional verification framework

Government departments usually prepare and implement contingency plans to address frequent urban flooding caused by short-term heavy rainfall. Previous studies focused on the evaluation of the static impact of the policies on urban floods, while there is a lack of research on the effect of off-design conditions, real-time feedback and treatments of the flood events on urban flood mitigation, which is detrimental to the optimization of management strategies of the cities. To quantify the effects of real-time management on flood mitigation in Fuzhou City, China, this study proposed a framework (EAPF) for evaluation and risk prediction. First, we collected data on the locations, rainfall intensity, inundation time, and the triggers of the waterlogging events from 2017 to 2021. Second, based on the vigilance analyses, a structural equation model (SEM) was constructed to quantitatively evaluate the mitigation effects of management on waterlogging. Finally, a probability prediction model of dynamic drainage capacity was proposed for flood simulation caused by the rainwater grate blockage. The results indicate that the environmental factors were the decisive triggers affecting the severity of waterlogging, and increasing the frequency of management events effectively reduced the probability of blocking. The correlation between the number of management events and blocking flood events was -0.42, while a decrease in vigilance increased the possibility of flooding caused by overdue treatment. The proposed hydrological waterlogging model, which considered blockages, exhibited a Nash-Sutcliffe efficiency (NSE) coefficient exceeding 0.9 under deterministic conditions. The probability prediction model verified the mitigating effect of management on the blockages and urban flooding, and its results were consistent with those of the SEM. Our study contributes to improving the reliability of waterlogging prediction and optimizing the management flow in the developing cities.

Evaluating the influence of road construction on landslide susceptibility in Saudi Arabia's mountainous terrain: a Bayesian-optimised deep learning approach with attention mechanism and sensitivity analysis

In the mountainous region of Asir region of Saudi Arabia, road construction activities are closely associated with frequent landslides, posing significant risks to both human life and infrastructural development. This highlights an urgent need for a highly accurate landslide susceptibility map to guide future development and risk mitigation strategies. Therefore, this study aims to (1) develop robust well-optimised deep learning (DL) models for predicting landslide susceptibility and (2) conduct a comprehensive sensitivity analysis to quantify the impact of each parameter influencing landslides. To achieve these aims, three advanced DL models-Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Bayesian-optimised CNN with an attention mechanism-were rigorously trained and validated. Model validation included eight matrices, calibration curves, and Receiver Operating Characteristic (ROC) and Precision-Recall curves. Multicollinearity was examined using Variance Inflation Factor (VIF) to ensure variable independence. Additionally, sensitivity analysis was used to interpret the models and explore the influence of parameters on landslide. Results showed that road networks significantly influenced the areas identified as high-risk zones. Specifically, in the 1-km buffer around roadways, CNN_AM identified 10.42% of the area as 'Very High' susceptibility-more than double the 4.04% indicated by DNN. In the extended 2-km buffer zone around roadways, Bayesian CNN_AM continued to flag a larger area as Very High risk (7.46%), in contrast to DNN's 3.07%. In performance metrics, CNN_AM outshined DNN and regular CNN models, achieving near-perfect scores in Area Under the Curve (AUC), precision-recall, and overall accuracy. Sensitivity analysis highlighted 'Soil Texture', 'Geology', 'Distance to Road', and 'Slope' as crucial for landslide prediction. This research offers a robust, high-accuracy model that emphasises the role of road networks in landslide susceptibility, thereby providing valuable insights for planners and policymakers to proactively mitigate landslide risks in vulnerable zones near existing and future road infrastructure.

Are open-source hydrodynamic models efficient in quantifying flood risks over mountainous terrains? An exhaustive analysis over the Hindu-Kush-Himalayan region

The Hindu-Kush-Himalaya is abode to numerous severely flood-prone mountainous stretches that distress vulnerable communities and cause massive destruction to physical entities such as hydropower projects. Adopting commercial flood models for replicating the dynamics of flood wave propagation over such regions is a major constraint due to the financial economics threaded to flood management. For the first instance, the present study attempts to investigate whether advanced open-source models are skillful in quantifying flood hazards and population exposure over mountainous terrains. While doing so, the performance of 1D-2D coupled HEC-RAS v6.3 (the most recent version developed by the U.S. Army Corps of Engineers) is reconnoitred for the first time in flood management literature. The most flood-prone region in Bhutan, the Chamkhar Chhu River Basin, housing large groups of communities and airports near its floodplains, is considered. HEC-RAS v6.3 setups are corroborated by comparing them with 2010 flood imagery derived from MODIS through performance metrics. The results indicate a sizable portion of the central part of the basin experiences very-high flood hazards with depth and velocities exceeding 3 m, and 1.6 m/s, respectively, during 50, 100, and 200-year return periods of floods. To affirm HEC-RAS, the flood hazards are compared with TUFLOW at 1D and 1D-2D coupled levels. The hydrological similarity within the channel is reflected at river cross-sections (NSE and KGE > 0.98), while overland inundation and hazard statistics differ, however, very less significant (<10 %). Later, flood hazards extracted from HEC-RAS are fused with the World-Pop population to estimate the degree of population exposure. The study ascertains that HEC-RAS v6.3 is an efficacious option for flood risk mapping over geographically arduous regions and can be preferred in resource-constrained environments ensuring a minimal degree of anomaly.