Flood Depth Research Articles

Prediction of flood depth detection system from rainfall with normal, alert and hazard levels based on fuzzy logic

Floods are natural calamities that frequently transpire and are of primary concern for governmental entities due to their potential for significant losses and casualties. Heavy rainfall and overflowing water stand as the primary triggers for flooding. Many communities lack adequate knowledge to forecast floods, thus necessitating technological interventions for early water depth detection and issuing flood warnings. This study devised a water depth detection system based on fuzzy logic using Arduino as a microcontroller. The system employs ultrasonic sensors for water level detection and a Tipping Bucket for precipitation measurement. Its primary objective is to establish a system capable of issuing early flood warnings through alarms. The outcome of this research entails the implementation of an Arduino Uno-based flood detection system that aids users in monitoring water levels and anticipating floods. Safety considerations are also addressed by incorporating fuzzy logic technology to forecast flood potential based on water level and rainfall data. The utilization of fuzzy logic enables the system to navigate uncertainties and ambiguities in data, thus furnishing more precise and dependable early warnings. Consequently, the findings of this study serve as a groundwork for the advancement of more sophisticated and efficient flood detection systems in the future.

Advancing rapid urban flood prediction: a spatiotemporal deep learning approach with uneven rainfall and attention mechanism

ABSTRACT Urban floods pose a significant threat to human communities, making its prediction essential for comprehensive flood risk assessment and the formulation of effective resource allocation strategies. Data-driven deep learning approaches have gained traction in urban emergency flood prediction, addressing the efficiency constraints of physical models. However, the spatial structure of rainfall, which has a profound influence on urban flooding, is often overlooked in many deep learning investigations. In this study, we introduce a novel deep learning model known as CRU-Net equipped with an attention mechanism to predict inundation depths in urban terrains based on spatiotemporal rainfall patterns. This method utilizes eight topographic parameters related to the height of urban waterlogging, combined with spatial rainfall data as inputs to the model. Comparative evaluations between the developed CRU-Net and two other deep learning models, U-Net and ResU-Net, reveal that CRU-Net adeptly interprets the spatiotemporal traits of rainfall and accurately estimates flood depths, emphasizing deep inundation and flood-vulnerable regions. The model demonstrates exceptional accuracy, evidenced by a root mean square error of 0.054 m and a Nash–Sutcliffe efficiency of 0.975. CRU-Net also accurately predicts over 80% of inundation locations with depths exceeding 0.3 m. Remarkably, CRU-Net delivers predictions for 3 million grids in 2.9 s, showcasing its efficiency.

Research on nowcasting prediction technology for flooding scenarios based on data-driven and real-time monitoring.

With the impact of global climate change and the urbanization process, the risk of urban flooding has increased rapidly, especially in developing countries. Real-time monitoring and prediction of flooding extent and drainage system are the foundation of effective urban flood emergency management. Therefore, this paper presents a rapid nowcasting prediction method of urban flooding based on data-driven and real-time monitoring. The proposed method firstly adopts a small number of monitoring points to deduce the urban global real-time water level based on a machine learning algorithm. Then, a data-driven method is developed to achieve dynamic urban flooding nowcasting prediction with real-time monitoring data and high-accuracy precipitation prediction. The results show that the average MAE and RMSE of the urban flooding and conduit system in the deduction method for water level are 0.101 and 0.144, 0.124 and 0.162, respectively, while the flooding depth deduction is more stable compared to the conduit system by probabilistic statistical analysis. Moreover, the urban flooding nowcasting method can accurately predict the flooding depth, and the R2 are as high as 0.973 and 0.962 of testing. The urban flooding nowcasting prediction method provides technical support for emergency flood risk management.

Stem elongation and gibberellin response to submergence depth in clonal plant Alternanthera philoxeroides

Clonal plants are widely distributed in the riparian zone and play a very important role in the maintenance of wetland ecosystem function. Flooding is an environmental stress for plants in the riparian zone, and the response of plants varies according to the depth and duration of flooding. However, there is a lack of research on the growth response of clonal plants during flooding, and the endogenous hormone response mechanism of clonal plants is still unclear. In the present study, Alternanthera philoxeroides, a clonal plant in the riparian zone, was used to investigate the time-dependent stem elongation, the elongation of different part of the immature internodes, and the relationship between growth elongation and the phytohormone gibberellin (GA) under a series of submergence depths (0 m, 2 m, 5 m, and 9 m). The results showed that stem elongation occurred under all treatments, however, compared to 0 m (control), plants grew more under 2 m and 5 m submergence depth, while grew less under 9 m water depth. Additionally, basal part elongation of the immature internode was the predominant factor contributing to the stem growth of A. philoxeroides under different submergence depths. The phytohormone contents in basal part of the mature and immature internodes showed that GA induced the differential elongation of internode. Plant submerged at depth of 2 m had the highest GA accumulation, but plant submerged at depth of 9 m had the lowest GA concentration. These data suggested that GA biosynthesis are essential for stem elongation in A. philoxeroides, and the basal part of the immature internode was the main position of the GA biosynthesis. This study provided new information about the rapid growth and invasion of the clonal plant A. philoxeroides around the world, further clarified the effects of submergence depth and duration on the elongation of the stem, and deepened our understanding of the growth response of terrestrial plants in deeply flooded environments.

Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation

Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation

Predicting the hydraulic response of critical transport infrastructures during extreme flood events

Understanding the effects of extreme floods on critical infrastructures such as bridges is paramount for ensuring safety and resilient design in the face of climate change and extreme events. This study develops robust computational and predictive modeling tools for assessing the impacts of extreme floods on the hydraulic response and structural resilience of bridges. A computational fluid dynamic (CFD) model utilizing RANS equations and k-ω Shear Stress Transport (SST) for simulating supercritical flows is adopted to compute hydrodynamic pressures and the water levels on bridge piers of cylindrical and rectangular shapes during a flood event. The CFD model is validated based on the case study data obtained from the Haj Omran Bridge, built on the Khorramabad River in Iran. The numerical simulations consider hydrological conditions and exclude geotechnical parameters and abutment damages. The numerical results are evaluated based on well-established design guidelines. Machine learning techniques, including Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Regression (SVR), optimized with Grid Search Cross-Validation (GSCV), are adopted to enhance the accuracy of hydrodynamic pressure forecasting at bridge piers. The XGBoost model exhibits superior performance (R2 = 0.908, RMSE = 0.0279, and E = 3.41%) compared to the RF and SVR models. All the estimated pressure data by XGBoost falls within ±6 percent error lines, highlighting the model's robustness for out-of-range hydrodynamic pressure prediction. Additionally, an optimized Long Short-Term Memory (LSTM) model is adopted to effectively predict free surface flow profiles (i.e. flood depth) over the bridge (R2 = 0.937 and RMSE = 0.083), demonstrating its potential for practical applications of flood depth predictions over bridge infrastructures. The proposed methodological framework outlined in this study can facilitate modeling the impacts of extreme floods on bridges, enabling robust climate resilience assessment of critical infrastructures.

Development of an Integrated Urban Flood Model and Its Application in a Concave-Down Overpass Area

Urban floods caused by extreme rainstorm events have increased in recent decades, particularly in concave-down bridge zones. To simulate urban flooding processes accurately, an integrated urban flood model (IUFM) was constructed by coupling a distributed urban surface runoff model based on the cellular automata framework (CA-DUSRM), a widely used pipe convergence module in the storm water management model (SWMM), with an inundation module that describes the overflow expansion process associated with terrain and land-cover. The IUFM was used in a case study of the Anhua Bridge (a typical concave-down overpass) study area in Beijing, China. The spatial-temporal variations in flood depth modeled by the IUFM were verified to be reliable by comparison with actual measurements and other simulations. The validated IUFM was used to obtain temporal variations in flood range, depth, and volume under four rainstorm scenarios (return periods of 3-year, 10-year, 50-year, and 100-year). The results showed that the surface runoff process, overflow from drainage networks, and overflow expansion process could affect the flooding status by changing the composition and spatial configuration of pervious or impervious patches, drainage capacity, and underlying surface characteristics (such as terrain and land-cover). Overall, although the simulation results from the IUFM contain uncertainties from the model structures and inputs, the IUFM is an effective tool that can provide accurate and timely information to prevent and control urban flood disasters and provide decision-making support for long-term storm water management and sponge city construction.

Can geomorphic flood descriptors coupled with machine learning models enhance in quantifying flood risks over data-scarce catchments? Development of a hybrid framework for Ganga basin (India).

Quantifying flood risks through a cascade of hydraulic-cum-hydrodynamic modelling is data-intensive and computationally demanding- a major constraint for economically struggling and data-scarce low and middle-income nations. Under such circumstances, geomorphic flood descriptors (GFDs), that encompass the hidden characteristics of flood propensity may assist in developing a nuanced understanding of flood risk management. In line with this, the present study proposes a novel framework for estimating flood hazard and population exposure by leveraging GFDs and Machine Learning (ML) models over severely flood-prone Ganga basin. The study incorporates SHapley Additive exPlanations (SHAP) values in flood hazard modeling to justify the degree of influence of each GFD on the simulated floodplain maps. A set of 15 relevant GFDs derived from high-resolution CartoDEM are forced to five state-of-the-art ML models; AdaBoost, Random Forest, GBDT, XGBoost, and CatBoost, for predicting flood extents and depths. To enumerate the performance of ML models, a set of twelve statistical metrics are considered. Our result indicates a superior performance of XGBoost (κ = 0.72 and KGE = 82%) over other ML models in flood extent and flood depth prediction, resulting in about 47% of the population exposure to high-flood risks. The SHAP summary plots reveal a pre-dominance of Height Above Nearest Drainage during flood depth prediction. The study contributes significantly in comprehending our understanding of catchment characteristics and its influence in the process of sustainable disaster risk reduction. The results obtained from the study provide valuable recommendations for efficient flood management and mitigation strategies, especially over global data-scarce flood-prone basins.

Cumulative sedimentation hazard map of urban areas subject to hyperconcentrated flash flood: A case study of Suide County in the Wuding River basin, China

AbstractFlash floods can carry substantial sediment, posing significant sedimentation hazards in hilly cities. The sedimentation hazard map can reproduce the sediment thickness and extent of an extreme events scenario, playing an important role in sediment risk management. However, current research primarily focuses on modeling the inundation area and depth of floods, while studying sedimentation hazard caused by flash floods in urban areas remains insufficient. This paper aims to address this gap by utilizing a numerical model that simulates hyperconcentrated flow in hilly urban areas using the two‐dimensional hydro‐sediment‐morphological model to compile the cumulative sedimentation hazard map. The model, built upon the open‐source TELEMAC‐MASCARET framework, incorporates Zhang Hongwu's formula to simulate sediment‐carrying capacity, particularly suitable for hyper‐sediment concentration near the riverbed. This paper uses the data of extreme flash flood events in the Wuding River basin in 2017 to simulate and compile the cumulative sedimentation hazard map. The hazard map delineates the sedimentation hazard extent and level attributable to overbank floodplain sedimentation. Notably, the sediment thickness is highest in areas near the levees on both sides of the Dali River. Moreover, the map illustrates the extent of channel erosion resulting from hyperconcentrated floods, which could jeopardize bank stability.

Effects of damage initiation points of depth-damage function on flood risk assessment

The flood depth in a structure is a key factor in flood loss models, influencing the estimation of building and contents losses, as well as overall flood risk. Recent studies have emphasized the importance of determining the damage initiation point (DIP) of depth-damage functions, where the flood damage is assumed to initiate with respect to the first-floor height of the building. Here we investigate the effects of DIP selection on the flood risk assessment of buildings located in Special Flood Hazard Areas. We characterize flood using the Gumbel extreme value distribution’s location (μ) and scale (α) parameters. Results reveal that average annual flood loss (AAL) values do not depend on μ, but instead follow an exponential decay pattern with α when damage initiates below the first-floor height of a building (i.e., negative DIP). A linear increasing pattern of the AAL with α is achieved by changing the DIP to the first-floor height (i.e., DIP = 0). The study also demonstrates that negative DIPs have larger associated AAL, thus contributing substantially to the overall AAL, compared to positive DIPs. The study underscores the significance of proper DIP selection in flood risk assessment.

Open-access digital elevation model (DEM) selection for flood inundation modelling using HEC-RAS in Capital City of Nusantara

Flood is a classic but complex issue in most regions of Indonesia. Nusantara, the future capital of Indonesia, is now undergoing construction but the site continues to experience flooding due to high intensity rainfall. To overcome this challenge, identification of flood points in those areas needs to be done. Digital Elevation Models (DEM) are the most important component in modeling flood inundation in data-sparse areas. High-accuracy DEMs have been found to give better flood estimation but the availability of such data is very limited. Therefore, open-access DEMs, such as SRTM, DEMNAS, and MERIT-Hydro, are the most common choices used in modeling flood inundation in Indonesia. Each data set may provide varying model outcomes, due to different data processing methods. These results often lead to confusion as to which result should be used in subsequent studies. In this study, flood inundation in Nusantara will be generated using different DEMs and HEC-RAS hydraulic modeling with 25-, 50-, and 100-year return period rainfall events. The return period rainfall was obtained by calibrating Global Precipitation Measurement (GPM) satellite rain data. The results provide various flood inundation conditions, MERIT-Hydro tends to present higher flood depths. Followed by DEMNAS and SRTM which have lower flood depths. On the other hand, the use of return period variation gives a linear increase in flood depth for the DEMNAS model. While a decline in increment occurred in the SRTM and MERIT-Hydro models when the two big year return periods were applied. This research can be considered for the Nusantara development planning.

Perception and Reality: How the Depths of the High Waters in Venice Apparently Change with the Reference System

Over the centuries, the depths of the most severe storm surges that have flooded Venice have been measured using different reference frames, i.e., related to the algae belt (CM), mean sea level (MSL), local land (ZMPS), large-scale leveling (IGM), and satellite altimetry (SA). Some reference frames, i.e., IGM and SA, are absolute, while the others are relative and represent two different physical points of view, i.e., CM and MSL refer to the sea that is rising and ZMPS refers to the land that is subsiding. The perceptions derived from the different systems are contradictory. This paper discusses and compares surges from 1821 to 2021 measured with these frames, also including the commemorative plaques that report the flood depths on walls in Venice. The paper explains the consequences of a change in frame and zero reference, and it transforms the flooding depths from the original systems to make them homogeneous. The severity of flooding changes in terms of rating with the choice of frame. In the 19th century, five storm surges exceeded the famous level of 1966 and, if they were to recur today or in the future, the sea level rise and the local land subsidence that have occurred in the meantime would greatly exacerbate the situation.

Application of Parallel Computing on Hybrid Inundation Model, Case Study: Chiayi County Flood 23-24 August 2018

A robust 2D inundation model is needed to support flood warning systems in urban areas. The conventional 2D hydrodynamic model uses shallow water equations as the governing equation and is computationally expensive. Although the models have benefited from parallel computation techniques, some issues remain. As an alternative, many flood models have been developed using different approaches, such as Cellular Automata (CA), DEM-based (DBM), and data-driven models. The hybrid inundation model (HIM) was developed by combining the CA-DBM concepts. The purpose of this study is to implement the parallel computation technique to increase the efficiency of HIM. The model performance was evaluated using the historical flood event in Chiayi County, Taiwan. Results showed that there is no significant difference between HIM and TUFLOW in terms of flood depth estimation, even though TUFLOW included the drainage system within the analysis. These results proved that the drainage system was not working during the event. HIM and TUFLOW give underestimated flood depth prediction compared to the observed data. The main reason because the observed data was obtained from local community testimonies. Hence, there might be many uncertainties in the observed data value. Finally, the parallelization process successfully decreased the computation time of the original HIM. The computation was decreased from 450 to 11 minutes depending on the number of cores used in the simulation.

Amplification factors for extreme sea level frequency have problematic features as a metric of coastal hazard

Abstract The future projected frequency of a specified baseline extreme sea level (ESL), often called the amplification factor (AF), is extensively used as a metric of evolving coastal flood hazard with sea level rise (SLR). The baseline ESL is typically analyzed using extreme value analysis, and the SLR is added to the resulting distribution. In the presence of SLR uncertainty, it is natural to analyze AFs probabilistically. I derive probability density functions (PDFs) of AF, given uncertainty distributions of SLR. If the ESL distribution is modeled as Gumbel and the SLR distribution as normal, then the AF distribution is log normal. However, in active tropical cyclone regions, ESL often has a longer tail than Gumbel, and a Frechet (Type-II) Generalized Extreme Value (GEV) is more appropriate. In this case, I show that the AF distribution has a divergent mean, preventing its use as a hazard metric. In addition, I show that for Frechet ESL, the AF cannot even be defined for SLR above a threshold β / ξ f 0 − ξ , where f 0 is the specified baseline frequency (e.g., f 0 = 0.01 yr−1 for the 100-year exceedance), β is the GEV scale parameter and ξ the shape parameter. This SLR threshold can be as low as 0.5 m in the southeast US and Caribbean, within reach mid to late century. Above the threshold, ESL at all frequencies exceeds the baseline reference frequency, preventing the calculation of AF. The resulting probabilistic distribution of AF is insensitive to SLR above the threshold. These features detrimentally impact the utility of AF as a hazard metric. Frechet distributions are appropriate and commonly used for ESL in tropical cyclone regions, but AFs applied to such distributions must interpreted with caution. In such regions, coastal risk managers should consider other flood hazard metrics, such as probabilistic estimates of flood depth.

Integration of UAV Digital Surface Model and HEC-HMS Hydrological Model System in iRIC Hydrological Simulation—A Case Study of Wu River

This research investigates flood susceptibility in the mid- and downstream areas of Taiwan’s Wu River, historically prone to flooding in central Taiwan. The study integrates the Hydrologic Engineering Center—Hydrologic Modeling System (HEC-HMS) for flow simulations with unmanned aerial vehicle (UAV)-derived digital surface models (DSMs) at varying resolutions. Flood simulations, executed through the International River Interface Cooperative (iRIC), assess flood depths using diverse DSM resolutions. Notably, HEC-HMS simulations exhibit commendable Nash–Sutcliffe efficiency (NSE) exceeding 0.88 and a peak flow percentage error (PEPF) below 5%, indicating excellent suitability. In iRIC flood simulations, optimal results emerge with a 2 m resolution UAV-DSM. Furthermore, the study incorporates rainfall data at different recurrence intervals in iRIC flood simulations, presenting an alternative flood modeling approach. This research underscores the efficacy of integrating UAV-DSM into iRIC flood simulations, enabling precise flood depth assessment and risk analysis for flood control management.

ELEV-VISION: Automated Lowest Floor Elevation Estimation from Segmenting Street View Images

We propose an automated lowest floor elevation (LFE) estimation algorithm based on computer vision techniques to leverage the latent information in street view images. Flood depth-damage models use a combination of LFE and flood depth for determining flood risk and extent of damage to properties. We used image segmentation for detecting door bottoms and roadside edges from Google Street View images. The characteristic of equirectangular projection with constant spacing representation of horizontal and vertical angles allows extraction of the pitch angle from the camera to the door bottom. The depth from the camera to the door bottom was obtained from the depthmap paired with the Google Street View image. LFEs were calculated from the pitch angle and the depth. The testbed for application of the proposed method is Meyerland (Harris County, Texas). The results show that the proposed method achieved mean absolute error of 0.190 m (1.18 %) in estimating LFE. The height difference between the street and the lowest floor (HDSL) was estimated to provide information for flood damage estimation. The proposed automatic LFE estimation algorithm using street view images and image segmentation provides a rapid and cost-effective method for LFE estimation compared with the surveys using total station theodolite and unmanned aerial systems. By obtaining more accurate and up-to-date LFE data using the proposed method, city planners, emergency planners and insurance companies could make a more precise estimation of flood damage.

Accuracy assessment of global DEMs for the mapping of coastal flooding on a low-lying sandy environment: Cassino Beach, Brazil

Projected sea level rise in the 21st century, driven by climate change, threatens low-lying coastal areas with the risk of persistent flooding. Accurately estimating flooding extent and depth is crucial to implementing effective coastal management, with digital elevation models (DEMs) playing a pivotal role. Intrinsic inaccuracies of DEMs might lead to uncertainty in the flooding projections due to SLR scenarios, which are problematic for decision-makers. This work assessed the accuracy of five global digital elevation models for coastal flooding mapping on a low-lying sandy coastal environment in the south of Brazil (Cassino Beach). Five global DEMs were assessed, namely ALOS-AW3D30, ALOS-PALSAR, ASTER, SRTM, and TanDEM-X, and a high-resolution digital elevation model (created using local aerial vehicle (UAV) imagery) was used as a benchmark. A morphometric comparison was conducted between the five global DEMs and the high-resolution local DEMs. Several statistical metrics were calculated, including the root mean squared error, correlation coefficient, and bias.Additionally, flood depths and extent were computed for different scenarios of sea level rise, and comparisons between the different DEMs were quantified. Results show that among the DEMs evaluated, TanDEM-X DEM achieved the highest correlation with the UAV DEM elevation in the beach and dune region, presenting R² equal to 0.56 and RMSE equal to 0.88 m. On the other hand, the ALOS-AW3D30, ALOS-PALSAR, ASTER, and SRTM DEMs presented low correlation and RMSE values above 2.49 m. The analysis of coastal flooding extension and depths confirms that the TanDEM-X DEM exhibited the highest similarity with the UAV DEM across various sea level scenarios, and it was the only global DEM analyzed capable of capturing dune depressions and roads, which serve as primary pathways for flooding in the type of coastal region under consideration.

Study on a flood damage reduction countermeasure by installing a spillway on a riverine levee for promoting the initiative of River Basin Disaster Resilience and Sustainability by All

Abstract. In light of the frequent occurrence of unprecedented heavy rains and floods attributable to climate change effects, the importance of the “River Basin Disaster Resilience and Sustainability by All” initiative is being emphasized and promoted strongly in Japan. For promoting discussions on a wide range of countermeasures for flood damage reduction by the initiative, this paper presents a trial estimation result of quantitative flood damage reduction effect by spillway installation on a riverine levee in a protected area where severe flood disasters have occurred in recent years. The result shows that the countermeasure considerably reduce the flooded area, the days required for drainage, and house flood depths. Results also indicate that the average annual damage to paddy fields in the area can be expected to decrease, although the inundation frequency will increase.

Soil Bacterial and Archaeal Communities of the Periodic Flooding Zone of Three Main Reservoirs in the South Ural Region (Russia)

Studying the soils in the periodical flood zone of three reservoirs is of promising importance for their subsequent return to economic activities. Research on the bacterial and archaeal communities of soils that are periodically or continuously flooded by reservoirs is still insufficient. To evaluate the chemical status of soils and their microbiota, the study was conducted in the Yumaguzino, Nugush, and Slak reservoir sites in the South Ural area (Russian Federation). The bacterial and archaeal communities of periodically flooded and non-flooded soils were investigated after a comparative investigation of chemical, hydrological, and climatic factors. It was discovered that flooded soils had anoxic conditions during the whole of the year, with brief drying intervals of limited length and low levels of effective temperatures. In terms of chemistry, flooded soils are distinguished by increased acidity, a fall in organic matter, and an increase in alkali-hydrolysable nitrogen. Compared to their counterparts in non-flooded soils, bacterial and archaeal communities in flooded soils are significantly different. Generally speaking, the biodiversity of flooded soils rises with the duration and depth of floods. Significant variations at the phylum level are mostly caused by a decline in the relative presence of Thaumarchaeota and an increase in Proteobacteria and Chloroflexi representation. It was discovered that the Euryarchaeota phylum was either absent or had a significantly decreased relative prevalence at the sites of intermittently flooding soils.

Improved flood depth estimation with SAR image, digital elevation model, and machine learning schemes

Study regionNhat Le river basin, the floodplains of Central coast of Vietnam. Study focusFlood disasters have a significant impact on population and economies worldwide. To accurately assess flood damage, it is crucial to estimate the water depth and predict the potential spread of damage. However, conventional methods of estimating flood depth can be time-consuming and costly due to the large amount of data required from hydraulic and rain-runoff models. To overcome these limitations, we propose a new approach that integrates a machine learning (ML) algorithm with a floodwater depth estimation tool (FwDET) based on SAR imagery and digital elevation models (DEMs). To evaluate our approach, we trained and tested six ML regression algorithms using 804 sets of inventory flood depth data from the historic flood on the Nhat Le River in Vietnam in October 2020 as the dependent variable. This approach significantly improves flood depth prediction accuracy, enabling a faster and more cost-effective estimation of flood damage. New hydrological insights for the regionOur research shows that by combining ML with FwDET, we were able to significantly enhance water depth prediction accuracy. We observed a 25.05% increase in the R2 coefficient and a 13.46% increase in the R coefficient. We recommend integrating satellite imagery, DEM, and ML for flood depth predictions, especially for floodplains with similar topographical conditions as the Nhat Le basin. This approach offers a practical, cost-effective, and near real-time solution for flood response. Implementing this approach can help improve flood damage assessment and mitigate the potential impacts of flood disasters on communities and economies.