Flood Warning Research Articles

Reservoir-based flood forecasting and warning: deep learning versus machine learning

In response to increasing flood risks driven by the climate crisis, urban areas require advanced forecasting and informed decision-making to support sustainable development. This study seeks to improve the reliability of reservoir-based flood forecasting and ensure adequate lead time for effective response measures. The main objectives are to predict hourly downstream flood discharge at a reference point, compare discharge predictions from a single reservoir with a four-hour lead time against those from three reservoirs with a seven-hour lead time, and evaluate the accuracy of data-driven approaches. The study takes place in the Han River Basin, located in Seoul, South Korea. Approaches include two non-deep learning (NDL) (random forest (RF), support vector regression (SVR)) and two deep learning (DL) (long short-term memory (LSTM), gated recurrent unit (GRU)). Scenario 1 incorporates data from three reservoirs, while Scenario 2 focuses solely on Paldang reservoir. Results show that RF performed 4.03% (in R2) better than SVR, while GRU performed 4.69% (in R2) better than LSTM in Scenario 1. In Scenario 2, none of the models showed any outstanding performance. Based on these findings, we propose a two-step reservoir-based approach: Initial predictions should utilize models for three upstream reservoirs with long lead time, while closer to the event, the model should focus on a single reservoir with more accurate prediction. This work stands as a significant contribution, making accurate and well-timed predictions for the local administrations to issue flood warnings and execute evacuations to mitigate flood damage and casualties in urban areas.

Relationship between Tibetan Plateau Surface Heat Fluxes and Daily Heavy Precipitation in the Middle and Lower Yangtze River Basins (1980–2022)

Variable heat fluxes over the Tibetan Plateau (TP) interact thermally with the atmosphere, affecting weather in surrounding areas, particularly in the Middle and Lower Yangtze River (MLYR). However, the circulation patterns and time-lag effects between TP heat fluxes and MLYR precipitation remain unclear. This study identified 577 large-scale daily heavy precipitation events (LSDHPEs) in the MLYR from 1980 to 2022. We analyzed the weather causation and spatiotemporal correlations between the TP surface heat fluxes and MLYR LSDHPEs using self-organizing map clustering, singular value decomposition, and harmonic analysis of time series. The results found two dominant synoptic patterns of LSDHPEs at 500 hPa: one, driven by anticyclonic and cyclonic circulations coinciding with shifts in the West Pacific subtropical high and South Asian high, increased from 2000 to 2022; the other, influenced by MLYR cyclonic circulation, showed a significant decrease. For the first time, we revealed lagged effects of the latent heat anomalies (with a lag time of 1–10 d and 130–200 d) and sensible heat anomalies (with a lag time of 2–4 months) over the TP during LSDHPEs in the MLYR. The results may enhance our understanding of TP heat flux anomalies as precursor signals for early warning of heavy rainfall and flooding in the MLYR.

A Synthetic Dataset for Semantic Segmentation of Waterbodies in Out-of-Distribution Situations

In the past decade, substantial global efforts have been devoted to the development of reliable and efficient solutions for early flood warning and monitoring. One of the most common strategies for tackling this challenge involves the application of computer vision techniques to images obtained from the numerous surveillance cameras present in urban settings today. While there are various datasets available for training and testing these techniques, none of them specifically addresses the issue of out-of-distribution (OoD) behavior. This issue becomes particularly critical when evaluating the reliability of these methods under challenging environmental conditions. Our work stands as the first attempt to bridge this gap by introducing a new, highly controlled synthetic dataset that encompasses the essential attributes required for analyzing OoD behavior. The very high correlation between the accuracy of artificial intelligence (AI) models trained on our synthetic dataset and models trained on real-world data proves our dataset’s ability to predict real-world OoD behavior reliably.

Evaluating Flood Early Warning System and Public Preparedness and Knowledge in Urban and Semi-urban Areas of Johor, Malaysia: Challenges and Opportunities

Flood Early Warning System (FEWS) play a crucial role in mitigating the impacts of floods by providing timely information to the public, which is particularly important for flood-prone areas in the Malaysian State of Johor that have suffer significant damages and disruptions almost every year. This research presents an assessment into the current state of FEWS through expert interviews and consultations with the concerned department to understand the management and institutional status and challenges in employing FEWS. In addition, a total of 106 structured questionnaires were administered as part of the survey research to a sample of residents in urban Johor Bahru and semi-urban Kota Tinggi, two regions vulnerable to floods, to collect data on their level of preparedness and knowledge, and their perceived effectiveness of FEWS. The analysis revealed that 69.8% of the respondents did not have any knowledge on the FEWS in their place, and 60.5% respondents turn to social media to gain information on flood warning, occurrence and forecast. This study also evaluates the opportunity for the messaging application as an additional support system for FEWS. The research highlights and identifies the challenges and barriers to accessing and utilizing FEWS. The study calls for the incorporation of messaging application, preferable WhatsApp to transmit early warnings to the end-users and to use their feedback in designing/redesigning the FEWS. The findings can inform policy and decision-making processes aimed at improving flood preparedness and response strategies, and contribute to the existing literature on FEWS in Malaysia and other similar regions.

IoT and AI: a panacea for climate change-resilient smart agriculture

The application of Internet of Things (IoT) and Artificial Intelligence (AI) for disaster preparedness and sustainable agriculture has been a topic of great interest lately. In the last few years, extreme weather swings due to climate change caused by global warming have caught the farming community off guard, especially in the developing world. One of the key objectives of smart agriculture is optimal use of freshwater, which has become an increasingly scarce resource around the world. Reference Evapotranspiration (ETo), an estimation of total flux of water evaporating from a reference surface is an important parameter for irrigation management. IoT & AI-based location-specific estimation of ETo for crop water requirements augments the decision-making process. In this work, we utilize the Hargeaves and Samani (H–S) model and six regression algorithms for the estimation of ETo. We create a location-specific dataset with locally sensed IoT data from a flood warning system and remotely sensed meteorological data, spanning over 5 years. We train and test Linear Regression (LR), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Support Vector Regression (SVR), Bagging and Random Forest (RF) algorithms on the locally curated dataset with 20 basic, extracted, and derived attributes. We gradually reduce number of attributes in the dataset from 20 to 3 and compare performance of the six algorithms using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Relative Absolute Error (RAE), Root Relative Squared Error (RRSE), Coefficient of Determination R2, Kendall Tau and Spearman Rho metrics. SVR shows superior performance with an MAE of 0.03 and an RMSE of 0.05, followed closely by MLP with an MAE of 0.04 and RMSE of 0.06 with a dataset of 12 attributes. The performance of Bagging and RF algorithms remains relatively unchanged with feature reduction whereas RBF shows slight improvement in performance when number of attributes is reduced to 3. Finally, we develop a novel ensemble hybrid model using the Stacked Generalization technique, which outperforms all individual models in prediction accuracy when using reduced-feature datasets. This work clearly delineates the performances of a diverse set of ML algorithms for feature-rich and feature-scarce scenarios and demonstrates the efficacy of our hybrid ensemble ML algorithm for estimating ETo under limited availability of data in resource-constrained environments.

Real-time prediction of river ice breakup phenomena: A jittered genetic programming model and wavelet analysis integrating remotely sensed imagery and machine learning

Forecasting the timing of breakup ice jams in rivers is crucial for early flood warning and effective management in cold regions where rising river flows can lead to significant damage. However, this task is hindered by insufficient data and the complex dynamics of river ice. These obstacles pose challenges in developing precise forecasting models. This study aimed to address the data scarcity issue by introducing innovative machine learning methods, focusing on classification and jittering (J), binary genetic programming (BGP), and wavelet transform (WT) for river ice forecasting (WT-JBGP) in the Tornio River, situated between Finland and Sweden. By considering time scales ranging from 2 to 32 days and time lags of 1 to 3 days, this method was applied to enhance the predictive capabilities of predictors. The findings reveal that certain predictors, with specific time scales and time lags, significantly influence the timing of breakup events. These include the 8-day temperature and 32-day discharge, both with a 2-day lag time, as well as the 4-day precipitation, approximation of albedo, and 16-day atmospheric pressure at ground level, all with a 1-day lag obtained from ERA5 and recorded data. Additionally, we conducted a quantitative evaluation of the effectiveness of the proposed model and contrasted its efficacy with that of BGP, WT-BGP, and advanced J-BGP techniques. The WT-JBGP model attains the highest overall classification accuracy of approximately 0.91, alongside a Heidke Skill Score exceeding 0.78, and a Positive Predictive Value surpassing 0.85, thereby demonstrating its superiority over competing methodologies. In summation, this study offers a promising approach to overcoming observed data scarcity in breakup date prediction, providing valuable insights into river ice dynamics.

The status of response to the flood early warnings in Kilosa District, Tanzania

Floods have been a challenging phenomenon, jeopardizing human life and property. Measures have been taken to alleviate flood effects, including using flood early warning systems (EWS), which give warnings to people. Despite the use of warnings from EWS, there is limited information on warnings contribution to mitigate flood effects. This study investigates the status of flood early warning response measures by communities in areas where floods frequently occur in Kilosa District. The data were collected from 375 household heads through surveys and triangulated by 17 participants via focus group discussions, 22 officials through key informant interviews, and a literature survey. The data were descriptively analysed, and chi-square tests and binary logistic regression analyses were done. Results indicate that 76.53 % of the respondents receive flood early warnings from word of mouth among relatives (54.21 %), phones (45.45 %), and radios (31.65 %). Upon receiving the early warnings, 45.43 % inform family members about what to do, 43.82 % vacate flood-prone areas, and 6.99 % make flood emergency response plans. Those flood warning response measures are significantly an outcome of the households’ distance from the rivers causing floods (p < .0001), chances of receiving flood warnings (p < .0001), past flood experience (p < .0001), and the nature of the houses (p < .0007). In conclusion, individuals can proactively protect against floods by diverting floodwaters away from populated areas and reducing human exposure to flood risks. To actively protect against floods, communities should implement multiple warning systems, establish reliable mechanisms to disseminate alerts and install water level gauges in all flood-prone rivers.

Effectiveness of flood early warning for the Jamuna char-dwellers at Sirajganj District in Bnagladesh

Floods, a pervasive global natural disaster, are a recurrent challenge in Bangladesh, causing substantial damage to property, infrastructure, and lives. The country has implemented a flood warning system since 1972, focusing on people, property, and cost-effectiveness. However, the efficacy of this system relies on accurate and timely dissemination of warnings and prompt responses from at-risk communities to mitigate losses and damages. This study evaluates the effectiveness of the flood early warning systems at the grassroots level in Sirajganj District, specifically in two purposively selected villages within the Kaijuri Union. One village is situated along the unprotected bankline, while the other is in the island char area. Data was gathered from 116 households through interviews, focus group discussions, and key informant interviews. Results of the Multi-criteria analysis reveal that the system is moderately effective for the bankline village (Kaijuri) with a score of 0.400, but considerably less effective for the char-land village (Thutia) with a score of 0.174. Inadequate communication links contribute to delayed and unreliable information, leading to higher losses and damages. The study emphasizes the necessity of building community trust by involving them in the planning and management of flood warning systems for more effective risk reduction.

Assessing Driver’s Trust, Compliance, and Reliance in an Automated Flood Warning System: Effects of Error Types and System Reliability

Assessing Driver’s Trust, Compliance, and Reliance in an Automated Flood Warning System: Effects of Error Types and System Reliability

A hybrid SARIMA-Prophet model for predicting historical streamflow time-series of the Sobat River in South Sudan

Accurate river streamflow forecasting is pivotal for effective water resource planning, infrastructure design, utilization, optimization, and flood planning and warning. Streamflow prediction remains a difficult task due to several factors such as climate change, topography, and lack of observed data in some cases. This paper investigates and evaluates the individual performances of the seasonal auto-regressive integrated moving average (SARIMA) and Prophet models in forecasting the streamflow of the Sobat River and proposes a hybrid SARIMA-Prophet model to leverage the strengths of both approaches. Using the augmented Dickey-Fuller (ADF) and the Kwiatkowski-Phillips-Schmidt-Shin (KPSS) tests, the flow of the Sobat River was found to be stationary. The performance of the models was then assessed based on their residual errors and predictive accuracy using the mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2). Residual analysis and prediction capabilities revealed that Prophet slightly edged SARIMA in terms of prediction efficacy; however, both models struggled to effectively capture extreme values, resulting in significant overestimations and slight underestimations. The hybrid SARIMA-Prophet model significantly reduced residual variability, achieving a lower MAE of 4.047 m3/s, RMSE of 6.17 m3/s, and a higher R2 of 0.92 than did the SARIMA (MAE: 5.39 m3/s, RMSE: 8.70 m3/s, R2: 0.85) and Prophet (MAE: 5.35 m3/s, RMSE: 8.32 m3/s, and R2: 0.86) models. This indicates that the hybrid model handles both long-term patterns and short-term fluctuations more effectively than the individual models. The findings of the present study highlight the potential of hybrid SARIMA-Prophet models for streamflow forecasting in terms of accuracy and reliability, thus contributing to more effective water resource management and planning, particularly in the Sobat River.

Runoff prediction based on the IGWOLSTM model: Achieving accurate flood forecasting and emergency management

With the acceleration of global climate change and urbanization, the frequency and impact of flood disasters are increasing year by year, making flood emergency management increasingly crucial for safeguarding people’s lives, property, and societal stability. To enhance the accuracy of river flow prediction, this study employs an Improved Gray Wolf Optimization Algorithm (IGWO) to optimize parameters of the Long Short-Term Memory Network (LSTM) model. Experimental results demonstrate that the proposed algorithm significantly improves the accuracy of river flow prediction, achieving higher precision and better generalization compared to traditional machine learning algorithms. This method provides more reliable data support for flood warning systems, aiding in the accurate prediction of flood occurrence timing and intensity, thereby providing scientific basis for flood prevention and mitigation efforts. Moreover, this approach supports hydro-logical research, enhancing understanding of river water cycle processes and ecosystem changes.

Improved similarity analysis of industrial alarm flood sequences by considering alarm correlations

Alarm floods are leading issues that compromise the efficiency of industrial alarm systems and are identified as major causes of many industrial accidents. As an advanced technique to handle alarm floods, sequence alignment based similarity analysis has been developed to match alarm flood sequences, and thus can help with further root cause identification and early warning of alarm floods. However, existing methods based on biological sequence alignment algorithms ignore the relations between alarm occurrences, and thus may cause incorrect matches or mismatches of alarms when comparing two flood sequences. Accordingly, this paper proposes a new alarm flood similarity analysis method based on global vectors and Move–Split–Merge (MSM) distance. The contributions are mainly twofold: (1) An alarm encoding model based on modified global vectors is devised to convert alarm sequences into numerical vectors that reflect the correlations of alarms; (2) a similarity analysis method based on the modified MSM distance is proposed for comparison of encoded alarm flood sequences of unequal lengths. The effectiveness of the proposed method is demonstrated through a case study with a publicly accessible industrial model for Vinyl Acetate Monomer.

Enhancing real-time flood forecasting and warning system by integrating ensemble techniques and hydrologic model simulations

ABSTRACT Flooding poses a severe threat to communities and infrastructure worldwide, which requires advanced flood forecasting warning systems. In this research paper, a real-time flood forecasting and warning system for the Dharoi Dam in the state of Gujarat, India is developed. This novel system combines ensemble techniques and hydrological modeling simulations to enhance flood prediction accuracy and provides a timely warning. The study focuses on critical gaps in the current flood forecasting capabilities, recognizes the need for improved flood management in the region, and builds upon the existing research conducted globally and in India. The real-time flood forecasting and warning system uses information from various sources such as rainfall, river flows, and water level observations. The system enhances the accuracy of flood forecasts with a 1–5-day lead time by utilizing ensemble techniques, which incorporate multiple models and their corresponding forecasts. The 2-day and 3-day lead times combined with postprocessing techniques yield excellent results, as evidenced by the reservoir inflow correlation value of 0.86 and the receiver operating characteristic-area under the curve (ROC-AUC) value of 0.93. This work aims to reduce the impact of floods in this region and can be used by decision-makers as a disaster management tool.

Policy implementation: Assessing institutional coordination and communication for flood warning in Namibia.

The study identifies bureaucracy, limited institutional capacities, inadequate funding and response and relief prioritisation as major challenges to system efficacy. It provides directives for better institutional coordination and communication to reduce future harm.

Simulation and Prediction of Snowmelt Runoff in the Tangwang River Basin Based on the NEX-GDDP-CMIP6 Climate Model

In this study, the future snowmelt runoff in the chilly northeast region’s Tangwang River Basin was simulated and predicted using the SWAT model, which was built and used based on the NEX-GDDP-CMIP6 climate model. This study conducted a detailed analysis of the spatial and temporal distribution characteristics of snowmelt runoff using high-resolution DEM, land use, and soil data, along with data from historical and future climatic scenarios. Using box plots and the Bflow digital filtering approach, this study first determined the snowmelt runoff period before precisely defining the snowmelt periods. Sensitivity analysis and parameter rate determination ensured the simulation accuracy of the SWAT model, and the correlation coefficients of the total runoff validation period and rate period were 0.75 and 0.76, with Nashiness coefficients of 0.75 for both. The correlation coefficients of the snowmelt runoff were 0.73 and 0.74, with Nashiness coefficients of 0.7 and 0.68 for both, and the model was in good agreement with the measured data. It was discovered that while temperatures indicate an increasing tendency across all future climate scenarios, precipitation is predicted to increase under the SSP2-4.5 scenario. The SSP2-4.5 scenario predicted a decreasing trend regarding runoff, while the SSP1-2.6 and SSP5-8.5 scenarios showed an increasing trend with little overall change and the SSP5-8.5 scenario even showed a decrease of 6.35%. These differences were evident in the monthly runoff simulation projections. Overall, the findings point to the possibility that, despite future climate change having a negligible effect on the hydrological cycle of the Tangwang River Basin, it may intensify and increase the frequency of extreme weather events, creating difficulties for the management of water resources and the issuing of flood warnings. For the purpose of planning water resources and studying hydrological change in this basin and other basins in cold regions, this study offers a crucial scientific foundation. An in-depth study of snowmelt runoff is of great practical significance for optimizing water resource management, rational planning of water use, spring flood prevention, and disaster mitigation and prevention, and provides valuable data support for future research on snowmelt runoff.

Insights from a topo-bathymetric and oceanographic dataset for coastal flooding studies: the French Flooding Prevention Action Program of Saint-Malo

Abstract. The French Flooding Prevention Action Program of Saint-Malo, France, requires the assessment of coastal flooding risks and the development of a local flood warning system. The first prerequisite is knowledge of the topography and bathymetry of the bay of Saint-Malo; the acquisition of new multibeam bathymetric data was performed in 2018 and 2019 to increase the resolution of the existing topo-bathymetric datasets and to produce two high-resolution (20 and 5 m) topo-bathymetric digital terrain models. Second, the hydrodynamics associated with coastal flooding were investigated through a dense and extensive oceanographic field experiment conducted during winter 2018–2019 using a network of 22 moorings with 37 sensors: the network included 2 directional buoys, 2 pressure tide gauges, 18 wave pressure gauges, 4 single-point current meters, 7 current profilers, and 4 acoustic wave current profilers from mid-depth (25 m) up to the upper beach and the dike system. The oceanographic dataset thus provides an extended overview of the hydrodynamics and wave processes in the bay of Saint-Malo from the coast up to over-flooding and over-topping areas. This dataset helps to identify the physical drivers of the coastal flooding and provides a quantification of their respective contributions. In particular, the wave processes at the foot of the protection structures can be observed: in this macro-tidal environment, during high spring tides, short and infragravity waves propagate up to the protection structures, while the wave set-up remains negligible, and over-topping by sea packs can occur. The combination of high-resolution topo-bathymetric and oceanographic datasets allows the construction, calibration and validation of a wave and hydrodynamic coupled model that is used to investigate flooding processes more deeply and might be integrated into a future local warning system by means of Saint-Malo inter-communality. The topo-bathymetric and oceanographic datasets are available freely at https://doi.org/10.17183/MNT_COTIER_GNB_PAPI_SM_20m_WGS84, https://doi.org/10.17183/MNT_COTIER_PORT_SM_PAPI_SM_5m_WGS84 and https://doi.org/10.17183/CAMPAGNE_OCEANO_STMALO (Shom, 2020a, b, 2021).

Flood preparedness in rural flood-prone area: a holistic assessment approach in Bangladesh

Despite the many fatalities and injuries, Bangladesh lacks holistic individual flood preparedness studies. This study evaluates flood preparedness in the flood-prone rural region of Dowarabazar Upazila, Sunamganj District, Bangladesh. The field survey had 596 respondents. As required, we implemented Spearman’s rank correlation and multiple linear regression. Flooding affected the study population, which made people feel extremely unsafe. Most respondents warned that floods might affect their homes. Many participants reported receiving flood-related information from locals. Most participants reported not being notified of flood forecasts and warnings in their area. The majority indicated that they sought refuge in flood shelters. A significant portion of the participants in the study were unaware of flood preparedness. Loss minimization and adaptability are deficiencies. Concerning flood preparedness, gender, age, occupation, monthly income, multiple sources of income, and house type are all significant determinants. According to field research, females are less prepared for flooding than males. Individuals with pucca housing are better equipped than those with unsafe housing (kacha). Authorities should thus take these factors into account while enhancing flood preparedness. In addition to implementing measures such as improving livelihood patterns and conducting educational campaigns, it is imperative to construct holistic flood preparedness.

Improving the understandability of flood warning messages – Explorative study on design preferences

Early warning systems (EWS) are effective if they prevent loss of lives, injuries and structural damage. Optimization of EWS is often focused on technical aspects such as the dissemination of warnings. Since the audience's response is key for the effectiveness of an EWS, non-technical aspects that improve perception and understandability of warning messages deserve attention, too. German warning messages have been criticized, particularly after fatal and destructive floods in July 2021, as being insufficient and not understandable. Data from an exploratory online survey in Germany (n = 131) reveal insights on preferences in flood warning message (FWM) design. The survey focused on structural appearance of recommendations on action and on graphic support like maps, symbols and photos. Respondents showed clear preferences of including graphics into FWMs (96 %) and structuring recommendations on action in a bullet point format (85 %). Maps were the most favored among the offered graphic options, as they offer visual information on e.g., intensity and extent of inundation. Display of real time flood maps is often not feasible yet, but flood hazard maps are available in Germany and could be integrated into future FWM as an intermediate solution.

Valuing the Economic Impact of River Floods and Early Flood Warning for Households in Bangladesh

Valuing the Economic Impact of River Floods and Early Flood Warning for Households in Bangladesh

Deep Neural Network-Based Flood Monitoring System Fusing RGB and LWIR Cameras for Embedded IoT Edge Devices

Floods are among the most common disasters, causing loss of life and enormous damage to private property and public infrastructure. Monitoring systems that detect and predict floods help respond quickly in the pre-disaster phase to prevent and mitigate flood risk and damages. Thus, this paper presents a deep neural network (DNN)-based real-time flood monitoring system for embedded Internet of Things (IoT) edge devices. The proposed system fuses long-wave infrared (LWIR) and RGB cameras to overcome a critical drawback of conventional RGB camera-based systems: severe performance deterioration at night. This system recognizes areas occupied by water using a DNN-based semantic segmentation network, whose input is a combination of RGB and LWIR images. Flood warning levels are predicted based on the water occupancy ratio calculated by the water segmentation result. The warning information is delivered to authorized personnel via a mobile message service. For real-time edge computing, the heavy semantic segmentation network is simplified by removing unimportant channels while maintaining performance by utilizing the network slimming technique. Experiments were conducted based on the dataset acquired from the sensor module with RGB and LWIR cameras installed in a flood-prone area. The results revealed that the proposed system successfully conducts water segmentation and correctly sends flood warning messages in both daytime and nighttime. Furthermore, all of the algorithms in this system were embedded on an embedded IoT edge device with a Qualcomm QCS610 System on Chip (SoC) and operated in real time.