Traffic Disruption Research Articles

Quantitative assessment of congestion diffusion and cascading effect under rainfall-flood disasters: A case study of Nanjing, China

Urban road networks are frequently disrupted by flooding rainfall-flood disasters, which can cause severe traffic disruptions and leading to traffic congestion due to cascading effect. This paper investigates the reliability issues under rainfall-flood conditions. A coupled model, integrating a rainfall-flood model with an improved cascading failure model, is proposed to assess how rainfall intensities and flooding will influence traffic congestion and bring network instability. Utilizing an improved Nonlinear Load-Capacity model, we quantify the impact of congestion and analyze cascading processes under various rainfall-flood conditions. The case study in Nanjing, China reveal that, when congestion causes network pressure to exceed the traffic percolation threshold, traffic congestion diffusion becomes more pronounced, putting excessive strain on other passable roads. Network cascading failures due to traffic congestion diffusion can lead to excessive focus on the remaining passable roads, resulting in a sharp increase in the average importance. The significance of this work lies in its provision of an effective method for predicting potential network disruptions and cascading failures in advance, thereby enhancing post-disaster road operations.

Real-Time Freeway Crash Detection Framework using Connected Vehicle Waypoint Data

Accurate and timely detection of traffic accidents is crucial for transportation agencies seeking swift responses and effective traffic management, particularly on freeways where crash severity and traffic flow disruptions are amplified. While several methods have been developed using cameras or infrastructure-mounted sensors, these approaches may face challenges in geographical scalability. To address this issue, a novel approach has been developed that leverages real-time connected vehicle trajectories at a market penetration rate of 4%–9%. The method involves extracting five key features from individual journeys that sense the speed and acceleration fluctuations. The results demonstrate promising outcomes, achieving an overall accuracy of 63.5% with 4.1% false detections and 33.4% non-detections. This accuracy surpasses the speed-alone model using the same data by 24%. Furthermore, higher traffic volumes lead to even greater accuracy, exceeding 80% at level of service D and 90% at level of service E. The developed algorithm also exhibits precision in crash detection, with a mean latency of only 2.5 min after the actual incidents. The entire processing time may additionally add up to 1 min. The robustness of the model is tested for a single day on one of the interstates, providing promising results. This study highlights the potential of connected vehicle data in enhancing crash prediction methods and underlines its value for the safety and efficiency of future transportation systems.

Integrated approach for flood shelter site selection and emergency response accessibility analysis at the provincial scale: a case study in Henan, China

ABSTRACT Emergency response efficiency is affected seriously by shelter location during traffic disruption caused by floods. In this paper, a new framework including the suitability assessment of shelter location and the accessibility analysis of emergency response is proposed. Firstly, an evaluation criteria system from a risk perspective is established to screen candidate shelters. Secondly, candidate shelters’ effective area, capacity, and service radius are combined to determine the suitable shelter locations. Finally, the emergency accessibility of traffic under different rainstorm scenarios is calculated, respectively. The results show that resident emergency congregate shelters are suitable to be built in economically developed and highly densely populated areas around the central part of Henan, and it is mainly to guard against extreme floods caused by heavy rainfall. It should be dominated by emergency evacuation and embarkation shelters to prevent daily floods in the west and southwest. In addition, the reduced accessibility is apparent in the western and southeastern regions owing to road inundation, and occurs in the disaster scenarios of the 20-year return period and more. This study suggests how to select suitable shelters by considering the spatial heterogeneity of the province.

Study on automatic anti-icing effect and rheological properties of asphalt based on SiO2 nanowires

This study addresses the issue of severe traffic disruptions caused by winter road icing by enhancing traffic disaster resilience. A primary road-surface ice-control technique, known as "anti-icing", is proposed. A nanomaterial with outstanding superhydrophobic properties was prepared and incorporated into asphalt to create hydrophobic ice-inhibiting modified asphalt. Extensive experimentation confirmed that the hydrophobic ice-inhibiting modified asphalt had desirable characteristics, achieving impressive anti-icing performance. The experimental results indicated that the synthesised material was superhydrophobic, with a contact angle exceeding 150° and its primary component being SiO2. At the microscopic level, the synthesised superhydrophobic material exhibited a complex microstructure, primarily characterised by entangled nanowires and a small quantity of nanoparticles. In addition, the material demonstrated stable thermal properties and good compatibility with asphalt. The superhydrophobic material significantly enhanced the hydrophobic properties of asphalt, and the prepared asphalt mixture effectively inhibited the formation of surface ice layers, consequently reducing the surface ice accumulation and ice formation efficiency by 69.11 % and 19.01 %, respectively, for the asphalt containing 15 % superhydrophobic material relative to the base asphalt. In conclusion, the superhydrophobic material prepared in this study enhances the performance of asphalt while imparting de-icing functionality, making it a novel road surface "anti-icing" material that improves winter traffic resilience.

An Autonomous Intelligent Liability Determination Method for Minor Accidents Based on Collision Detection and Large Language Models

With the rapid increase in the number of vehicles on the road, minor traffic accidents have become more frequent, contributing significantly to traffic congestion and disruptions. Traditional methods for determining responsibility in such accidents often require human intervention, leading to delays and inefficiencies. This study proposed a fully intelligent method for liability determination in minor accidents, utilizing collision detection and large language models. The approach integrated advanced vehicle recognition using the YOLOv8 algorithm coupled with a minimum mean square error filter for real-time target tracking. Additionally, an improved global optical flow estimation algorithm and support vector machines were employed to accurately detect traffic accidents. Key frames from accident scenes were extracted and analyzed using the GPT4-Vision-Preview model to determine liability. Simulation experiments demonstrated that the proposed method accurately and efficiently detected vehicle collisions, rapidly determined liability, and generated detailed accident reports. The method achieved the fully automated AI processing of minor traffic accidents without manual intervention, ensuring both objectivity and fairness.

Deep reinforcement learning assisted memetic scheduling of drones for railway catenary deicing

Icy rainfall and snowfall in 2024 Spring Festival struck the high-speed railway catenary systems and caused serious traffic disruptions in central and eastern China. Deicing drones are an effective method in response to these freezing events due to their fast speed and high environmental tolerance. However, the large disaster-affected area and the large scale and complexity of catenary networks make deicing drone scheduling a very difficult problem. In this paper, we formulate two versions of deicing drone scheduling problem, one for single drone scheduling and the other for multiple drone scheduling. Unlike most existing vehicle/drone routing problems, our problem aims to minimize the total negative effect caused by the freezing events on train operations, which reflects the prime concern of the decision-maker and is highly complex. To efficiently solve the problem, we propose a reinforcement learning assisted memetic optimization algorithm, which integrates global mutation and a set of neighborhood search operators adaptively selected by deep reinforcement learning. Computational results on real-world problem instances demonstrate its significant performance advantages over selected popular optimization algorithms in the literature.

Enhancing work zone Safety: A psychological and behavioral analysis of Anti-Tailgating strategies using dynamic message signs and fixed warning signs

Rear-end collisions in work zones, particularly those resulting from tailgating, pose a significant safety challenge that has not been adequately addressed in road safety research. Existing studies have extensively investigated speeding, but the psychological triggers and behavioral patterns leading to tailgating remain largely unexplored. Bridging this critical gap, this research introduces an anti-tailgating strategy using dynamic and fixed message signs, designed with a deep understanding of driver psychology. The methodology involved a user-centric survey assessing the effect of positively toned, non-numerical anti-tailgating messages, which favored clearer comprehension and elicited favorable psychological responses from drivers. Field experiments demonstrated that these signs effectively increased headway and decreased tailgating, without the traffic disruptions associated with pavement markings or the technological limitations of in-vehicle alerts. These encouraging results underscore the potential of strategically placed message signs to positively influence driver behavior. This research not only fills a significant void by elucidating the behavioral factors of tailgating in work zones, but also paves the way for the implementation of behaviorally informed and nonintrusive road safety interventions. The use of dynamic and fixed message signs emerges as a promising, technologically inclusive, and psychologically effective tool for improving road safety.

Toward the Development of an Impact-Based Decision Support Tool for Surface-Transportation Hazards. Part I: Tying Weather Variables to Road Hazards and Quantifying Impacts

Abstract Development of an impact-based decision support forecasting tool for surface-transportation hazards requires consideration for what impacts the product is intended to capture and how to scale forecast information to impacts to then categorize impact severity. In this first part of the series, we discuss the motivation and intent of such a product, in addition to outlining the approach we take to leverage existing and new research to develop the product. Traffic disruptions (e.g., crashes, increased travel times, roadway restrictions, or closures) are the intended impacts, where impact severity levels are intended to scale to reflect the increasing severity of adverse driving conditions that can correlate with a need for enhanced mitigation efforts by motorists and/or transportation agencies (e.g., slowing down, avoiding travel, and imposing roadway restrictions or closures). Previous research on how weather and road conditions impact transportation and novel research herein to create a metric for crash impact based on precipitation type and local hour of the day are both intended to help scale weather forecasts to impacts. Impact severity classifications can ultimately be determined through consideration of any thresholds used by transportation agencies, in conjunction with the scaling metrics. Significance Statement Weather can profoundly impact surface transportation and motorist safety. Because of this and because there are no explicit tools available to forecasters to identify and communicate potential impacts to surface transportation, there is a desire for the development of such a forecast product. However, doing so requires careful consideration for what impacts are intended to be included, how weather corresponds to impacts, and how thresholds for impact severity should be defined. In this first part of the paper series, we outline each of these aspects and present novel research and approaches for the development of an impact-based forecast product specifically tailored to surface-transportation hazards. The product is ultimately intended to improve motorist safety and mobility on roads.

Equity in Transportation Asset Management: A Proposed Framework

Transportation asset management has historically overlooked equity considerations. However, recently, there has been a significant increase in concerns about this issue, leading to a range of research and practices aimed at achieving more equitable outcomes. Yet, addressing equity is challenging and time-consuming, given its complexity and multifaceted nature. Several factors can significantly impact the outcome of an analysis, including the definition of equity, the evaluation and quantification of its impacts, and the community classification. As a result, there can be a wide range of interpretations of what constitutes equity. Therefore, there is no single correct or incorrect approach for equity evaluation, and different perspectives, impacts, and analysis methods could be considered for this purpose. This study reviews previous research on how transportation agencies are integrating equity into transportation asset management, particularly pavement management systems. The primary objective is to investigate important equity factors for pavement management and propose a prototype framework that integrates economic, environmental, and social equity considerations into the decision-making process for pavement maintenance, rehabilitation, and reconstruction projects. The proposed framework consists of two main steps: (1) defining objectives based on the three equity dimensions, and (2) analyzing key factors for identifying underserved areas through a case study approach. The case study analyzed pavement condition and sociodemographic data for California’s Bay Area. Statistical analysis and a machine learning method revealed that areas with higher poverty rates and worse air quality tend to have poorer pavement conditions, highlighting the need to consider these factors when defining underserved areas in Bay Area and promoting equity in pavement management decision-making. The proposed framework incorporates an optimization problem to simultaneously minimize disparities in pavement conditions between underserved and other areas, reduce greenhouse gas emissions from construction and traffic disruptions, and maximize overall network pavement condition subject to budget constraints. By incorporating all three equity aspects into a quantitative decision-support framework with specific objectives, this study proposes a novel approach for transportation agencies to promote sustainable and equitable asset management practices.

Assessing dynamic congestion risks of flood-disrupted transportation network systems through time-variant topological analysis and traffic demand dynamics

Amid escalating climate change and extreme weather events, urban road networks face increasingly severe flood risks. Current congestion risk analyses on transportation systems, largely grounded in static network characteristics, fall short of capturing the dynamic impacts of evolving flood events on network topology. A notable gap in integrating dynamic flood models with detailed temporal network property measurements impedes a deep understanding of the cascading mechanisms of traffic disruptions caused by floods. The research introduces an innovative framework for assessing dynamic congestion risks within transportation networks under flooding conditions. This framework comprises four distinct layers. The Data and Context layer collates and contextualizes primary data, encompassing road networks, commuter behaviour patterns and hydrological risks. This layer establishes a baseline for understanding the structure of the transportation system and its environmental vulnerabilities. The Computation layer focuses on calculating context-based betweenness centrality values to capture the importance of road segments within the network, setting a static indicator. Concurrently, this layer examines the dynamic exposure flag under flood conditions, providing a dynamic indicator that accounts for the fluctuating susceptibility of road networks to flooding. The Integration layer bridges the topological analysis and the functional performance of the transportation system. It creates a dynamic series that describes the topological properties of the network, reflecting its vulnerability to disruptions. Simultaneously, the time-variant traffic demand series are tracked to capture the system’s operational response to flood-induced conditions. Finally, the Evaluation layer synthesizes data and analyses from the previous modules. This synthesis involves a novel dual assessment: generating a time-variant vulnerability index series and evaluating the time-variant congestion risk map on the transportation system under flooding. The London case study is developed based on this proposed framework to identify critical areas of congestion risks. This study offers valuable data-driven insights for urban planning and disaster management, aiding policymakers, planners and emergency teams to enhance urban resilience against flood-induced transport disruptions.

An assessment of priorities in handling climate change impacts on infrastructures

Climate change (CC) will likely significantly impact the world’s infrastructure significantly. Rising temperatures, increased precipitation, and rising sea levels are all likely to stress critical infrastructures (CI). Rising temperatures can lead to infrastructure damage from extreme heat events. This can cause roads and bridges to buckle or crack, leading to costly repairs and potential traffic disruptions. In addition, heat waves can damage vital electrical infrastructure, leading to widespread power outages. In light of this context, this article reports on a study which examined the connections and impacts of CC on infrastructure. The study employed a mixed-method approach, combining bibliometric analysis for the period 1997–2022 with a series of relevant case studies from the five continents to offer insight into the impact of CC on infrastructure. The article fills a research gap in respect of assessments of the extent to which climate change (CC) negative influences the infrastructure, with a special focus on developing countries. It also showcases CI projects and adaptation measures being currently deployed, to address CC. The results show that the current infrastructure is vulnerable to CC. The selected case studies on CI adaptation show that in developing and industrialised countries, there is a perceived need to understand better the connections and potential impacts of CC on critical areas such as transport, settlements, and coastal infrastructure. In order to protect infrastructure from CC impacts, governments need to invest in measures such as flood control, early warning systems, and improved building codes. Additionally, they need to work to reduce greenhouse gas emissions more actively, which are the primary cause of CC.

TECHNOLOGICAL ASPECTS OF PRODUCTION OF EPOXY ASPHALT CONCRETE BY ADDING CARBON ADDITIVES

Epoxy asphalt concrete is a durable, high-quality material consisting of epoxy resins, hardeners, and the mineral part itself. Accordingly, slow-hardening epoxy asphalt concrete has high physical properties and low sensitivity to temperature changes, which makes it usable as a rigid pavement and applicable even on metal and concrete bridge decks. However, a downside of epoxy asphalt concrete is its ability to gain strength over a long period of operation (up to 1 year). It is a disadvantage when using such coatings in the upper layer of the road surface. In addition, a long period of strength gain during intensive use of the road pavement leads to critical destruction of the pavement itself, plastic deformation, and a reduction in the service life (which may differ much from the standard). Using metal fibre substantially increases the strength and keeps the area from collapsing. The use of metal elements can significantly reduce the performance of the tires of vehicles that will drive on the road and even create a hazard in the event of destruction of the epoxy asphalt concrete area. Using epoxy binders notably increases the strength characteristics of road materials, especially at high temperatures, and boosts their ability to resist rutting. At the same time, the characteristics of epoxy concrete do not decrease during operation and at low temperatures, which indicates the versatility of such a material. The only drawback that cancels out all the positive features of epoxy asphalt concrete is its long strength gain. This disadvantage not only led to the problems mentioned above but also delayed the opening of traffic, which, especially on roads of higher categories, caused traffic disruption and inconvenience to the movement of vehicles. The authors proposed a solution to this problem by developing an improved epoxy asphalt concrete composition by introducing fibre ash into the developed composition as a reinforcing and structuring additive that accelerates the pavement formation time and strengthens the asphalt matrix in epoxy asphalt concrete. Keywords: epoxy asphalt concrete, additive, fibre, fly ash, combustion products.

Traffic Flow Prediction with Random Walks on Graph and Spatiotemporal Bidirectional Attention Transformer

Traffic flow prediction is crucial in intelligent transportation systems. Considering the severe disruptions caused by traffic accidents or congestion, a time series model is developed for traffic flow prediction based on multiple random walks on graphs (MRWG) and the bidirectional spatiotemporal attention mechanism (BSAM), which can adapt to both normal and exceptional situations. The MRWG mechanism is applied to capture spatial features of urban areas during traffic accidents and congestion, especially the spatial dependencies among neighboring regions. Further, a local position attention module is applied to acquire the spatial correlations between different regions to investigate their impact on the global area, while a local temporal attention module is adopted to extract short-term periodic time correlations from traffic flow data. Finally, a spatiotemporal bidirectional attention module is applied to simultaneously extract both the temporal and spatial correlations of the historical traffic flow data in order to generate the output prediction. Experiments have been conducted on NYCTaxi and NYCBike datasets with abnormal events, and the results indicate that the developed model can efficiently predict traffic flow in abnormal events, especially short-term traffic disruptions, outperforming the baseline methods under both abnormal and normal conditions.

Routing attack induced anomaly detection in IoT network using RBM-LSTM

The network of resource constraint devices, also known as the Low power and Lossy Networks (LLNs), constitutes the edge tire of the Internet of Things applications like smart homes, smart cities, and connected vehicles. The IPv6 Routing Protocol over Low power and lossy networks (RPL) ensures efficient routing in the edge tire of the IoT environment. However, RPL has inherent vulnerabilities that allow malicious insider entities to instigate several security attacks in the IoT network. As a result, the IoT networks suffer from resource depletion, performance degradation, and traffic disruption. Recent literature discusses several machine learning algorithms to detect one or more routing attacks. However, IoT infrastructures are expanding, and so are the attack surfaces. Therefore, it is essential to have a solution that can adapt to this change. This paper introduces a comprehensive framework to detect routing attacks within Low Power and Lossy Networks (LLNs). The proposed solution leverages deep learning by combining Restricted Boltzmann Machine (RBM) and Long Short-Term Memory (LSTM). The framework is trained on 11 network parameters to understand and predict normal network behavior. Anomalies, identified as deviations from the forecast trends, serve as indicators of potential routing attacks and thus address vulnerabilities in the RPL.

Smart and Resilient Mobility Services Platform for Managing Traffic Disruptive Events

This article aims to develop a smart mobility solution to enhance the travel experience of individuals facing traffic disruptive events. Unlike prior research focusing on isolated solutions for managing these events, this study takes a holistic approach combining real-time monitoring, predictive modeling, route guidance, and effective communication to create efficient traffic disruption management. The study introduces the Smart and Resilient Mobility Services Platform (SRMS), specifically designed to address mobility restrictions as a form of disruptive events in the Palestinian territories, West Bank. SRMS empowers users to make well-informed decisions by providing services such as real-time mapping of mobility restrictions, a prompt notification system, informal route mapping, and alternative path suggestions. Moreover, it aims to enhance engagement among travelers and citizens by adopting spatial crowdsourcing as the primary data source for potential restrictions and embracing the User-Centered Design (UCD) approach to enrich users’ interaction with the developed solution. The methodology involves presenting the architectural layering system of the SRMS platform, and detailing the prototyping and design development considering the UCD approach. Results present the practical implementation of the SRMS tailored to the Palestinian context and adopted UCD.

Improved Finite Element Model Updating of a Highway Viaduct Using Acceleration and Strain Data.

Most finite element model updating (FEMU) studies on bridges are acceleration-based due to their lower cost and ease of use compared to strain- or displacement-based methods, which entail costly experiments and traffic disruptions. This leads to a scarcity of comprehensive studies incorporating strain measurements. This study employed the strain- and acceleration-based FEMU analyses performed on a more than 50-year-old multi-span concrete highway viaduct. Mid-span strains under heavy vehicles were considered for the strain-based FEMU, and frequencies and mode shapes for the acceleration-based FEMU. The analyses were performed separately for up to three variables, representing Young's modulus adjustment factors for different groups of structural elements. FEMU studies considered residual minimisation and the error-domain model falsification (EDMF) methodology. The residual minimisation utilised four different single-objective optimisations focusing on strains, frequencies, and mode shapes. Strain- and frequency-based FEMU analyses resulted in an approximately 20% increase in the overall superstructure's design stiffness. This study shows the benefits of the intuitive EDMF over residual minimisation for FEMU, where information gained from the strain data, in addition to the acceleration data, manifests more sensible updated variables. EDMF finally resulted in a 25-50% overestimated design stiffness of internal main girders.

Real-Time Dynamic Intelligent Image Recognition and Tracking System for Rockfall Disasters.

Taiwan, frequently affected by extreme weather causing phenomena such as earthquakes and typhoons, faces a high incidence of rockfall disasters due to its largely mountainous terrain. These disasters have led to numerous casualties, government compensation cases, and significant transportation safety impacts. According to the National Science and Technology Center for Disaster Reduction records from 2010 to 2022, 421 out of 866 soil and rock disasters occurred in eastern Taiwan, causing traffic disruptions due to rockfalls. Since traditional sensors of disaster detectors only record changes after a rockfall, there is no system in place to detect rockfalls as they occur. To combat this, a rockfall detection and tracking system using deep learning and image processing technology was developed. This system includes a real-time image tracking and recognition system that integrates YOLO and image processing technology. It was trained on a self-collected dataset of 2490 high-resolution RGB images. The system's performance was evaluated on 30 videos featuring various rockfall scenarios. It achieved a mean Average Precision (mAP50) of 0.845 and mAP50-95 of 0.41, with a processing time of 125 ms. Tested on advanced hardware, the system proves effective in quickly tracking and identifying hazardous rockfalls, offering a significant advancement in disaster management and prevention.

Secure and lightweight message dissemination framework for internet of vehicles

AbstractThe Internet of Vehicles (IoV) revolutionizes vehicle communication in dynamic networks. Message dissemination in IoV involves sharing critical information for the safety and convenience of the IoV network. It is very crucial to secure message dissemination due to potential cyber‐attacks, traffic disruptions, and privacy breaches. Data integrity, authentication, and privacy are vital to maintaining trust and safety in the IoV network. This network consists of resource‐constrained IoV devices with limited resources due to the availability of embedded components in vehicular systems. Therefore, optimizing algorithms and protocols is crucial for efficient vehicle‐to‐everything (V2X) communication, enhancing safety and transportation efficiency. Solutions often include lightweight protocols and secure message exchange. This paper proposes a machine learning (ML) based secure and lightweight message dissemination framework for resource‐constrained IoV. First, we present an ML‐based threat classification model capable of effectively categorizing adversarial and nonadversarial data streams and delivering an optimized model with superior accuracy. Furthermore, we also propose a secure message dissemination scheme using lightweight cryptographic primitives, which significantly reduces computational, communication, and energy overhead. To validate the robustness of our proposed ML‐based secure and lightweight message dissemination framework, we evaluate it using various security parameters and performance measures such as computation cost, communication cost, energy cost, accuracy, precision, recall, and F1‐score. Our contributions promise to significantly enhance the security and efficiency of message dissemination in IoV environments and advance lightweight, secure, and reliable transportation systems for the future.

Real-time anomaly detection of short-term traffic disruptions in urban areas through adaptive isolation forest

The escalating congestion impacts of short-term traffic disruptions, such as double parking or short-duration work zones, are gaining increased attention. This study introduces an enhanced isolation forest-based unsupervised anomaly detection algorithm to detect short-term traffic disruptions in urban areas. To enable the detection in real-time, a sliding window approach is introduced to allow the streaming data to be read and processed according to the window size. An adaptive threshold that automatically adjusts itself to overcome the limitations of the miss rate on local anomalies is shown to further enhance the model predictions. The proposed algorithm is empirically validated on four study sites in Manhattan, New York City. The experimental results demonstrate that the proposed unsupervised algorithm can effectively detect different types of traffic anomalies including accidents, work zones/road closures, traffic jams, double parking events and police activities. On all sites, the average detection rate is 81.1% for traffic jams and 89.6% for police activities, respectively. For three out of the four sites, the detection rate ranges from 71.4% to 100% for accidents, work zones and double parking. An optimizer using high-pass filter is also presented to further improve off-line detection. The primary advantages of this proposed computationally-efficient method are that its only required data input is travel time information and that it does not need labeled data for training, which make it highly deployable for real-time operational applications and can be easily adopted by other cities.

Comprehensive Application of Borehole Fine Detection Methods: A Case Study in Shantou Bay Subsea Tunnel

Water inrush disaster is one of the most severe problems during the construction of sea tunnels, primarily due to faults, karst, and weathered zones. Once a water inrush disaster occurs, it can lead to construction delays, traffic disruptions, and major economic losses, as well as potential consequences such as seawater intrusion, casualties, project suspension, and tunnel closure. Thus, advanced geological prediction is indispensable. During the construction of the Shantou Bay subsea tunnel, a sudden water inrush accident occurred in the sea–land transition section. To prevent such incidents and ensure safety, an integrated approach was employed. Firstly, the cross‐hole resistivity method was used to predict water content in front of the tunnel, as it is highly sensitive to water. Subsequently, borehole ground‐penetrating radar was applied to finely characterize the geological structure. By combining these two methods, the size, scale, location, water content, and spatial distribution of water‐bearing structures in front of the tunnel were identified. With the above measures, the Shantou Bay subsea tunnel passed through the detection section successfully. Herein, we present a case study and offer a valuable reference for similar projects concerning subsea tunnel construction.