Rescue Resources Research Articles

Global, regional, and national drowning trends from 1990 to 2021: Results from the 2021 Global Burden of Disease Study.

Drowning is a preventable public health concern that burdens emergency care systems globally. This study comprehensively evaluated fatal drowning patterns across population, time, and geography from 1990 to 2021 to inform effective prevention strategies. Using the 2021 Global Burden of Disease Study framework and standardized estimation methods, the study analyzed global and regional drowning burden in terms of mortality, incidence, and disability-adjusted life-years (DALYs), based on population registry data and drowning-related epidemiological covariates. Global drowning incidents decreased by 33.67% from 1990 to 2021. The drowning incidence rate and mortality rate declined from 24.20 and 9.68 per 100,000 in 1990 to 10.85 and 3.48 per 100,000 in 2021, respectively. Years of life lost and DALYs rates due to drowning also decreased significantly, from 715.80 and 718.69 per 100,000 in 1990 to 197.64 and 198.92 per 100,000 in 2021. Regionally, East Asia had the highest drowning mortality (27.15% of global deaths), while the high-income Asia Pacific region experienced the highest incidence rate (21.38 per 100,000). South Asia had the greatest number of drowning deaths (75,639). Tropical Latin America showed the largest incidence decline, while high-income Asia Pacific exhibited increasing trends. Drowning disproportionately affected children under 5 and the elderly in most regions. While global drowning rates have declined, progress varies across regions. To improve prevention, focus should target low-income/middle-income countries and vulnerable populations like children and the elderly. Increased investment in safety education and rescue resources is vital to address their disproportionate risks.

Optimization of Predefined-Time Agent-Scheduling Strategy Based on PPO

In this paper, we introduce an agent rescue scheduling approach grounded in proximal policy optimization, coupled with a singularity-free predefined-time control strategy. The primary objective of this methodology is to bolster the efficiency and precision of rescue missions. Firstly, we have designed an evaluation function closely related to the average flying distance of agents, which provides a quantitative benchmark for assessing different scheduling schemes and assists in optimizing the allocation of rescue resources. Secondly, we have developed a scheduling strategy optimization method using the Proximal Policy Optimization (PPO) algorithm. This method can automatically learn and adjust scheduling strategies to adapt to complex rescue environments and varying task demands. The evaluation function provides crucial feedback signals for the PPO algorithm, ensuring that the algorithm can precisely adjust the scheduling strategies to achieve optimal results. Thirdly, aiming to attain stability and precision in agent navigation to designated positions, we formulate a singularity-free predefined-time fuzzy adaptive tracking control strategy. This approach dynamically modulates control parameters in reaction to external disturbances and uncertainties, thus ensuring the precise arrival of agents at their destinations within the predefined time. Finally, to substantiate the validity of our proposed approach, we crafted a simulation environment in Python 3.7, engaging in a comparative analysis between the PPO and the other optimization method, Deep Q-network (DQN), utilizing the variation in reward values as the benchmark for evaluation.

Mediatized governance in environmental disasters: self-organizing community rescue through collaborative online documents

The frequency of risks and disasters in contemporary society has created new challenges for rescue governance. Through content analysis and participant observation, this study examined the development of an online collaborative and self-organizing community during the 2021 rainstorm rescue effort in Zhengzhou, China. The study shows that this community provided and optimized major public goods and services, adapted rescue resources to victim needs, facilitated streamlined information transfer, protected privacy, and connected a multitude of actors. The findings illustrate the significance of a new mode of mediatized governance that emphasizes the continuous process of reconciling conflicting interests and encouraging joint action among multiple actors, thereby realizing a flexible and efficient rescue that could not have been achieved by a top-down government-led administration.

The spatial overlay effect of urban waterlogging risk and land use value

Urban waterlogging poses a severe threat to lives and property globally, making it crucial to identify the distribution of urban value and waterlogging risk. Previous research has overlooked the heterogeneity of value and risk in spatial distribution. To identify the overlay effect of urban land value and risk, this study employs the Entropy Weighting Method (EM) to assess urban value, Principal Component Analysis (PCA) to determine waterlogging risk and key areas (RK), local Moran's I (SC) to identify key areas (HK), and finally Bivariate local Moran's I (DC) to comprehensively evaluate urban value and waterlogging risk to delineate key areas (BH). The results indicate that waterlogging risk is primarily influenced by proximity to water systems (PCA coefficient: 0.567), population density (0.550), and rainfall (0.445). There is a positive correlation between urban value and waterlogging risk, with a global Moran's I of 0.536, indicating that areas with higher urban value also face greater waterlogging risk. The DC method improved identification precision, reducing the BH area by 6.42 and 3.51 km2 compared to RK and HK, accounting for 25.50 % and 15.76 % of the RK and HK identified areas, respectively. At present, rescue resources can access less than one-third of the area within 5 min, but with the DC method, during the centennial rainfall scenario, the accessibility rate within 5 min for the BH area reaches 63 %, and all BH key areas can be covered within 15 min. This study provides a new methodology for identifying key areas of waterlogging disasters and can be used to enhance urban rescue efficiency and the precision management of flood disasters.

Graph convolutional LSTM algorithm for real-time crash prediction on mountainous freeways

Accurate real-time traffic crash prediction is crucial for proactive traffic safety management. Currently, the majority of real-time models forecast crashes every 5 min to support different intelligent transportation systems. However, these intervals might be too short for practical use in manually implementing proactive traffic safety measures such as deploying traffic law enforcement and emergency rescue resources. Therefore, this study develops hourly crash prediction models to provide network operators with sufficient time to take measures in advance. A section of a mountainous freeway in Guizhou province is divided into homogeneous segments, with crash data, traffic operations data, and meteorological data being collected hourly. As the result is an imbalanced dataset of crash and non-crash instances, the training dataset is resampled using synthetic minority over-sampling technique (SMOTE) to address the issue. To fully capture the complex spatiotemporal relationships in the data and achieve high crash prediction accuracy, a graph convolutional network-long short-term memory (GCN-LSTM) model is constructed for the first time, combining a graph convolutional network (GCN) and long short-term memory (LSTM) neural network. For comparison purposes, LSTM, Extreme Gradient Boosting (XGBoost), and logistic regression (LR) models are developed. The results show that the GCN-LSTM model outperforms other models in hourly traffic crash prediction, and the optimal prediction performance is achieved with the crash-to-non-crash ratio of 1:4. The GCN-LSTM method is found to effectively capture the complex spatiotemporal relationships in prediction data and to handle imbalanced traffic crash data.

Development of violence-associated penetrating trauma in the Düsseldorf metropolitan region over a5-year period (GewPen study)

Penetrating injuries are arare but recurring emergency situation in the out-of-hospital and in-hospital emergency settings. The purpose of this study was to determine the incidence and characteristics of injuries associated with penetrating violence across aGerman metropolitan region over a5-year period. In the retrospective study, adatabase query of the control center of the Düsseldorf rescue service area was used to identify and descriptively analyze all rescue service operations with penetrating violence-associated injuries in the years 2015, 2017, and 2019. For those patients who were transferred to the major trauma center, afurther analysis of the in-hospital course was performed. In the 3 years 2015, 2017 and 2019 atotal of 266 patients (age: 33 ± 14years, male: 79%) could be recorded (2015 vs. 2017 vs. 2019: n = 81 vs. n = 93 vs. n = 92, respectively). The most common age group involved had an age range of 15-34years. Aparticularly higher frequency of emergency calls was found for the areas of Old Town, City Center, and one other district (Oberbilk). Ahigh frequency of rescue missions was found in the nights from Saturday to Sunday between 20.00 p.m. and 04.00 a.m. Rescue missions with emergency physicians on board increased over the years (2015 vs. 2019: 27 vs. 42%, p = 0.04). The primary weapons used were knives (56%), broken glass bottles (18%) and broken glasses (6%). Out of all patients 71 (27%, injury severity score11 ± 14) were admitted to the major trauma center. Among these patients, the proportion of immediate surgical care (2015 vs. 2019: 20% vs. 35%, p < 0.05) and positive alcohol detection increased over the years (2015 vs. 2019: 10% vs. 43%, p < 0.05). The 30-day mortality in the 3 years studied was 1.1% (n = 3). Penetrating injuries associated with violence are relevant but rare rescue missions. Future care strategies should focus on deployment of rescue resources close to the scene of the incident ("old town guard", central station), and prevention strategies should focus on weapon prohibition zones. A control of alcohol consumption should be discussed.

Accident black spot clustering oriented maritime search and rescue resource allocation and optimization

Efficient and rapid deployment of maritime search and rescue(MSAR) resources is a prerequisite for maritime emergency search and rescue, in order to improve the efficiency and accuracy of MSAR. This paper proposes an integrated approach for emergency resource allocation. The approach encompasses three main steps: identifying accident black spots, assessing high-risk areas, and optimizing the outcomes through a synergistic combination of an optimization algorithm and reinforcement learning. In the initial step, the paper introduces the iterative self-organizing data analysis technology (ISODATA) for identifying accident spots at sea. A comparative analysis is conducted with other clustering algorithms, highlighting the superiority of ISODATA in effectively conducting dense clustering. This can effectively carry out dense clustering, instead of the situation where the data spots are too dispersed or obvious anomalies that affect the clustering. Furthermore, this approach incorporates entropy weighting to reassess the significance of accident spots by considering both the distance and the frequency of accidents. This integrated approach enhances the allocation of search and rescue forces, ensuring more efficient resource utilization. To address the MSAR vessel scheduling problem at sea, the paper employs the non-dominated sorting genetic algorithm II combined with reinforcement learning (NSGAII-RL). Comparative evaluations against other optimization algorithms reveal that the proposed approach can save a minimum of 7% in search and rescue time, leading to enhanced stability and improved efficiency in large-scale MSAR operations. Overall, the integrated approach presented in this paper offers a robust solution to the ship scheduling problem in maritime search and rescue operations. Its effectiveness is demonstrated through improved resource allocation, enhanced timeliness, and higher efficiency in responding to maritime accidents.

Safety Wearable for Miners

INTRODUCTION: Mining is the process of extraction of valuable minerals, ores and other non-renewable resources from the Earth’s surface. The mining industry is known for its hazardous and highly risky working environment. OBJECTIVES: The mining industry is involved in the extraction of these geological materials, which is essential for the development of the country and its economy. However, this industry comes with its fair share of risks and dangers. Recent statistics show that around 100 miners fall victim to the harsh working conditions every year. METHODS: Explosions due to Methane and coal dust followed by roof collapses, mine fires, gas outburst, blasting accidents, poisoning and suffocation are the major reasons out of these few of them causes deaths inside the mines. RESULTS: Even though many precautions are suggested, and measures have been taken to improve the safety of the miners and to improve the work environment, but mines are still unpredictable, and accidents are also recorded then and there. CONCLUSION: The existing safety technologies and measures have either failed to monitor multiple vital features that could lead to fatalities, or to provide adequate and appropriate rescue resources in time to help the miners in danger.

A Three-Stage Stochastic Model to Improve Resilience with Lateral Transshipment in Multi-Period Emergency Logistics

Driven by the growing threat of natural disasters caused by climate change, there is an urgent need to strengthen the emergency rescue logistics network. However, insufficient research has been conducted on optimizing both pre-disaster preparation and post-disaster response, resulting in lower resilience and inefficiency of emergency logistics management. To this end, this study explores the optimization of emergency rescue resource allocation and transportation network design, considering the uncertainty and multi-period nature of natural disaster rescue. By employing a lateral transshipment strategy, a three-stage stochastic programming model is established, which aims to balance economic benefits with the need for devastations, thereby enhancing the resilience of the logistics network. Numerical experiments verify the effectiveness of the proposed model with different instances and the performance of the lateral transshipment strategy by comparing it with a two-stage stochastic programming model. Sensitivity analysis is performed on the costs of constructing a depot and the penalties for unmet needs. The analysis yielded valuable insights that can be used to enhance emergency rescue operations, supply chain network design, and logistics network design. The research outcome can benefit emergency responders and logistics professionals in optimizing their operations.

Międzynarodowy wymiar polskiego ratownictwa

International dimension of Polish rescue The article presents international security structures within the framework of which it is possible to dispose of Polish rescue resources outside Poland. The authors focused mainly on three major international organizations, where appropriate structures, mechanisms or groups have been created for this purpose, i.e. – the European Union (EU), the United Nations (UN), the North Atlantic Treaty Organization (NATO). These organizations also have their own coordination centers operating on a 24-hour basis, which makes these activities coordinated and supervised. This article also presents the legal basis on which the above-mentioned structures are established. In addition, examples are presented of rescue fields in the area of which the created rescue entities function according to specific schemes, determined by international conventions, guidelines, etc., referring here mainly to marine and air rescue.

A Multi-Objective Optimization Method for Maritime Search and Rescue Resource Allocation: An Application to the South China Sea

To effectively address the increase in maritime accidents and the challenges posed by the trend toward larger ships for maritime safety, it is crucial to rationally allocate the limited maritime search and rescue (MSAR) resources and enhance accident response capabilities. We present a comprehensive method for allocating MSAR resources, aiming to improve the overall efficiency of MSAR operations. First, we use long short-term memory to predict the number of future accidents and employ the K-medoids algorithm to identify the accident black spots in the studied area. Next, we analyze the multi-constraint conditions in the MSAR resource allocation process. A multi-objective integer programming model is constructed to minimize the response time and allocation cost. Finally, we use the non-dominated sorting genetic algorithm II (DNSGA-II) with Deb’s rules to solve the model, and we propose a multi-attribute decision optimization-based method for MSAR resource allocation. We found that the DNSGA-II exhibits better convergence and generates higher-quality solutions compared to the NSGA-II, particle swarm optimization (PSO), and enhanced particle swarm optimization (EPSO) algorithms. Compared with the existing MSAR resource emergency response system, the optimized scheme reduces the response time and allocation cost by 11.32% and 6.15%, respectively. The proposed method can offer decision makers new insights when formulating MSAR resource allocation plans.

Modeling the Spatial Distribution of Population Based on Random Forest and Parameter Optimization Methods: A Case Study of Sichuan, China

Spatial population distribution data is the discretization of demographic data into spatial grids, which has vital reference significance for disaster emergency response, disaster assessment, emergency rescue resource allocation, and post-disaster reconstruction. The random forest (RF) model, as a prominent method for modeling the spatial distribution of population, has been studied by many scholars, both domestically and abroad. Specifically, research has focused on aspects such as multi-source data fusion, feature selection, and data accuracy evaluation within the modeling process. However, discussions about parameter optimization methods during the modeling process and the impact of different optimization methods on modeling accuracy are relatively limited. In light of the above circumstances, this paper employs the RF model to conduct research on population spatialization with multi-source spatial information data. The study primarily explores the differences in model parameter optimization achieved through random search algorithms, grid search algorithms, genetic algorithms, simulated annealing algorithms, Bayesian optimization based on Gaussian process algorithms, and Bayesian optimization based on gradient boosting regression tree algorithms. Additionally, the study investigates the influence of different optimization algorithms on the accuracy of population spatialization modeling. Subsequently, the model with the highest accuracy is selected as the prediction model for population spatialization. Based on this model, a spatial population distribution dataset of Sichuan Province at a 1 km resolution is generated. Finally, the population dataset created in this paper is compared and validated with open datasets such as GPW, LandScan, and WorldPop. Experimental results indicate that the spatial population distribution dataset produced by the Bayesian optimization-based random forest model proposed in this paper exhibits a higher fitting accuracy with real data. The Coefficient of Determination (R2) is 0.6628, the Mean Absolute Error (MAE) is 12,459, and the Root Mean Squared Error (RMSE) is 25,037. Compared to publicly available international datasets, the dataset generated in this paper more accurately represents the spatial distribution of the population.

Documenting Baseline Efficacy of Grain Rescue Training for Emergency First Responders Through Pre- and Post-Testing, and Follow-Up Survey

Highlights Pre- and post-tests, administered to 2,141 emergency first responder participants, showed an average improvement in test scores from 67% to 75%, highlighting the efficacy of the training. Interviews conducted within 3 years post-training revealed high participant satisfaction, with over 25% reporting adoption of key strategies discussed in the training by their fire/rescue service. Areas of concern were identified, including the lack of understanding related to certain hazards, such as free-flowing grain, which may put first responders at risk of secondary victimization. Abstract. Purdue University’s Agricultural Safety and Health Program has provided leadership for nearly 40 years in the documentation of fatalities and injuries associated with agricultural confined spaces, especially those relating to grain storage, handling, and transport. Findings have been used to develop evidence-based resources to assist in the prevention and mitigation of these incidents, including the design of in-service training resources for emergency rescue and medical personnel responding to entrapments or engulfment in agricultural confined spaces. To enhance the efficacy and consistency of these training resources, a list of core competencies was developed with companion test questions by a panel of experts to validate the baseline understanding and knowledge gain of training participants. The test questions were pilot tested as pre- and post-tests and incorporated into a curriculum developed under a U.S. Department of Labor Susan Harwood Training Grant. The twenty-question pre- and post-tests were administered to 2,141 registered emergency first responder participants in training conducted primarily in Indiana. Participation was voluntary, providing 671 usable matched pre- and post-tests. On average, test scores improved from 67% to 75%. A question-by-question review highlighted areas of common knowledge as well as at least one topic in which the potential for confusion was increased by the instructional content. In addition, participants were interviewed within 3 years to assess the impact of the training received. Interviewees indicated a high level of satisfaction with the training, and over 25% indicated that their fire/rescue service adopted at least one of the seven key strategies discussed in the training. One key concern observed in training was the lack of understanding related to certain hazards, such as the nature of free-flowing grain, that may put first responders at risk of becoming secondary victims during rescue and extrication efforts. A need was identified for continued improvement of emergency first responder training through the incorporation of recent research findings on confined space rescue, greater attention to the prevention of secondary injuries, and more consistent instructor preparation in order to increase the probability of successful outcomes from incidents involving grain storage, handling, and transport. Keywords: First responder, Grain entrapment, Grain rescue, Safety training

Risk analysis of mutual influence relationships among residents under rescue operations in long-term flooded areas

Recent climate change is expected to cause severe flood damage, and new flood countermeasures are urgently required. However, there is concern that the current capacity of rescue operations is limited in response to the increasing scale of flood damage. In future flood countermeasures, it will be necessary for the government not only to carry out rescue activities but also to demand a balance between self-help and public assistance, for example, by requesting residents to evacuate voluntarily. However, to expect a change in the attitude of the residents themselves, it is important to communicate the risk by presenting evidence for such a change. Therefore, in this study, problems related to the rescue of isolated residents in water rescue operations in long-term inundated areas and the effects on residents waiting for rescue were identified. Specifically, we conducted a rescue simulation using a multiagent system in an actual urban area that was expected to be flooded for a long period. We confirmed that boat rescue operations are subject to more restrictions than ground rescue operations and pose a significant risk to residents waiting for rescue operations. We observed a strong interrelationship between residents who shared limited rescue resources, and that the decisions of individual residents influenced each other's rescue time. These relationships have given rise to an ethical problem called rescue triage owing to the nature of boat rescue operations. This study does not aim to find a rescue policy or an efficient rescue operation but discusses risk management in rescue operations in a long-flooded area.

Development and validation of a soft voting-based model for urban fire risk prediction

Early identification of fire risk helps to mitigate the possible consequences incurred by fire, and meanwhile helps optimize the allocation of rescue resources. In this paper, we propose a comprehensive machine learning-based approach for predicting fire risk. The study area is divided into multiple 1 km × 1 km grid cells, and fire incident records, Point of Interest (POI) data, and meteorological data are geographically mapped to these grid cells. By applying the k-means clustering algorithm to analyze monthly fire occurrences, fire risk levels are assigned to each grid cell. A dataset is constructed with the target variable being the fire risk level and the predictive variables being POI data and meteorological data. After undergoing feature engineering, the dataset is divided into training and testing sets based on a time span. Deep neural networks, Randomforest, and Extreme Gradient Boosting (XGBoost) algorithms are trained on the training set and combined using a soft voting approach to create the final soft voting-based model (SV-based model). The performance of the SV-based model is rigorously evaluated on the testing set, achieving a prediction accuracy of 98.9 %. When evaluated using the AUC and F1-score as metrics, the scores are 0.92 and 0.98, respectively, surpassing other machine learning models used for comparison. The findings of this research contribute to the field of urban fire risk management and provide valuable insights for decision-makers and urban planners in formulating proactive fire prevention strategies.

Spatial risk assessment of maritime transportation in offshore waters of China using machine learning and geospatial big data

Maritime transportation plays a crucial role in global trade and economic development. However, this industry is exposed to various risks (e.g., natural disasters), which can cause significant economic and environmental damage. This study aims to develop a spatial risk assessment approach for maritime transportation using machine learning and geospatial big data to identify potential risks in China's maritime transportation industry. The proposed approach first produces risk maps that reveal significant variability in maritime transportation risks across different regions of China. Then, factor importance analysis identifies wave height, rainfall, and sea surface temperature as the most influential factors affecting navigational safety. Finally, capability indicators are employed to analyze the matching relationship between coastal search and rescue resources and maritime transportation risks. Our study provides valuable references for enhancing maritime emergency response capabilities and protecting marine ecological environments.

Deep Reinforcement Learning-Based Rescue Resource Distribution Scheduling of Storm Surge Inundation Emergency Logistics

A high-intensity storm surge hazard exposes residents and facilities to inundation danger. A continuously operating robust inundation emergency logistics system is vital to guarantee lives and support the control of hazardous materials. A massive inundation area, large number of affected facilities, and instantly changing flooding situation bring tremendous challenges to rescue resource allocation. In this article, a rescue resource distribution scheduling of storm surge inundation logistics is proposed to quantitatively formulate the rescue time minimization problem in emergency logistics. The mixed-integer linear programming (MILP) method is proposed for the emergency logistics scheduling model validation and optimality comparison. To enhance the efficiency of creating a good quality allocation strategy when facing large-scale problems, a deep reinforcement learning algorithm—deep deterministic policy gradient (DDPG)—is utilized to search the solutions. Based on a rescue resource scheduling model of storm surge inundation logistics targeting storm surge Mangkhut in September, 2018, a case study of the Futian District, Shenzhen, China, was conducted to verify the correctness and efficiency of the MILP and the DDPG. The optimal schedule solution designed by the MILP had a duration of 3.5138 h, while the solution calculated by DDPG had a duration of 5.065 h for the rescue. The execution time of DDPG was stable and under a second, while the execution time of the MILP was over two hours.

Modeling the power system resilience in China under different natural disasters

A good understanding of the power system resilience is necessary for optimizing the investment strategies and supporting the emergency rescue, but the existing quantitative estimation results based on real outage events are still lacked due to the data limitations. Therefore, this study first establishes a unified framework to measure the power system resilience under different natural disasters, by integrating the electricity performance curve with the dynamic inoperability input-output model. Then, a database of 285 Chinese historical big power outage events caused by natural disasters is established, and the city-level power system resilience values are estimated. Finally, a benefit analysis is conducted for improving the power system resilience. Our major findings are that: (1) Electricity system recoveries quickest from hail (23.05 h), while restores slowest from snowstorm (117.31 h). (2) China's city electricity system is the most resilient to the thunderstorm, while is the least resilient to the earthquake. (3) Enhancing the power system resilience will significantly reduce the requirements for rescue resources, and the saved emergency rescue cost ranges from 0.57 million yuan to 12.08 million yuan with 1% reduction of initial inoperability.

Spatiotemporal Information Mining for Emergency Response of Urban Flood Based on Social Media and Remote Sensing Data

The emergency response is crucial in preventing and mitigating urban floods. Both remote sensing and social media data offer distinct advantages in large-scale flood monitoring and near-real-time flood monitoring. However, current research lacks a thorough exploration of the application of social media data and remote sensing imagery in the urban flood emergency response. To address this issue, this paper, while extracting disaster information based on social media data, deeply mines the spatiotemporal distribution characteristics and dynamic spatial accessibility of rescue points. Furthermore, SAR imagery and social media data for monitoring urban flooding are compared. This study took the Zhengzhou 7.20 urban flood as a case study and created a methodological framework to quickly extract flood disaster information (flood, landslide, and rescue points) using these two types of data; spatiotemporal analysis and random forest classification were also conducted to mine valuable information. Temporally, the study revealed that disaster information did not increase proportionally with the amount of rainfall during the rainfall process. Spatially, specific regions with higher susceptibility to flooding, landslides, and rescue points were identified, such as the central region characterized by low drainage standards and high-density urban areas, as well as the eastern region with low-lying terrain. Moreover, this study examined the spatial accessibility of rescue resources in real flood scenarios and found that their service coverage varied throughout the day during and after the disaster. In addition, social media excelled in high-density urban areas’ flood point extraction, while SAR performed better in monitoring floods at the edges of low-density urban areas and large water bodies, allowing them to complement each other, to a certain extent. The findings of this study provide scientific reference value for the optimal selection of rescue paths and the allocation of resources in the emergency response to urban floods caused by extreme rainstorms.

Location and path planning for urban emergency rescue by a hybrid clustering and ant colony algorithm approach

Rescue station setup and rescue path planning are two important tasks in urban emergency rescue. The former task ensures rescue response capability and the latter task provides effective rescue solutions. When emergencies occur in cities, evacuees are distributed along the urban road network. Rescue resources refer to rescue vehicles whose available number and capacity are both limited. With the constraints of rescue resources and the number of rescues, this paper aims to simultaneously optimize the tasks of rescue station setup and rescue path planning. In the addressed scenario, the priority of each evacuee is quantified as a weight value that is used as the main optimization objective. To solve the problem, a comprehensive urban emergency rescue planning approach is proposed. The proposed approach consists of components of road network processing, road network weight calculation, rescue station setup and rescue path planning. For the setup of rescue stations, this paper employs a clustering method to provide a set of high-quality candidate rescue stations for subsequent path planning based on the locations of evacuees and the road network structure. For rescue path planning, an improved ant colony optimization algorithm is developed. The proposed method is called the planning algorithm with clustering and improved ant colony optimization (PA-C-IACO). The proposed PA-C-IACO redefines the degree of heuristic and pheromone concentration increments for transfer between intersections in the ant colony algorithm and incorporates a reward mechanism during the pheromone update process. Experimental results on six different size datasets show that PA-C-IACO outperforms state-of-the-art algorithms and shows good robustness and feasibility.