Predicting and identifying traffic hot spots applying neuro-fuzzy systems in intercity roads

Providing safety in roads for the purpose of protecting human assets and preventing social and economic losses resulted from road accidents is a significant issue. Identifying the traffic hot spots of the roads provides the possibility of promoting the road safety which is also related to investigate frequency and intensity of occurred accidents. Accidents are multidimensional and complicated events. Identifying the accident factors is based on applying a comprehensive and integrated system for making decisions. Therefore, applying common mathematical and statistical methods in this field can be resulted in some problems. Hence, the new research methods with abilities to infer meaning from complicated and ambiguous data seem useful. Therefore, along with identifying the traffic hot spots, adaptive Neuro-Fuzzy inference system is used to predict traffic hot spots on rural roads. In this process, a fuzzy inference system from Sugeno type is trained applying hybrid optimization routine (back propagation algorithm in combination with a least square type of method) and accident data of Karaj-Chalus road in Tehran Province. Then the system was tested by a complete set of data. Finally, the stated system could predict 96.85 % of accident frequencies in the studied blocks. Furthermore, the amount of effective false negative in all cases included only 0.82 % of predictions, which indicated a good approximation of predictions and model credibility.     

Spatio-temporal analysis of road traffic accident fatality in Bangladesh integrating newspaper accounts and gridded population data

Road traffic accidents pose serious threats to human lives and often cause premature deaths, disabilities, and socioeconomic impacts. The objective of this study is to analyze the fatal road traffic accidents in Bangladesh by performing a space–time characterization of fatality rates involving an innovative newspaper-based method in concert with gridded population data to construct a road traffic fatality database. Kernel density estimation, temporal data plots and space–time pattern mining tools that combine the Getis-Ord Gi* statistic with the Mann–Kendall test are used to describe spatio-temporal hotspots/coldspots and trends. Results show different patterns between the urban and rural areas of Bangladesh and higher rates of road traffic accidents occur in the metropolitan regions (Dhaka) and in a northern region centered on Sirajganj area. Most of the road traffic accidents took place in between 9:00 and 12:00 pm while the accident rates remain low between 12:00 and 3:00 am. Spacetime analysis results reveal a core region of persistently high rates along with four smaller regions with high and intensifying rates. The output of this study could be useful to reduce road traffic fatalities, injuries, increase awareness, and adopt necessary interventions for public safety through integrating both the local, regional, and central level decision makers of public transportation policy and issues in Bangladesh. The approach has potential to be translated to other developing countries.     

A GIS framework for evaluating the implications of urban road network failure due to earthquakes: Bucharest (Romania) case study

Through this paper we propose and test a GIS framework that addresses the issue of seismic risk due to urban road network failure. The approach relies on full GIS integration, on Monte Carlo simulations for generating potentially disrupted network configurations, considering also the damage probability due to direct earthquake implications, and on traffic considerations (both in typical and post-earthquake situations). The damage probability can be obtained using fragility functions for critical structures like bridges and tunnels or by determining empirically the possibility of affected buildings to generate debris leading to road obstruction. Multiple performance indicators such as travel time and distance under various conditions are combined, in order to quantify the risks inflicted by dysfunctionalities in the emergency intervention process. The framework considers at the same time temporal and spatial dimensions, being able to cope with traffic dynamics or reconfigurable network configurations. The ArcGIS Network Analyst Module is used for model integration, and full city scale analysis is performed in order to test the capabilities. Bucharest (capital of Romania) is selected for the case study; this 2 million inhabitant city is one of the most endangered in Europe, due to earthquakes that occur in the Vrancea Area, at intermediate depth, with moment magnitudes > 7, but also due to the vulnerable building stock. Beside this, it is one of Europe’s top cities when it comes to traffic congestion. The results of the study provide initial insights on the deficiencies of the city’s road network and connectivity limitations, showing the high impact of road obstructions and traffic congestion on intervention times, for ambulances and firefighters, in case of an earthquake.     

A GIS framework for evaluating the implications of urban road network failure due to earthquakes: Bucharest (Romania) case study

Through this paper we propose and test a GIS framework that addresses the issue of seismic risk due to urban road network failure. The approach relies on full GIS integration, on Monte Carlo simulations for generating potentially disrupted network configurations, considering also the damage probability due to direct earthquake implications, and on traffic considerations (both in typical and post-earthquake situations). The damage probability can be obtained using fragility functions for critical structures like bridges and tunnels or by determining empirically the possibility of affected buildings to generate debris leading to road obstruction. Multiple performance indicators such as travel time and distance under various conditions are combined, in order to quantify the risks inflicted by dysfunctionalities in the emergency intervention process. The framework considers at the same time temporal and spatial dimensions, being able to cope with traffic dynamics or reconfigurable network configurations. The ArcGIS Network Analyst Module is used for model integration, and full city scale analysis is performed in order to test the capabilities. Bucharest (capital of Romania) is selected for the case study; this 2 million inhabitant city is one of the most endangered in Europe, due to earthquakes that occur in the Vrancea Area, at intermediate depth, with moment magnitudes > 7, but also due to the vulnerable building stock. Beside this, it is one of Europe’s top cities when it comes to traffic congestion. The results of the study provide initial insights on the deficiencies of the city’s road network and connectivity limitations, showing the high impact of road obstructions and traffic congestion on intervention times, for ambulances and firefighters, in case of an earthquake.

     

Assessment of potential sediment disasters and resilience management of mountain roads using environmental indicators

In recent years, extreme rainfall events occur frequently, causing serious watershed sediment disasters, destroying mountain roads, and endangering the safety of residents' lives and property. This study aims to deal with the spatial change of potential sediment movement on the road slope pre-disaster and to screen disaster hot spots for early warning and control system. The conceptual model is used to simulate the distribution of primary and/or derived disasters on a watershed scale to assess the impact of sediment disasters caused by heavy rain event. Correlation analysis shows that the models in assessment of primary disaster and derived disaster are significantly correlated with the collapse ratio and disaster ratio, respectively. Since the primary disaster has been considered when calculating the derived disaster risk, the terrain subdivision along Provincial Highway 21 (Tai-21) is extracted to understand the derived sediment disaster on the road slope. The model can effectively evaluate the road sections prone to disasters. According to the risk level, the hot spot of road slope disasters and the management of disaster resilience are determined and can be the reference for disaster prevention and control.

     

Hot spots of wetland vegetation reduction in relation to human accessibility: differentiating human impacts on natural ecosystems at multiple scales

Human activities have profoundly influenced natural ecosystems, especially wetlands. This study attempted to differentiate the impact of human activities on reductions in wetland vegetation in the Lixiahe wetlands, China, at multiple spatial scales. The reduction in wetland vegetation from 1988 to 2006 was quantified using Landsat data, and moving window analysis was used to detect hot spots of vegetation reduction in the wetlands at window sizes of 150, 1,000 and 2,500 m. Logistic regression was used to examine the influence on occurrence of the hot spots of landscape variables representing accessibility to human settlements and roads. Over the study period, wetland vegetation declined by 69%, which was largely attributable to aquaculture development. The hot spots of wetland vegetation reduction exhibited increasing patch size, but decreasing patch number with increasing window size. The occurrence probability of the hot spots rose significantly with increasing proximity to rural settlements and secondary roads, with only a minor response to the presence of towns. With increasing window size, however, the density of secondary roads and rural settlements were less influential, whereas the presence of major roads had more influence on hot spot occurrence. These trends are reasonable in that wetland use activities in the study area are directly associated with the settlements and roads in the rural areas at local scales, but are also indirectly associated with the major transportation network from a regional perspective. Overall, these results suggested that different human activities, as distinguished by their sources on the landscape, could have different environmental consequences at different scales for scale-dependent features.     

An epidemiological approach to determining the risk of road damage due to landslides

Disruption of segments of roads can have a significant impact on the vulnerability of the entire network. Natural disasters are frequent causes of disruptions of this kind. This article focuses on determining the risk of road disruptions due to landslides. Our approach is based on methodology widely used in the field of epidemiology. We had available data on the location of the landslides, the road network and a list of the disrupted road segments. With the use of a 2 × 2 table, we determined the relationship between landslide data and road segment disruptions and derived the risk coefficient based on the number of landslides in the vicinity of the road and its length. The result is a disruption risk map with risk coefficients ranging from 0 to 47.94. In order to distinguish the most risky segments, we calculated a threshold of 12.40 with the use of a risk breakdown in a group of segments without damage. Nineteen percentage (402 km) of the road network in the Zlín region (Czech Republic), where the methodology was applied, is located beyond this threshold. The benefits of this approach stem from its speed and potential to define the most risky areas on which a detailed geomorphologic analysis can be focused.     

The assessment of traffic accident risk based on grey relational analysis and fuzzy comprehensive evaluation method

The traffic accident risk includes three aspects, traffic accident probability, traffic accident severity, and traffic accident trend respectively. In this paper, nine indicators are selected to evaluate the traffic accident risk. The grey relational analysis method was used to determine the weights, and the fuzzy comprehensive evaluation method was used to calculate the risk. These methods were applied to assess the comprehensive risk of traffic accident in 31 provinces in China. The results show that the average value of traffic accident risk is 55.17. Nine provinces which are located in the northwest area and southeast area belong to the high-risk level. The medium-risk areas are widely distributed in the central, northeast, and southwest regions. The low-risk areas are Jilin, Neimenggu, Guizhou, and Beijing. The results have great significance for the measurement and management of regional traffic accident risk.     

Bayesian analysis of school bus accidents: a case study of China

Natural Hazards - Prevention and control of school bus accidents have been a hot spot topic around the world. The catastrophic accident can result in severe casualties associated with negative...     

Risk assessment of the areas along the highway due to hazardous material transportation accidents

As the industrialization process accelerates in developing countries, road accidents involving hazardous materials are increasing, and the threat associated with these accidents to areas along the highway cannot be ignored. The main objective of this paper is to contribute information regarding risk quantification, risk prevention, and control by government managers in areas along the highways. Thus, the risk assessment of the area along the highway (RAAH) method was established and applied as a regional risk prevention policy. Considering that the damage caused by accidents can vary substantially between different surroundings, the RAAH method was used as an integrated function comprising of accident frequency, intensity and vulnerability along the route, and the vulnerability system reflected the characteristics of the social and environmental factors in the study area. Then, in this study, we implemented this assessment model in geographic information system and applied it to a typical section of the Beijing–Tibet Highway in Beijing, China, to demonstrate its functionality and utility. A risk map was successfully obtained, and it showed that this method not only effectively reveals the neglected high-risk units but also can be used to provide technical support to the regional government to identify the blind spots and strengthen their risk management.     

Temporal and spatial evaluation of environmental noise in urban area: a case study in Iran

Environmental noise pollution is a disrupting factor in the urban areas which can lead to adverse health effects, behavior and quality of life. Present study was carried out in Tabriz (Iran) and aimed to achieve a real condition of noise pollution. Thirty-five measurement stations were selected, and noise levels were recorded. The equivalent noise level in (A) frequency weighting network, route-mean-square sound pressure level, minimum sound pressure level, maximum sound pressure level and noise pollution level were computed as applicable indices. Temporal and spatial variability of these noise indices were plotted by Arc GIS. Public awareness about the noise pollution was assessed through interview. Mixed model and pairwise comparisons were used for comparison of noise indices based on stations and times. It was found that noise levels were significantly different and higher than permissible levels at most stations, especially at heavily travelled crossroads and squares. Mean equivalent noise level for morning, noon, afternoon and night was 71.35 ± 7.49, 71.63 ± 4.90, 70.67 ± 4.52 and 68.74 ± 5.22 dB(A), respectively. The noise indices of all stations and measurement times had significant difference (p value = 0.028 and 0.019, respectively). It was observed that in normal traffic, the highest sound levels are produced by buses, trucks and motorbikes due to low-technology engines. Using the horn was the first reflex of the most drivers. A main part of the noise pollution problem of the studied city can be attributed to driving culture and non-compliance with traffic laws.     

Crowdsourcing photograph locations for debris flow hot spot mapping

This study shows the feasibility of obtaining hazardous hot spot information on landslide and debris flow from crowdsourced data. Historical hazard or disaster photographs were voluntarily uploaded by the public to a Web photograph album. A total of 2245 hazard photographs from 1973 to 2015 were crowdsourced, and each photograph was tagged with geographical coordinates. After the removal of outliers, 96% of the photograph points were found within the 4 km potential debris flow buffer of existing databases, and none was found along the steep slopes with a mean of 14°. The photograph hot spot analysis using local Moran’s I or G _i * was identified statistically significant without subjective judgment. The DBSCAN model was also used to detect hot spot clusters effectively. The model parameters were nearly automatically generated on the basis of the count plot and the nearest neighbor distance graph. The results of these approaches were generally consistent with the hazardous hot spot maps and strongly related to central and southern Taiwan from the crowdsourced photograph data. Results reveal that the hot spot areas are found in areas with faults and near the potentially weak and fractured rocky regions. The majority of the landslides occur near the fault line because the strong ground motions triggered by an earthquake propagated along the fault rupture plane. Hot spot mapping using crowdsourced data can be used to estimate where debris flow will frequently occur and show how large the debris flow will be. Potentially hazardous areas can be effectively determined by the hot spot analysis of crowdsourced data.     

The effects of hydrometer reading times on the spatial variability of soil textures in southeast Iran

Soil texture is an important physical soil property that may contribute to variations in many soil functions as well as nutrient storage and availability, water retention, and soil erosion. Although several methods for determining the texture classes of soil particles have been proposed, differences among hydrometer reading times have presented challenges in determining the precise soil texture classes. Therefore, this study was conducted to evaluate the effects of hydrometer reading time on the spatial variability of soil textures in the Rafsanjan area, southeast Iran. To accomplish this, 77 soil samples were collected on a 500-m square sampling grid from depths of 0–40, 40–80, and 80–120 cm, and their particle sizes were determined through analysis for 40 s, 2 h, 6.5 h, and 8 h using the Bouyoucos hydrometer method. The results showed a strong spatial correlation in the soil particles among sampling soil layers and across the study area. Moreover, the differences among hydrometer reading times did not have a significant impact on determination of coarse soil texture classes, although they did influence determination of the finer classes. Although the 8 h reading time provided the most accurate response with respect to mechanical analysis of a soil, after 6.5 h the hydrometer could also largely (more than 80.0 %, on average) achieve this goal. Additionally, the 2 h hydrometer reading time could also be useful for the initial assessment or general overview of the soil texture in a certain region; however, it is not recommended for precision agriculture or site-specific management.     

Analysis of precipitation extremes based on satellite (CHIRPS) and in situ dataset over Cyprus

A study of a daily precipitation database for the island of Cyprus is performed for a period of 30 years. A number of climatic indices for precipitation are calculated using the recently available CHIRPS dataset, on high spatial (0.05°) and temporal (daily) resolution. The same parameters for the same time period (1981–2010) are then calculated using the dense network of rain gauges of the Cyprus Department of Meteorology. The results show a quite promising performance regarding indices related to daily precipitation thresholds, resulting in high correlation scores. In the case of indices referring to number of days, it seems that the results are ambiguous, with medium or no correlation, probably related to the criteria used for the identification of a wet (rainy) day on the CHIRPS dataset.     

西安都市圈道路网络化对景观格局的影响

在快速城市化过程中,道路网络快速扩张对区域生态景观的分割、隔离、破坏等是导致生态景观过程与格局演变的重要原因。研究道路网络化对景观格局的影响可为快速城市化地区生态、道路建设和区域可持续发展规划提供参考。本文以西安都市圈为例,利用GIS和RS技术,基于西安都市圈TM遥感影像和Arcgis 10.1、Fragstats 4.2软件平台,通过构建道路网空间指数,定量评价了路网空间结构和景观格局变化,并从空间上分析了道路网络化对景观格局的影响。结果表明:1)1985—2015年,西安都市圈路网发育不断成熟,基本呈现以西安市区为中心、空间指数向四周递减(除杨陵区和阎良区外)且东高西低的趋势。2)随着城市化进程的不断推进,西安都市圈景观呈现多样化、复杂化和破碎化。其中:园地、林地和建设用地规模扩大,景观聚集度上升;耕地、水域及滩涂景观破碎化程度不断加深。3)30年间,高等级道路的修建、低等级道路的不断完善以及市内环路打通等,使得西安都市圈路网逐渐完善,景观优势度下降,破碎化程度上升,形状趋于规则化。此外,路网发育的程度不同对不同地类的影响各不相同:路网成熟的区域,建设用地面积较多,形状较规则,呈聚集状态,林地面积较少,且零星分布,破碎化程度较高;道路结构简单的区域,林地聚集成片,聚集度较高,耕地、水域及滩涂在路网空间指数各等级影响域内均呈现破碎化状态,且形状较不规则。     

空间数据智能统计方法研究与软件实现

在进行空间数据统计分析的过程中,为了提高统计工作的效率,笔者采用C#+Arc Engine和数据库融合的开发模式,利用循环与数据库方法计算空间图斑数量、位置和面积等信息实现单属性和多属性自动分类统计,图斑质心八方向方位统计法确定图斑的空间位置,chart和word API方法实现地图数据的图表化和语言化表达。研究结果表明:将属性数据和空间数据分离可以实现空间数据准确高效地统计,循环和数据库方法的应用实现了空间数据的单属性和多属性分类统计;图斑质心八方向方位统计法的应用提高了空间统计的效率; chart和word API方法实现了属性数据统计图的自动生成以及地图数据报表化的自动生成与发布。     

A novel hybrid integration model using support vector machines and random subspace for weather-triggered landslide susceptibility assessment in the Wuning area (China)

This study proposed a hybrid modeling approach using two methods, support vector machines and random subspace, to create a novel model named random subspace-based support vector machines (RSSVM) for assessing landslide susceptibility. The newly developed model was then tested in the Wuning area, China, to produce a landslide susceptibility map. With the purpose of achieving the objective of the study, a spatial dataset was initially constructed that includes a landslide inventory map consisting of 445 landslide regions. Then, various landslide-influencing factors were defined, including slope angle, aspect, altitude, topographic wetness index, stream power index, sediment transport index, soil, lithology, normalized difference vegetation index, land use, rainfall, distance to roads, distance to rivers, and distance to faults. Next, the result of the RSSVM model was validated using statistical index-based evaluations and the receiver operating characteristic curve approach. Then, to evaluate the performance of the suggested RSSVM model, a comparison analysis was performed to other existing approaches such as artificial neural network, Naïve Bayes (NB) and support vector machine (SVM). In general, the performance of the RSSVM model was better than the other models for spatial prediction of landslide susceptibility. The AUC results of the applied models are as follows: RSSVM (AUC = 0.857), followed by MLP (AUC = 0.823), SVM (AUC = 0.814) and NB (AUC = 0.783). The present study indicates that RSSVM can be used for landslide susceptibility evaluation, and the results are very useful for local governments and people living in the Wuning area.     

Towards a spatial data infrastructure for technological disasters: an approach for the road transportation of hazardous materials

Spatial data have been used for the environmental monitoring of the consequences of accidents that involve the transportation of hazardous chemical products. This spatial data infrastructure (SDI), which was created for the sharing and use of spatial data, is limited by the absence of policies to support its establishment. The main objective of this study was to explore the use of social network analysis (SNA) as a tool to identify spatial data sharing between organizations involved in the management of accidents related to road transport of hazardous materials (RTHM). In addition, to discuss the existing policies and institutional agreements, and to initiate a conceptual SDI framework for RTHM sector. In this context, the institutions that are involved with RTHM were identified and information concerning their interest in the use and sharing of spatial data via a SDI was collected through interviews and consolidated. The interviews were at 39 institutions with representative employees. The interview data were tabulated and entered into the UCINET software (2000 version) to calculate metrics of centrality. From the SNA, the flow of data among the participating institutions was identified through the visual representation of the spatial data sharing and use networks. Subsequently, the existing institutional agreements for spatial data sharing were analyzed and discussed. The compiled results enabled the proposal of a conceptual SDI framework to support the management of disasters involving RTHM, based on the application of SNA theory, and the development of a methodology that supports the analysis of interactions among the various actors of an SDI. The purpose is to facilitate the formulation of policies for the sharing of spatial data for decision-making and preventive disaster management. The results indicate that the 39 institutions share spatial data, but this sharing is not always predetermined by formal agreements. Furthermore, there is a strong demand, by the institutions involved in the management of RTHM accidents, regarding legal mechanisms governing the sharing of data for the purpose of producing maps that help to describe actions of preparedness, prevention, management and immediate relief involving RTHM incidents. Finally, it was possible to propose a conceptual framework with data that is considered essential for creating an SDI for RTHM.     

Probabilistic risk assessment of major accidents: application to offshore blowouts in the Gulf of Mexico

Major accidents are low-frequency, high-consequence accidents which are not well supported by conventional statistical methods due to the scarcity of directly relevant data. Modeling and decomposition techniques such as event tree have been proved as robust alternatives as they facilitate incorporation of partially relevant near accident data–accident precursor data—in probability estimation and risk analysis of major accidents. In this study, we developed a methodology based on event tree and hierarchical Bayesian analysis to establish informative distributions for offshore blowouts using data of near accidents, such as kicks, leaks, and failure of blowout preventers collected from a variety of offshore drilling rigs. These informative distributions can be used as predictive tools to estimate relevant failure probabilities in the future. Further, having a set of near accident data of a drilling rig of interest, the informative distributions can be updated to render case-specific posterior distributions which are of great importance in quantitative risk analysis. To cope with uncertainties, we implemented the methodology in a Markov Chain Monte Carlo framework and applied it to risk assessment of offshore blowouts in the Gulf of Mexico.     

Using spatial statistics to identify the uranium hotspot in groundwater in the mid-eastern Gangetic plain,India

The occurrence of uranium in groundwater is of particular interest due to its toxicological and radiological properties. It has been considered as a relevant contaminant for drinking water even at a low concentration. Uranium is a ubiquitously occurring radionuclide in the environment. Four hundred and fifty-six (456) groundwater samples from different locations of five districts of South Bihar (SB) were collected and concentrations of uranium (U) were analyzed using a light-emitting diode (LED) fluorimetric technique. Uranium concentrations in groundwater samples varied from 0.1 µg l^?1 to 238.2 µg l^?1 with an average value of 12.3 µg l^?1 in five districts of Bihar in the mid-eastern Gangetic plain. This study used hot spot spatial statistics to identify the distribution of elevated uranium concentration in groundwater. The hypothesis whether spatial distribution of high value and low value of U is more likely spatially clustered due to random process near a uranium hotspot in groundwater was tested based on z score and Getis-Ord Gi* statistics. The method implemented in this study, can be utilized in the field of risk assessment and decision making to locate potential areas of contamination.