hani rezaian

Nowadays, deep learning as a branch of artificial intelligence acts as an alternative for human with hopeful outcomes. Open Street Map as the biggest open source data is used as a complementary data sources for spatial projects. It is notable that is some advanced counties the accuracy of VGI data is higher than governmental official data. This research aims to use artificial intelligence to produce and subsequently promote completeness of OSM data. Res_UNet architecture was utilized to train landuse categories to the network. The result shows that IoU metric is about 83 percent that implies a high accuracy paradigm. Then, united-based method was used to calculated completeness of OSM data. The unit-based results show that completeness of building blocks, forest, fruits garden and agriculture land are: 3.6, 9.7, 90.4 and 81.88 respectively. It shows the low volunteer  participation rate to produce OSM data. On the other side the high accuracy achieved by deep learning leads us to complete OSM data by artificial intelligence instead of human prepared data. The advantage of using machine rather than human may be utilized in undeveloped countries or low density population regions as well as inaccessible areas.

The need to carry out the emergency evacuation of people from disaster-affected areas and their transfer to safe areas, in the shortest possible time and with the least number of injured, has made the issue of urban emergency evacuation a complex one in the real world. The complexity of the spatial layout of the courtyards and the presence of a large population within the Shrine, among which vulnerable groups also have a significant share, increase the probability of the population's vulnerability to natural and human disasters. Based on this, the current research was conducted to investigate the vulnerability of the pilgrims of Imam Reza's Shrine during the emergency evacuation caused by the crisis and what measures could reduce the vulnerability.

The present applied study was conducted based on a descriptive-analytical method. The required data were collected through documentary-library and field studies methods. The gathered data were analyzed using the Analytic Hierarchy Process model, fuzzy logic, and the Inverse Distance Weighting interpolation method in Arc GIS and Expert Choice software.

The findings of this study indicated that based on the presented integrated model, which included 7 variables of the length of the route, the number of nodes along the route, the number of nodes in the surrounding space of the settlement, fixed and passing population density, the ratio of the population to the width of the exit door, and distance from buildings, the highest level of a possible vulnerability in the Shrine was related to Rozeh Monavvareh, Goharshad Courtyard, Sheikh Bahaie Sanctuary, the western part of the Great Prophet Courtyard, and Bab-Al-Javad in descending order. The north and northeast parts of the Shrine had a low level of vulnerability for people's exit.

The results of this research showed that the presented model could be used as a suitable model in other religious places. In addition, some measures can be adopted to reduce the vulnerability of pilgrims, including increasing the number and width of the doors, removing obstacles in the place of the doors, and paying attention to the type of activities assigned to different parts of the Shrine.

Behavioural patterns of the people can affect the emergency evacuation procedure. The most important issue of crisis management is to evacuate the people from the accident site in the shortest time and with the maximum speed. Pilgrimage destinations attract many pilgrims on religious occasions, and this has highlighted the importance of addressing this issue in these centers. This study aimed to explain and propose an optimal evacuation exit plan for pilgrims during accidents in the most important and prominent religious center of Iran (Holy Shrine of Imam Reza).

This descriptive-analytical study was performed using an applied research method. The document-library and field methods were used to collect data. The statistical population includes the managers of the Holy Shrine complex, experts of the crisis management headquarters, consulting engineers in architecture and urban planning, as well as managers and experts in Mashhad Municipality. The sample size was estimated to be 384 cases based on Cochran's formula. The collected data via questionnaires were analyzed by SPSS and Smart PLS software using structural equation modelling.

According to the results, the presented model includes seven variables (group movement, individual movement, incident management technology tools, perception of the physical environment, physical movement, modelling, and behavioural culture) affecting the pilgrims leaving the incident site in the Holy Shrine of Imam Reza. 

The results of this study indicated that the presented model with 7 variables and 21 parameters can be used as a suitable model in other places.