مطالب

INTRODUCTION: The structure of the urban platform of Tehran and its physical characteristics depends on the inherent conditions and environmental thresholds in relation to changes. This study aimed to determine the natural landscapes of Tehran by two phenomena of earthquake and flood that posed the highest risk in different periods of this city. Therefore, the natural perspective of Tehran is divided into three perspectives of north, central, and south regarding the inherent features and evolutionary process. METHODS: The relationship between the perspective of Tehran based on the form and geomorphological processes and the evaluation of earthquake and flood hazards have been observed in four stages, which included data collection, data processing, calculation of indicators, and analysis of findings. The studied area was divided into three northern, central, and south urban landscapes to determine the resistance thresholds of the city according to the characteristics of topography, physiography, geology, the results of field studies and satellite images, aerial photographs, as well as paleogeomorphological research in Tehran. FINDINGS: According to the zoning map of Tehran based on the earthquake phenomenon in three perspectives of north, center, and south, the highest distribution of non-resistance is observed in the northern and southern areas of the city. Northeast, southwest, and semi-western regions have the highest urban resilience to earthquakes. Moreover, regarding the zoning of Tehran based on the flood phenomenon in the three perspectives of north, center, and south, the highest distribution of non-resilience has been observed in the northern regions of the city. Northeast, southwest, and west of Tehran have the highest urban flood resilience. CONCLUSION: Based on the results of the present study, in order to increase resilience against the risks of earthquakes and floods, the city of Tehran should be studied not in just one perspective but in different perspectives.

Recent developments in Question Answering (QA) have improved state-of-the-art results, and various datasets have been released for this task. Since substantial English training datasets are available for this task, the majority of works published are for English Question Answering. However, due to the lack of Persian datasets, less research has been done on the latter language, making comparisons difficult. This paper introduces the Persian Question Answering Dataset (ParSQuAD) based on the machine translation of the SQuAD 2.0 dataset. Many errors have been discovered within the process of translating the dataset; therefore, two versions of ParSQuAD have been generated depending on whether these errors have been corrected manually or automatically. As a result, the first large-scale QA training resource for Persian has been generated. In addition, we trained three baseline models, i.e., BERT, ALBERT, and Multilingual-BERT (mBERT), on both versions of ParSQuAD. mBERT achieves scores of  56.66% and 52.86% for F1 score and exact match ratio respectively on the test set with the first version and scores of 70.84% and 67.73% respectively with the second version. This model obtained the best results out of the three on each version of ParSQuAD.