Krayem Alaa, Yeretzian Aram, Faour Ghaleb, Najem Sara
Physics Department, American University of Beirut, Beirut, Lebanon.
Architecture and Design, American University of Beirut, Beirut, Lebanon.
PLoS One. 2021 Jan 28;16(1):e0246096. doi: 10.1371/journal.pone.0246096. eCollection 2021.
In this paper we focus on a critical component of the city: its building stock, which holds much of its socio-economic activities. In our case, the lack of a comprehensive database about their features and its limitation to a surveyed subset lead us to adopt data-driven techniques to extend our knowledge to the near-city-scale. Neural networks and random forests are applied to identify the buildings' number of floors and construction periods' dependencies on a set of shape features: area, perimeter, and height along with the annual electricity consumption, relying a surveyed data in the city of Beirut. The predicted results are then compared with established scaling laws of urban forms, which constitutes a further consistency check and validation of our workflow.
在本文中，我们聚焦于城市的一个关键组成部分：其建筑存量，它承载着城市的大部分社会经济活动。就我们的情况而言，由于缺乏关于其特征的全面数据库，且该数据库仅限于一个调查子集，这促使我们采用数据驱动技术将我们的知识扩展到近城市尺度。我们应用神经网络和随机森林，依据贝鲁特市的调查数据，根据一组形状特征（面积、周长和高度）以及年耗电量来确定建筑物的层数和建造时期的相关性。然后将预测结果与已确立的城市形态缩放定律进行比较，这构成了对我们工作流程的进一步一致性检查和验证。
