The Methods of Deep Learning and Big Data Analysis in Promoting Sustainable Architecture

Abstract

These days, sustainability in different aspects has been among the main discussions of architecture and building science. At the same time, historic architecture has evolved over centuries and has adapted to environmental conditions, it can be a great source of inspiration in using smart ways to achieve sustainable architecture. A good illustration of this adaptation can be found in using vernacular materials, the spatial configuration according to climate conditions, and different elements of historic architecture that have helped to improve the occupant’s comfort. In response, one plausible solution for improving the sustainability of architecture is translating the concept of the sustainable elements and features of historic architecture to be used in contemporary architecture. Therefore, these elements need to be studied thoroughly to comprehend their features and characters. There are several studies, investigating sustainable historic architecture to find and measure sustainable solutions by using conventional methods. Although the accuracy of studying the sustainable historic elements has been fairly high, the number of features and variety of these elements in historic architecture have made this task highly challenging. It has been suggested to study and evaluate a considerable number of these elements in different historic architecture to reduce the errors and increase the reliability of results. Since the conventional methods are labor-intensive, time-consuming, and costly, this paper proposed a robust AI method to study the sustainable elements of historic architecture by using Deep Learning. In this study, by introducing and developing a new method for detecting sustainable elements in historic architecture, their features were comprehensively extracted by means of mining meaningful data from areal images of historic cities to produce big data. The proposed method has a sophisticated workflow starting from subdividing the High-Resolution Aerial Images to detecting the sustainable elements and using data science to analyze the extracted features of the segmented objects. Results of a sample analysis of this method showed its high accuracy and its applicability in analyzing sustainable elements of historic architecture, by which designers are expected to design more sustainable buildings inspired by historic architecture.