Mapping Heat Exposure of Pedestrian Density Around Metro Stations Using Artificial Intelligence: Ramses Square, Cairo, Egypt

Introduction

A massive literature group tackles the challenges of climate change and smart technologies in urban research. A group of studies looks at the effects of urban heat islands (UHIs) on cities and how this phenomenon affects user perceptions (Fang, et al., 2021; Roshan, Oji, & Fdez-Arróyabe, 2022; Hernandez & Monzon, 2016; Hutton, 2013). Numerous studies explore the urban heat island effect, which arises when cities replace the natural land cover with high pavement, buildings, and other heat-absorbing and heat-retaining surfaces (Elmarakby, Khalifa, Elshater, & Afifi, 2021; Elbardisy, Salheen, & Fahmy, 2021). This impact results in a rise in energy expenses (for example, air conditioning), air pollution levels, and heat-related unhealthy environments. Scholars address artificial intelligence (AI) to get the benefits of digital research methods. The literature describes AI as an influential technology with increasing applications in various fields. AI is the technology that enables machines to do cognitive functions that were always done by humans (Yigitcanlar, et al., 2020). While cities are now increasingly digitised, technology's role in urban fabrics has been widely covered (Hashem, et al., 2016). Literature acknowledges smart cities by using AI applications as an efficient tool to observe and model the creation of sustainable urban environments (Abusaada & Elshater, 2021a; Gessa & Sancha, 2020; Yigitcanlar, et al., 2018).

In this chapter, among various actions for achieving sustainable urban environments, we adapt the metro as a sustainable mode of public transportation (Falvo, Lamedica, Bartoni, & Maranzano, 2011; Khosravi, Haghshenas, & Saleh, 2020). The previous literature discussed how urban designers and planners play an essential role in reorienting people's daily travel decisions (Stojanovski, 2020; Middleton, 2011; Salonen & Toivonen, 2013). Providing a comfortable urban environment around stations may encourage people to use public transit (Rijsman, van Ort, Hoogendoorn, Molin, & Teijl, 2019). Capturing the behaviour of pedestrians in various situations is essential in urban planning, land use, marketing, or traffic operations (Antonini, Bierlaire, & Weber, 2005; Boarnet & Crane, 2001). Previous studies relied on several methods to provide qualitative and quantitative analysis of human behaviour in urban spaces (Rahaman, Ojmori, & Harata, 2005; Sarkar, 2003; Zakaria & Ujang, 2015).

This chapter tackles the challenges of metro transit as a primary transportation mode in Cairo, with more than three million people using the current three metro lines daily (Cairo Governorate Metro, 2021). This massive crowd of people might face problems in their daily commutes because of external factors like heat exposure. Metro commuters always need to use other public transportation methods or walk to reach their destinations. There are various pedestrian scenarios around metro stations. Pedestrians on Egyptian metro lines deal with different conditions throughout their door-to-door journey, from origin to destination.

Several studies have deliberated on the effects of outdoor thermal conditions on pedestrian behaviour in various shapes and urban spaces (Fahed, Ginestet, & Adolphe, 2020; Hendel, Azos-Diaz, & Tremeac, 2017; Sun, Zacharias, Ma, & Oreskovic, 2016). However, there is a lack of studies that use various AI applications to detect and model pedestrian behaviour and link it to changing thermal conditions. The gap in the literature is in providing quantitative analysis and mapping pedestrian movement patterns that can reflect their experience in a more precise way (Elias, 2011; Lesani & Miranda-Moreno, 2018). This study helped investigate the effect of the emergence of UHI effects and their physical elements on users’ experiences and comfort in the study area.