Investigation of urban climates and built environment relations by using machine learning

Applications of machine learning and deep learning methods for climate change mitigation and adaptation

“…On the other hand, adaptation focuses on the importance of resilience planning and catastrophe management for coping with climate change impacts (Nalau and Verrall 2021; Rolnick et al, 2019). Even though countless research on climate change adaptation and mitigation has been undertaken worldwide, complete success does not appear to be attainable (Koc and Acar 2021). The changing equipment and methods used to collect enormous volumes of climate data are beyond the human skills and processing power of modern climate science, resulting in an increasing requirement for technology-based research tools (Koc and Acar 2021).…”

“…Climate data are increasingly abundant due to technological advancements, model simulations, sensors, and observers (Faghmous and Kumar, 2014; Koc and Acar 2021). At the same time, advances in computer science theory, mathematical research, and processing power equip us with the tools we need to gather the data (Milojevic-Dupont and Creutzig, 2021).…”

“…Artificial intelligence applications such as machine learning (ML) have become increasingly popular in recent years as a versatile tool for technological advancement (Rolnick et al, 2019). Machine learning is a field of artificial intelligence in which algorithms use large data sets to discover patterns (Abduljabbar et al, 2019; Huntingford et al, 2019; Koc and Acar 2021; Vapnik, 1999). It is a fast-evolving and helpful tool for comprehending complicated networks, identifying knowledge in big data, and generating future forecasts (Koc and Acar 2021).…”

“…Machine learning is a field of artificial intelligence in which algorithms use large data sets to discover patterns (Abduljabbar et al, 2019; Huntingford et al, 2019; Koc and Acar 2021; Vapnik, 1999). It is a fast-evolving and helpful tool for comprehending complicated networks, identifying knowledge in big data, and generating future forecasts (Koc and Acar 2021). Machine learning techniques have contributed to a variety of application fields, such as transportation management, urban planning, distribution of resources, forecasting energy requirements, forecasting food security and supply, and monitoring as well as forecasting poor air quality, etc.…”

“…(Audu et al, 2020; Nosratabadi et al, 2019; Wataya and Shaw, 2019). Given that the climate change issue is extremely complex and necessitates multidisciplinary research (Huntingford et al, 2019), the usage of ML techniques has shown to be a helpful tool for realizing and predicting climate-related issues (Koc and Acar 2021). In general, ML can be classified into two categories: supervised and unsupervised (Murphy 2012).…”