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

Abstract

Climate change can cause a cascade of effects from the individual organisms to ecosystem-scale where in nature, all species are elements of complex networks of interactions. Hence, every impact on every scale has a significant role. Those properties of the networks are decisive on the global ecosystem, so how they will be modified by climate change needs serious studies. The vast population of the urban areas exerts significant effects on climate change even though they cover a small proportion of the surface of the Earth; however, impacts of urbanization on climate and ecosystems remain inadequately understood. In the meantime, urbanization continues to increase and in 2030, two-thirds of the population is expected to be living in urban areas with an increasing rate in time. It is of great importance to elaborate on the relations between urbanization and climate. In this respect, the use of information technologies with an extensive computational capacity is one of the cornerstones of climate and urban studies.& nbsp; Machine learning is a branch of computer science that deals with the automated recognition of patterns from data. The use of machine learning algorithms can bring significant advantages to both understandings and predicting the climate. The computational power with big data, their ability to capture nonlinear behavior, and learn as new data arrive make machine learning a useful tool for understanding climate and developing urban planning. In this sense, the purpose of this study is to show the advantages of machine learning algorithm by developing a recurrent neural network algorithm to make climate predictions and stating possible effects of machine learning on design and its contribution to understanding the climate.