| Abstract |
From an urban planning perspective, accurately predicting urban block carbon emissions (UBCE) based on built environment factors is a good way to minimize UBCE as well as reduce urban heat islands. At a metropolitan level, this study gathered different wellsprings of information and proposed an AI strategy to foresee various elements of UBCE. Based on smart grid greenhouse gas emission and reinforcement learning, this study proposes a novel carbon footprint analysis method for sustainable building construction. In the proposed research, a novel hybrid optical wireless communications (OWC) topic is presented as a contribution to Internet of Things (IoT) devices of smart grids within smart sustainable cities. Among the rapidly evolving fields used in smart cities are OWC and IoT. The construction of the building is made with smart grid-based solar cells, and reinforcement learning is used to find the carbon footprint. The adaptive fuzzy convolutional multi-layer kernel vector neural network is then used to optimize the carbon footprint. It will discuss potential outcomes of structural engineering applications of machine learning and neural networks, and most importantly, it requires professional data from around the world to form a fundamental foundation that will speed up the transition to a more sustainable built environment. In terms of energy consumption, sensitivity, positive and negative predictive values, and training accuracy, the experimental analysis is carried out. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. |
