Neural Network-based Approach for Identifying the Influence of Factors affecting the Green Building Rating of a Rural Housing Construction
Kim Carlo A. Lat, Dario Landa-Silva, Kevin Lawrence M. de Jesus
Abstract
Environmental sustainability is a critical factor in all aspects of building. Recent years have seen a substantial rise in rural population growth, creating a need for housing developers to build more housing developments. Because of the rapid urbanization, environmental and energy-related problems have gotten a lot of attention, and promoting and implementing green building concepts has to turn out to be a major emphasis of innovative construction. Green construction is one of the recommended strategies for mitigating the negative environmental, social, and economic repercussions of the current building stock. As more industries transition to Industry 4.0, the utilization of machine learning (ML) techniques has become more common. The artificial neural network (ANN) - based approach using Garson's Algorithm (GA) was applied to establish the effect of different factors in the green building rating (GBR) schemes of Leadership in Energy and Environmental Design (LEED) and Building for Ecologically Responsive Design Excellence (BERDE), using LEED and BERDE-identified parameters such as Location and Transportation (LT), Water Efficiency (WE), Energy and Atmosphere (EA), Materials and Resources (MR), and Indoor Environmental Quality (IEQ). The findings indicated that the characteristics having the most effect on the LEED and BERDE green building (GB) grading systems are the general factors, and energy efficiency and conservation factors, respectively. The findings of the study indicated that using a sensitivity analysis (SA) technique based on neural networks is an effective technique for assessing and establishing the effect and impact of different variables.