Methods to Optimize Carbon Footprint of Buildings in Regenerative Architectural Design with the Use of Machine Learning, Convolutional Neural Network, and Parametric Design

Abstract

The analyzed research issue provides a model for Carbon Footprint estimation at an early design stage. In the context of climate neutrality, it is important to introduce regenerative design practices in the architect’s design process, especially in early design phases when the possibility of modifying the design is usually high. The research method was based on separate consecutive research works–partial tasks: Developing regenerative design guidelines for simulation purposes and for parametric modeling; generating a training set and a testing set of building designs with calculated total Carbon Footprint; using the pre-generated set to train a Machine Learning Model; applying the Machine Learning Model to predict optimal building features; prototyping an application for a quick estimation of the Total Carbon Footprint in the case of other projects in early design phases; updating the prototyped application with additional features; urban layout analysis; preparing a new approach based on Convolutional Neural Networks and training the new algorithm; and developing the final version of the application that can predict the Total Carbon Footprint of a building design based on basic building features and on the urban layout. The results of multi-criteria analyses showed relationships between the parameters of buildings and the possibility of introducing Carbon Footprint estimation and implementing building optimization at the initial design stage.

Circular Digital Built Environment: An Emerging Framework

“…Additive/Robotic Manufacturing "circular economy" AND ("3D printing" OR "additive manufacturing" OR robotic* OR "digital fabrication") AND (construction OR building OR "built environment") 24 8 [52,111,122,126,131,204] Artificial Intelligence "circular economy" AND (ai OR "artificial intelligence" OR "machine learning" OR "deep learning") AND (construction OR building OR "built environment") 16 5 [69,138,141,142,144]…”

“…Big data are used to train machine learning algorithms for designing low carbon regenerative buildings [138], supporting generative design tools [148], and assisting decision making in design processes [30]. Moreover, data mining techniques are employed for the improvement of buildings' energy performance [149] during the operational phase, leading to the lower use of resources.…”

“…Data-driven approaches, such as neural networks (a subset of Machine Learning), provide advanced solutions for the generation of multiple design alternatives and the selection of the most optimal design solution [69,137]. For example, researchers developed and tested a machine learning model to support architects during the early design phase, which can predict the total carbon footprint of regenerative building design alternatives [138].…”

Life Cycle Assessment as a Major Support Tool within Multi-Criteria Design Process of Single Dwellings Located in Poland

“…In recent decades, scientists around the world have been looking for solutions that would significantly reduce the environmental impact of construction. There are many works devoted to this topic in the literature [29][30][31][32][33][34]. Despite a considerable presence in the literature, there are still many problems to be solved.…”

“…The use of multi-criteria optimization seems necessary when choosing the optimal shape and construction technology of a facility with the goal of minimal environmental impact. Of course, many optimization methods described in the literature can be used [28,29,[35][36][37][38][39][40]. When choosing one of the simplest and most popular optimization methods, designers expect simple and easy-to-use tools to support the design process and the ability to perform a sensitivity analysis of the optimal solution.…”