Search for: All records

Buildings account for the largest share of accumulated materials and waste globally. Tracking the material composition, quantity and location of these materials, known as building material stock analysis (MSA), is a first step in enabling the reuse or repurposing of materials, key strategies of the circular economy. While the number of building MSAs is growing, there is a need to coalesce methods, data and scope. Therefore, in this work, we reviewed and evaluated 62 journal and conference articles on MSA of buildings from different angles including scope, boundaries, archetype classification, material intensity determination, approaches (i.e. bottom-up, top-down, remote sensing) and quantity of materials to identify barriers, gaps and opportunities in this area along with its implications for decision-making, policy and regulations. We cataloged the three major approaches of MSAs and discuss their advantages and shortcomings. We also created a comprehensive directory of building archetypes, references and materials for future researchers. As expected, most of the studies estimated that concrete had the largest mass compared with other materials; however, mass-based distribution of materials showed significant variations in different building stocks across the world. Also, embedded plastics and their types remain under-represented in current studies. A major barrier to MSA is related to a lack of information on physical attributes and geographic information system, design and construction data. Policy makers can play a role in mitigating data barriers through instituting regulations that enforce the reporting of building-related data during the permitting process. Furthermore, outcomes of building MSA can help policy makers when considering incentives for design and construction that utilize these abundant building materials.

 

Given the urgency of climate change, development of fast and reliable methods is essential to understand urban building energy use in the sector that accounts for 40% of total energy use in USA. Although machine learning (ML) methods may offer promise and are less difficult to develop, discrepancy in methods, results, and recommendations have emerged that requires attention. Existing research also shows inconsistencies related to integrating climate change models into energy modeling. To address these challenges, four models: random forest (RF), extreme gradient boosting (XGBoost), single regression tree, and multiple linear regression (MLR), were developed using the Commercial Building Energy Consumption Survey dataset to predict energy use intensity (EUI) under projected heating and cooling degree days by the Intergovernmental Panel on Climate Change (IPCC) across the USA during the 21st century. The RF model provided better performance and reduced the mean absolute error by 4%, 11%, and 12% compared to XGBoost, single regression tree, and MLR, respectively. Moreover, using the RF model for climate change analysis showed that office buildings’ EUI will increase between 8.9% to 63.1% compared to 2012 baseline for different geographic regions between 2030 and 2080. One region is projected to experience an EUI reduction of almost 1.5%. Finally, good data enhance the predicting ability of ML therefore, comprehensive regional building datasets are crucial to assess counteraction of building energy use in the face of climate change at finer spatial scale.