Building industry is closely related to current energy and environmental issues. Several green building codes and rating systems addressing the problems have been developed. Leadership in Energy and Environmental Design (LEED) rating system is recognized as one of the effective and widely adopted commercial building standards. LEED buildings were investigated in several green city and green building studies but only used as instances in static matrices. These studies were not able to answer the question why a particular city favors LEED. However, in this paper, three commonly used machine learning algorithms – Linear Regression, Locally Weighted Regression and Support Vector Regression (SVR) – are compared and SVR is used to investigate, discover and evaluate the variables that could influence LEED building markets in U.S. East Coast cities. Machine learning models are first created and optimized with the features of city geography, demography, economy, higher education and policy. Then SVR model identifies the key factors by dynamic self-training and model-tuning using the dataset. Via optimization, the correlation coefficient between the model's prediction and actual value is 0.79. The result suggests that population and policy can be important factors for developing LEED buildings. It is also interesting that higher education institutions, especially accredited architecture schools could also be driving forces for LEED commercial building markets in East Coast cities.
Energy and environmental problems have become a critical concern for our society. The building sector, including commercial and residential has great impact on the issues. According to U.S. Department of Energy (DOE) Building Energy Data Book, in 2010 the total energy consumed by commercial and residential buildings accounted for 41% of total U.S. primary energy use, which has exceeded the consumption of the industrial (30%) and transportation sectors (29%) (Department of Energy, 2011a). Meanwhile, the building industry has negative impact on the environment, such as soil erosion, water pollution, construction waste, and ecological damage.
To address these problems, green building design, which primarily focuses on sustainable site, energy efficiency, water efficiency, environmentally friendly material, indoor environment quality, and other environmental aspects, has been well recognized as a next generation building design method. Numerous green building standards, codes, and evaluation systems have been developed globally. Leadership in Energy and Environmental Design (LEED) is one of the most popular rating systems. LEED was developed by the U.S. Green Building Council (USGBC) in 2000 and “it provides building owners and operators with a framework for identifying and implementing practical and measurable green building design, construction, operations and maintenance solutions” (U.S. Green Building Council, 2011b).
According to the USGBC project directory, the U.S. LEED building market has been growing dramatically since LEED was established in 2000. Fig. 1 shows the total number of LEED certified projects in the U.S. from 2000 to 2011. The average annual growth rate for the past 12 years is 103%.
Despite the economic recession which began in 2008, according to McGraw-Hill Construction, the value of green building construction increased 50% from 2008 to 2010 and represented 25% of total new construction activity in 2010 (Bernstein, 2010). Particularly, the author also mentioned that “LEED may impact growth of larger commercial green building market” by pointing out that, LEED projects certified between 2004 and 2009 have higher average value than non-LEED projects. In a nutshell, LEED has become an essential part and could be a driving force for the building industry in the U.S.
However, in different cities, the quantity of LEED certified projects varies significantly. It is worthwhile discovering the key factors that affect the popularity of LEED buildings in various places. By uncovering, investigating and advocating the influential features, LEED projects could be promoted through effective methods. In this research authors do not differentiate between platinum, gold, silver, and certified LEED projects. One reason is that data mining requires large dataset. However, the dataset for different levels of LEED certification is skewed. For example there are only 659 LEED Platinum buildings out of 11,377 LEED overall certified buildings for the entire U.S. over 12 years. It is nearly impossible to find general patterns for different cities with a small dataset. It is necessary to only consider quantity of all certified LEED buildings rather than separate them by levels of certification. In addition, this study tries to find reasons why people in a city favor LEED buildings. Instead of focusing on a few “deep green” projects that can achieve LEED Platinum awards, looking at a bigger all inclusive picture and encouraging more people to be involved in LEED activities will eventually raise the bar for the whole society.
Given the fact that LEED certified buildings are growing rapidly in the United States, a machine learning study is conducted to find influential factors that could shape the LEED commercial building market in the future. The number of LEED buildings in the East Coast cities, the geographic and demographic information, economic status, policy preference and the information of higher education institutions are trained. The model is built by Support Vector Regression based on performance comparison of three regression model building algorithms, LR, LWR and SVR. The correlation coefficient between the model's prediction and real data when it is applied to a new set of data is expected to be 0.79. The result analysis suggests that policy, population, and the quality and quantity of higher educational institutes, especially accredited architecture schools could be driving forces for the local LEED commercial building markets in the East Coast cities. With the purpose of promoting LEED or other green building concepts, in the East Coast region, the marketing strategy should be more focused on policy making and green building related education.
