The purpose of this master thesis is to develop a model to estimate the carbon intensity, i.e the carbon emission relative to economic activity, of publicly traded companies which do not report their carbon emissions. By using statistical and machine learning models, the core of this thesis is to develop and compare different methods and models with regard to accuracy, robustness, and explanatory value when estimating carbon intensity. Both discrete variables, such as the region and sector the company is operating in, and continuous variables, such as revenue and capital expenditures, are used in the estimation. Six methods were compared, two statistically derived and four machine learning methods. The thesis consists of three parts: data preparation, model implementation, and model comparison. The comparison indicates that boosted decision tree is both the most accurate and robust model. Lastly, the strengths and weaknesses of the methodology is discussed, as well as the suitability and legitimacy of the boosted decision tree when estimating carbon intensity. / Syftet med denna masteruppsats är att utveckla en modell som uppskattar koldioxidsintensiteten, det vill säga koldioxidutsläppen i förhållande till ekonomisk aktivitet, hos publika bolag som inte rapporterar sina koldioxidutsläpp. Med hjälp av statistiska och maskininlärningsmodeller kommer stommen i uppsatsen vara att utveckla och jämföra olika metoder och modeller utifrån träffsäkerhet, robusthet och förklaringsvärde vid uppskattning av koldioxidintensitet. Både diskreta och kontinuerliga variabler används vid uppskattningen, till exempel region och sektor som företaget är verksam i, samt omsättning och kapitalinvesteringar. Sex stycken metoder jämfördes, två statistiskt härledda och fyra maskininlärningsmetoder. Arbetet består av tre delar; förberedelse av data, modellutveckling och modelljämförelse, där jämförelsen indikerar att boosted decision tree är den modell som är både mest träffsäker och robust. Slutligen diskuteras styrkor och svagheter med metodiken, samt lämpligheten och tillförlitligheten med att använda ett boosted decision tree för att uppskatta koldioxidintensitet.

The residential building sector plays an important role in combating climate change in Canada. Many energy efficiency solutions along with new building energy standards have been implemented to improve building energy performance. However, their effects on energy saving and GHG emissions reduction vary due to the complexity of the building systems and the variability of their operational conditions. This work quantifies such variability in both energy efficiency devices and building energy standards implementation, respectively. The first study in this dissertation assesses the energy savings from sensible heat recovery in a residential apartment suite in various locations across Canada. A series of detailed building energy performance models are developed in TRNSYS. The HVAC system’s annual energy consumption is simulated and the results are compared with and without HRV for each climate zone. The results show the heating energy savings of employing the HRV vary from 17 to 34% depending on the winter climatic conditions; while, the building cooling energy use can be increased due to the undesired thermal recovery occurring in the HRV during the cooling season. The second study investigates the free cooling potential of outside air in various Canadian cities. A series of thermal models developed using BEopt 2.8 for a hypothetical single-family house with various window-to-wall ratios and building aspect ratios simulates hourly building cooling load profiles. The free cooling potential is analyzed by comparing the maximum available and the actual usable free cooling for various building features and different climates. The results indicate that, although free cooling is widely available in most areas of Canada during the summer and shoulder seasons, only 17-42% of such free cooling is usable without the use of thermal storage. The last study examines the effects of two building energy standards - the BC Step Code and the Passive House criteria - on reductions in residential household space heating GHG emissions under different enforcement scenarios. The space heating energy and the GHG emissions are estimated using the forecast growth of single detached households for the period from 2020 to 2032. The results show that the space heating GHG emissions can be reduced by 77% and 89%, respectively if the BC Step Code or the Passive House criteria is implemented in Canada. It is also found the impacts of energy code on GHG emission mitigation are less significant in regions where the carbon intensity of the dominant heating fuels is low. / Graduate