We have a strong knowledge on integrating Machine Learning Models (MLM) into energy modeling for whole building renovation and construction. Our academic and professional experiences enable us to design a methodology for optimizing the energy performance of multiple building renovations considering Total Energy Consumption (TEC), Life cycle cost (LCC) and Life Cycle Assessment (LCA).

As the most recent experience, our team is involved in an ongoing research on evaluating the performance of different MLMs to estimate energy performance of whole building design and renovation. The objective of the study is evaluating the performance of surrogate MLMs for simulation in BEMs. More specifically, it aims to propose accurate MLMs to estimate TEC, LCC, and LCA using data from the Simulation-Based Multi-Objective Optimization (SBMO) model. The results of the MLMs are compared with SBMO models for accuracy. The output will fill the gap of current BEM that oversimplify the LCC and LCA impacts and enables the forecasting of the energy consumption of buildings. The proposed SBMO framework, which is integrated with MLM, takes advantage of the BIM model coupled with simulation. The first part of the study was published in the Journal of Building Engineering and presented in two conferences. 

In another research project, we observed that the mapping is a field that remains mainly unexplored in the BEM industry. Therefore, the lack of integrated data leads to an increase in the amount of effort required and a decrease in accuracy, which has a negative effect on the use of BEM at the urban level. We have applied SBOM in BEM to optimize energy consumption in large-scale buildings belonging to universities in Montreal, Canada. We did a pilot study focusing on an energy map of a university campus including data gathering, data analysis, and implementation. GIS and CityGML platforms were used for simulation of energy mapping at the urban scale. We also proposed the integration of GIS, CityGML, and district level BIM.

We have had successful experiences using GIS and BIM alongside BEM. We have been experimenting with new tools and possibilities for building CityGML models for downtown Montreal using the above-mentioned simulation tools. We focused on integrating BEM and BIM for visualizing, data management and sharing. Furthermore, we elected to use the Athena Impact Estimator, due to its ability to assess the whole building and its components.

We have also worked on development of an Urban Energy Map (UEM). UEMs are promising solutions that provide municipalities and planners with a better evaluation of energy consumption. This plays a significant role in creating energy efficient plans for cities. The initial results have been published in CRC2016.
Moreover, we have a significant experience in key collaborators in building and construction industries and environmental agencies on a variety of projects ranging from energy simulation, improving building envelope systems, integrating popular models with AI techniques, environmental impact assessment, LCA and LCIA, etc. We have organized many practical workshops and targeted events for designers, engineers, experts, and active players in building and energy industries to improve their knowledge, update the procedures, and enhance their method of thinking towards a sustainable world.