@inproceedings{simbuild2024_2186,
	doi = {},
	url = {https://publications.ibpsa.org/conference/paper/?id=simbuild2024_2186},
	year = {2024},
	month = {May},
	publisher = {IBPSA-USA},
	author = {Daksh Bansal and  Omprakash Ramalingam Rethnam and  Albert Thomas},
	title  = {A Decision-Support Framework for Community Building Energy Modeling in Developing Nations, Leveraging Satellite Imagery and Machine Learning Techniques},
	booktitle = {Proceedings of SimBuild Conference 2024},
	volume  = {11},
	isbn = {},
	address  = {Denver, Colorado},
	series  = {IBPSA-USA Building Simulation Conference},
	pages = {501--510},
	abstract = {Reducing energy consumption in buildings is pivotal to reaching the global net-zero target as they contribute about 40% of energy-related carbon dioxide emissions. To achieve this holistic optimization of energy consumption in the global building stock, achieving net zero energy status only for a few buildings sparsely distributed across the national landscape may not yield the desirable outcome. A nascent evolving modeling schema called urban building energy modeling tries to address this gap by strategizing retrofit strategies for buildings on an urban scale. However, implementing such frameworks is primarily limited only to developed countries because of the availability of a rich existing database of digitized building footprints, which is not the case in developing countries. This study tries to bridge this gap by developing a framework using satellite imagery and machine learning techniques for developing a community building energy model and implementing the framework on a case study from India for validation. Employing this framework can help particularly in developing countries where building footprint details are not digitally available to arrive at appropriate energy reduction strategies community-wide.},
	issn = {},
	Organisation = {IBPSA-USA},
	Editors = {}
}