A GIS-Based Artificial Neural Network Model to Assess Building Location Potential to Harvest Solar Energy

Dependency upon non-renewable energy sources has created challenges related to climate change, wars over energy supplies, famine, and cycles of deforestation concerns. As populations increase and economic development progress, energy demand grows, and ultimately the scalability of the problems associated with non-renewable energy resources. Solar energy plays a promising role to solve the problem and it is foreseen as the most promising renewable energy source due to its availability and benefits. Despite the promising effects, only a limited amount of electricity is currently produced globally from solar power. In order to realize the importance of tapping into solar energy, it is crucial to reveal the potential amount of electricity that could be thus produced. Many criteria should be taken into consideration before switching to solar energy. One of the most important criteria is the building location and surrounding environment. For example, a house on a hill or less shaded area will get more direct sunlight and generate more solar energy compared to a house in a shaded area. A multi-criteria methodology based on geographic information systems (GIS) and artificial neural network (ANN) is used in this research to assess community benefits of switching to solar energy by evaluating houses location and surrounding environment. The methodology presented in this research uses a tool for automated extraction of photography from 360° video data at locations of interest. The extracted imagery provides a data set to train a deep learning neural network to predict whether a house location is a good fit for solar energy. This research presents a state-of-the-art methodology to assess community benefits of switching to solar energy by using GIS and deep learning to automate the assessment of buildings location potential to harvest solar energy.