Machine Learning Methods in Energy Simulations for Architects and Designers: The implementation of supervised machine learning in the context of the computational design process

Application of Machine Learning (ML) in the field of architecture is a worthwhiletopic to discuss in the context of digital architecture. Authors propose to extendthis discussion, presenting an integrated ML pipeline built with thestate-of-the-art data science tools. To investigate the affordances of suchpipelines, an ML model being able to predict the environmental metrics of ageneralized facade system is created. This approach is valid for arbitraryfacades, as long as the proposed design could be discretized in the formanalogous to the data generated for the ML model training. The presentedexperiment evaluates the precision of the sunlight hours and radiation valuespredictions, aiming at the application in the early design phases. Conductedinvestigation builds up on the knowledge embedded in the Grasshopper andLadybug toolsets. Potential application of Convolutional Neural Networks andcategorical datasets for classifications tasks to increase the precision of the MLmodels have been identified. Possibility to extend the approach beyond theworkspace of Rhino and Grasshopper is suggested. Further research outlook,investigating the data pattern recognition capabilities in relation to thethree-dimensional forms discretized as multidimensional arrays, is stated.