Machine Learning for Dimensional Shading is a project exploring the methodologies of machine learning, using Neural Networking in specific. The application of this in an architectural scale is with the aim of designing a façade of a structure of a particular orientation. This façade has openings in a specific location, specific dimensions and a specific extrusion length for shading. These values are obtained by running two processes using Ladybug and Neural Networking.

//Design Process_Step 1

Tool Used_ Ladybug

Using Ladybug, the weather of a specific location was analyzed to obtain radiation analysis and shadow studies on a specified geometry. This was used to obtain data regarding three aspects: Orientation and openings of the facade, as well as rotation angle of these openings.

//Design Process_Step 2

Tool Used_ Neural Networking

//Pseudo Code

//Design Development

//Radiation Analysis_ Ladybug

//Tensor Sets

//Fitting lengths after Machine Learning

//Final Output_Designing the Facade


Machine Learning for Dimensional Shading is a project of IAAC, Institute for Advanced Architecture of Catalonia developed in the Master in Advanced Architecture 2021/22 in the Business Innovation Seminar by Students: Aniket Sonawane, Chirag Shah, Hairati Tupe and Lekha Gajbhiye and Faculty: Mateusz Zwierzycki