Field Condition - Environmental sensibility of spatial configurations with the use of machine intelligence
Christina Doumpioti, Jeffrey R. Huang · eCAADe proceedings · 2022
Within computational environmental design (CED), different Machine Learning (ML) models are gaining ground. They aim for time efficiency by automating simulation and speeding up environmental performance feedback. This study suggests an approach that enhances not the optimization but the generative aspect of environmentally driven ML processes in architectural design. We follow Stan Allen's (2009) idea of 'field conditions' as a bottom-up phenomenon according to which form and space emerge from local invisible and dynamic connections. By employing parametric modeling, environmental analysis data, and conditional Generative Adversarial Networks [cGAN] we introduce a generative approach in design that reverses the typical design process of going from formal interpretation to analysis and encourages the emergence of spatial configurations with embedded environmental intelligence. We call it Intensive-driven Environmental Design Computation [IEDC], and we employ it in a case study on a residential building typology encountered in the Mediterranean. The paper describes the process, emphasizing dataset preparation as the stage where the logic of field conditions is established. The proposed research differentiates from cGAN models that offer automatic environmental performance predictions to one that spatial predictions stem from dynamic fields.