A machine-learning framework for daylight and visual comfort assessment in early design stages

TL;DR

This paper presents a machine learning framework that accurately predicts daylight and visual comfort metrics in early design stages, reducing reliance on time-consuming simulations.

Contribution

It introduces a novel neural network-based model trained on a large simulation dataset for early-stage daylight and visual comfort assessment.

Findings

Prediction accuracy of 97% on average

Effective early-stage analysis without extensive simulations

Utilizes a Grasshopper-based algorithm for visual comfort evaluation

Abstract

This research is mainly focused on the assessment of machine learning algorithms in the prediction of daylight and visual comfort metrics in the early design stages. A dataset was primarily developed from 2880 simulations derived from Honeybee for Grasshopper. The simulations were done for a shoebox space with a one side window. The alternatives emerged from different physical features, including room dimensions, interior surfaces reflectance, window dimensions and orientations, number of windows, and shading states. 5 metrics were used for daylight evaluations, including UDI, sDA, mDA, ASE, and sVD. Quality Views were analyzed for the same shoebox spaces via a grasshopper-based algorithm, developed from the LEED v4 evaluation framework for Quality Views. The dataset was further analyzed with an Artificial Neural Network algorithm written in Python. The accuracy of the predictions was estimated at 97% on average. The developed model could be used in early design stages analyses without the need for time-consuming simulations in previously used platforms and programs.