As the global community addresses climate change, the building sector plays a crucial role in achieving a zero-carbon future. Innovative, smart, adaptive façades are essential for sustainable buildings, but predicting their performance accurately remains a challenge. Traditional methods, reliant on human intervention, lack the precision and efficiency needed for these complex systems. Automated, AI-driven methods are necessary to gather robust datasets for better predictive modelling.
This research explores AI's potential to shift from traditional to data-centric models, enhancing building performance modelling and simulation. The study investigates various complex façade types, their parameters, and effects, focusing on daylight, energy, and indoor conditions. A significant aspect involves using AI to deliver robust façade performance data, validated through real-time site monitoring. The research merges calibrated data and monitoring records into a comprehensive database, facilitating a transition to data-driven assessment models. The project's success will be measured by comparing AI-predicted performance against actual building data.
I completed my MA in Mechanical Engineering and Energy Systems at K. N. Toosi University of Technology in Tehran. During my time there, I began developing various machine learning and AI methods to forecast energy consumption in the household sector. As a research assistant at the Integration Lab, I contributed to a peer-reviewed publication that utilised stacking ensemble methods for forecasting energy consumption in households with enhanced accuracy and generalizability.
Currently, I am focused on exploring innovative facades and AI approaches to accurately predict and enhance the energy performance of buildings. My research aims to advance the sustainability and efficiency of building energy systems. My research is dedicated to advancing the sustainability and optimising the efficiency of buildings, contributing to more environmentally friendly and cost-effective solutions.