Global Seminar | Surrogate modelling of building energy use
22 Apr | Dr Ralph Evins will speak on various methods of Surrogate Modelling - the creation of simplified approximations of more complex, higher-order models.
Surrogate modelling of building energy use
Date: Monday, 22 April
Time: 1.00-2.00pm (SGT)/ 7.00-8.00am (CEST)
Venue: Value Lab Asia, L6, Create Tower
Zoom: external page https://ethz.zoom.us/j/63882787354
Register: Scan the QR code or external page register here
Abstract
Surrogate modelling is the creation of simplified approximations of more complex, higher order models. This talk will cover the various surrogate modelling methods developed in Dr Evins’ research group. These provide fast approximations using machine learning can be used in online dashboards to explore complex engineering design problems in an interactive manner, revolutionising the role of such tools in the building design process.
About the Speaker
external page Dr Ralph Evins is an Associate Professor at the University of Victoria in British Columbia, Canada. He leads the external page ReBuild Initiative, which brings together 15 industry and government partners to explore data-driven ways to facilitate building retrofits. Dr Evins’ research group has pioneered the use of machine learning algorithms as ‘surrogate models’ for detailed engineering simulations of building energy use, achieving huge improvements in speed and usability. He also works on the application of machine learning algorithms directly to data about buildings, from IoT sensors, smart meters and thermostats up to city-wide catalogues of the building stock.