Moving the needle on decarbonising buildings: How to optimise your building designs with Daisy, our smart digital design tool
Truly moving the needle on decarbonising building design will require complex navigation of the design space that integrates architectural and holistic engineering performance objectives at the concept stage. Daisy combines Digital, AI and Sustainability. It is a computational, parametric design tool which revolutionises decision making and helps you choose the optimum high performing solutions in conceptual design.
map marker
United Kingdom
|
17 January 2022
Reading Time :
4 minutes
The early design stage is the crucial point in a project’s lifecycle for selecting the optimum, low-carbon design solutions. However, it can be challenging to understand how the whole design can be truly optimised when there are multiple design teams involved. Bringing in data-driven computational design tools at the early stage can help us overcome this challenge. We can create conceptual designs using the data from each design team which can be analysed to make more informed decisions about how to optimise the building.
Video of Daisy showing the impact different designs have on the embodied and operational carbon and daylight factor
Using our strong understanding of the design process, Daisy has been developed to help you navigate the complex design solution so you can choose the design which gives you the best value-based outcomes. Here are some of the benefits of this tool:
1. Set parameters to improve design performance
Definitions that define success are becoming universally recognised, increasingly quantifiable and desired by our clients. These include carbon and cost but also other engineering and architectural performance objectives such as daylight autonomy, thermal comfort, acoustic comfort and natural ventilation.
2. Analyse multiple objectives for a holistic view of the design
In order to facilitate designs on a holistic level, optimisation techniques must help designers navigate a complicated design space by providing functionality for searching through many design options, prioritising different objectives, and presenting rapid and reasonably accurate performance feedback.
3. AI and machine learning for automation of difficult tasks
Recent advances in machine learning paired with growing data availability are being leveraged at WSP to push the automation of difficult tasks to tackle sustainable building design. We can tap into the wealth of experience and projects that WSP has developed globally. And Machine Learning Surrogate models are being used to provide building performance assessment much faster than simulation-based design analysis.
Ultimately this tool can genuinely facilitate moving the needle on decarbonising design by accounting for multi-disciplinary and multi-objective performance.
