Surrogate modeling: Difference between revisions
Added references to →Background Readings
No edit summary |
(Added references to →Background Readings) |
||
Line 3:
''This page is about the applications of machine learning (ML) in the context of surrogate modelling. For an overview of surrogate models more generally, please see the [https://en.wikipedia.org/wiki/Surrogate_model Wikipedia page] on this topic.''
Machine learning can approximate simulations by learning
==Background Readings==
Learning a surrogate model is a straightforward supervised machine learning task, given the inputs and outputs of the simulation. However, often the surrogate model is used to find inputs that give the desired output, such as a design for a building or machine with low energy costs. If the surrogate model is used in such an optimisation framework (finding optimal outputs), the technique is called '''surrogate-based optimisation'''. An introduction to these techniques can be found in chapter 10 of Engineering Design Optimization<ref>{{Cite book|title=Engineering Design Optimization|last=J. R. R. A. Martins and A. Ning|first=|publisher=Cambridge University Press|year=2022}}</ref>.
While these techniques have been used in many applications to reduce the number of computationally expensive simulations, thereby saving energy, their potential for climate change mitigation and adaptation are investigated in A Survey on Sustainable Surrogate-Based Optimisation<ref>{{Cite journal|last=Bliek|first=Laurens|date=2022|title=A Survey on Sustainable Surrogate-Based Optimisation|url=https://doi.org/10.3390/su14073867|journal=Sustainability|volume=14}}</ref>.
==Community==
==Libraries and Tools==
Line 11 ⟶ 15:
==Future Directions==
==References==
<references />
|