Introduction

Ralph Evins

doi:10.1080/19401493.2026.2705019

August 5, 2026Journal of Building Performance SimulationOpen Access

Introduction

View Full Paper

Ask AI

Bookmark

Share

Key Points

This research aims to establish surrogate modelling techniques to replicate complex physics-based simulations efficiently.
Utilized machine learning algorithms to train models for simulating EnergyPlus outcomes.
Compared computational costs of surrogate models against traditional physics-based simulations.
Conducted analyses to evaluate performance and efficiency of the proposed modelling approach.
Surrogate models achieved up to 90% reduction in computational time compared to traditional simulations.
Model accuracy maintained with minimal loss in fidelity, highlighted by R-squared values greater than 0.8 for key performance metrics.
Demonstrated significant cost-saving potential in energy simulations, indicating broader applicability.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Explores surrogate modelling to improve simulation efficiency, suggesting significant cost reductions.

Abstract

Surrogate modelling, the training of machine learning models to emulate computationally expensive physics-based simulations such as EnergyPlus at a fraction of the cost, has emerged as one of the m...

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Ralph Evins (2026) studied this question.

synapsesocial.com/papers/6a76da3bf12abadc79814907 https://doi.org/10.1080/19401493.2026.2705019

View Full Paper

Ask AI

Bookmark

Share

Introduction

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Introduction

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading