TY - JOUR

T1 - Component-Based Machine Learning for Indoor Flow and Temperature Fields Prediction

T2 - latent feature aggregation and flow interaction

AU - Wang, Shaofan

AU - Thuerey, Nils

AU - Geyer, Philipp

N1 - Publisher Copyright: Copyright © 2026. Published by Elsevier B.V.

PY - 2026/3/1

Y1 - 2026/3/1

N2 - Accurate and efficient prediction of indoor airflow and temperature distributions is essential for building energy optimization and occupant comfort control. However, traditional CFD simulations are computationally intensive, limiting their integration into real-time or design-iterative workflows. This study proposes a component-based machine learning (CBML) surrogate modeling approach to replace conventional CFD simulation for fast prediction of indoor velocity and temperature fields. The model consists of three neural networks: a convolutional autoencoder with residual connections (CAER) to extract and compress flow features, a multilayer perceptron (MLP) to map inlet velocities to latent representations, and a convolutional neural network (CNN) as an aggregator to combine single-inlet features into dual-inlet scenarios. A two-dimensional room with varying left and right air inlet velocities is used as a benchmark case, with CFD simulations providing training and testing data. Results show that the CBML model accurately and fast predicts two-component aggregated velocity and temperature fields across both training and testing datasets.

AB - Accurate and efficient prediction of indoor airflow and temperature distributions is essential for building energy optimization and occupant comfort control. However, traditional CFD simulations are computationally intensive, limiting their integration into real-time or design-iterative workflows. This study proposes a component-based machine learning (CBML) surrogate modeling approach to replace conventional CFD simulation for fast prediction of indoor velocity and temperature fields. The model consists of three neural networks: a convolutional autoencoder with residual connections (CAER) to extract and compress flow features, a multilayer perceptron (MLP) to map inlet velocities to latent representations, and a convolutional neural network (CNN) as an aggregator to combine single-inlet features into dual-inlet scenarios. A two-dimensional room with varying left and right air inlet velocities is used as a benchmark case, with CFD simulations providing training and testing data. Results show that the CBML model accurately and fast predicts two-component aggregated velocity and temperature fields across both training and testing datasets.

KW - CFD simulation

KW - Component-based machine learning (CBML)

KW - Data-driven model

KW - Indoor environment prediction

KW - Reduced order model (ROM)

UR - http://www.scopus.com/inward/record.url?scp=105027248592&partnerID=8YFLogxK

U2 - 10.1016/j.enbuild.2026.116958

DO - 10.1016/j.enbuild.2026.116958

M3 - Article

VL - 354

JO - Energy and buildings

JF - Energy and buildings

SN - 0378-7788

M1 - 116958

ER -