2024
Wang, H., Ma, W., Niu, J., You, R.* 2024. Evaluating a deep learning-based surrogate model in predicting wind distribution for urban microclimates. Building and Environment, Accepted.
​
Abstract: Wind environment assessment in urban areas is crucial for enhancing pedestrian wind comfort and managing pollutant dispersion. Deep learning-based models have shown the potential to replace traditional computationally intensive numerical simulations for accelerated assessment. However, the effectiveness and characteristics of the models in predicting urban wind environments for different building configurations remain unclear. Moreover, there is a lack of knowledge about the influence of the training dataset composition on the model performance. This study aimed to comprehensively evaluate the performance and characteristics of a deep learning-based surrogate model for fast prediction of wind distribution for urban microclimates. Based on a dataset of 4,000 simulations, an end-to-end model was first trained, and the model’s performance and domain transferability were then evaluated. The trained model achieved average mean absolute percentage errors (MAPE) ranging from 1.74% to 12.49% for unseen configurations containing 1 to 4 buildings, offering a speed-up of 3–4 orders of magnitude over traditional CFD methods. The model exhibits limited domain transferability, as it can learn transferable wind flow patterns. As a result, the model can accurately predict wind flow patterns around isolated buildings, while it struggles to capture the complex wind flow caused by a dense arrangement of multi-building cases. To improve the robustness and applicability of the model, integrating building configurations with different numbers of buildings into the training stage could be an effective strategy.
Zhao. R., Zhong. S., You R.* 2024. Application of convolutional neural network for efficient turbulence modeling in urban wind field simulation. Physics of Fluids, 36: 105169.
​
Abstract: Accurate flow field estimation is crucial for the improvement of outdoor environmental quality, but computational fluid dynamics (CFD) based on the widely used Reynolds-averaged Navier-Stokes method has limitations in this regard. This study developed a turbulence modeling framework based on a convolutional neural network (CNN) to model turbulence in urban wind fields. The CNN model was trained by learning the Reynolds stress patterns and spatial correlations with the use of high-fidelity datasets. Next, the model was integrated into the CFD solver to generate accurate and continuous flow fields. The generalization capability of the proposed framework was initially demonstrated on simplified benchmark configurations. The validated framework was then applied to case studies of urban wind environments to further assess its performance, and it was shown to be capable of delivering accurate predictions of the velocity field around an isolated building. For more complex geometries, the proposed framework performed well in regions where the flow properties were covered by the training dataset. Moreover, the present framework provided a continuous and smooth velocity field distribution in highly complicated applications, underscoring the robustness of the proposed turbulence modeling framework.
2022
Zhou, Y., An, Y., Huang, W., Chen, C., You, R.* 2022. A combined deep learning and physical modelling method for estimating air pollutants' source location and emission profile in street canyons. Building and Environment, 219: 109246.
​
Abstract: Roadside air pollution monitoring stations have become frequently available for street canyons. To efficiently estimate source location and emission profile in street canyons, this study developed a combined deep learning and physical modelling method using the monitoring data as inputs. First, a deep neural network (DNN) was constructed for locating the source. The training datasets were generated from numerical simulations by the computational fluid dynamics (CFD)-Markov chain model. An inverse method based on Tikhonov regularization was then used to estimate the emission profile. Finally, the Markov chain model was used to calculate the air pollutant distribution in the whole street canyon. Case studies were conducted to demonstrate the performance of the proposed method. For the unit impulse source in the 2-D ventilated chamber of 27 m2, the source in 83% of the cases were accurately identified, and in another 13% of the cases, the identified source was within 0.4 m to the true location. For the continuous pollutant source with varying emission profile in the 3-D street canyon with an area of 25,600 m2, the source in 36% of the cases were accurately located, and in another 52% of the cases, it was within 10 m from the true location.
