Global warming and increasing heat events necessitate long-term assessments of passive design strategies to ensure thermal resilience under future climatic conditions. Although machine-learning-based Surrogate Models (SMs) offer timely approximation of building performance compared to conventional simulation-based approaches, the lack of uncertainty quantification raises concerns about the reliability of their design optimization outcomes. This study aims to develop a robust surrogate-assisted optimization framework, based on a probabilistic Bayesian Neural Network (BNN) model and supported by an uncertainty-aware objective function. The framework is applied to an affordable housing case study in Surakarta, Indonesia, evaluating its generalizability under current and future climatic scenarios for 2050, 2070, and 2090. Thermal resilience is assessed through overheating hours exceeding acceptability limits in Southeast Asian context, using a parametric workflow implemented in Ladybug-tools and Grasshopper 3D. Compared to simulated test data, the BNN model demonstrates reliable predictive accuracy and probabilistic inference (R2 = 0.99, MAE = 0.52%, CRPS = 0.38%). Furthermore, validation against re-evaluated optimal solutions shows low error ranges (RMSE = 0.43%, MAE = 0.33%), outperforming the deterministic SM optimization approach—using Artificial Neural Networks—by a factor of five. Overall, the uncertainty-aware framework provides a feasible, overconfidence-resistant, and reliable surrogate-assisted optimization method, identifying optimal solutions closely matching those from simulation-based optimization while reducing computational time by 96%.
Elwy et al. (Tue,) studied this question.