U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts

Optimizing urban layouts for climate adaptation requires balancing building density with cold-air ventilation. Because physics-based climate simulations are computationally expensive, planners typically evaluate fewer than ten manual designs. glsqd algorithms offer a way to systematically illuminate the design space, but they require surrogate models to be practical. In this paper, we replace a slow, regulatory physics simulator with a spatial deep-learning surrogate (U-Net) inside an offline MAP-Elites loop. We systematically compare this spatial approach with a traditional glsgp surrogate across different training-data strategies (quasi-random Sobol sampling vs. active glsqd bootstrapping). Our results reveal that scalar glsgp surrogates fail catastrophically when trained on random samples, requiring expensive, actively generated glsqd archives to generalize. In contrast, the spatial inductive bias of the U-Net allows it to learn the underlying physics mapping robustly (R2 = 0.996), completely independent of the training data source. This allows offline glsqd optimization to achieve highly accurate fitness rankings (ρ = 0.994) using only a one-time batch of random training samples. The resulting pipeline, deployed in the open-source OpenSKIZZE tool, generates thousands of diverse, climate-evaluated building layouts in under ten minutes.