{"ID":3050140,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T08:58:50.400332682Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04658","arxiv_id":"2606.04658","title":"U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts","abstract":"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. \\gls{qd} 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 \\gls{gp} surrogate across different training-data strategies (quasi-random Sobol sampling vs.\\ active \\gls{qd} bootstrapping). Our results reveal that scalar \\gls{gp} surrogates fail catastrophically when trained on random samples, requiring expensive, actively generated \\gls{qd} archives to generalize. In contrast, the spatial inductive bias of the U-Net allows it to learn the underlying physics mapping robustly ($R^2 = 0.996$), completely independent of the training data source. This allows offline \\gls{qd} 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.","short_abstract":"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. \\gls{qd} algorithms offer a way to systematically illuminate the design space...","url_abs":"https://arxiv.org/abs/2606.04658","url_pdf":"https://arxiv.org/pdf/2606.04658v1","authors":"[\"Alexander Hagg\",\"Tania Guerrero\",\"Dirk Reith\"]","published":"2026-06-03T09:35:11Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.LG\"]","methods":"[]","has_code":false}