Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows
This enables interactive urban planning and compliance workflows for city regulators and planners, though it is an incremental improvement over existing deep learning methods.
The paper tackles the problem of slow urban noise prediction by developing a conditional Normalizing Flows model that generates sound-pressure maps from 2D urban layouts in real time, accelerating map generation by over 2000 times compared to physics-based solvers while improving accuracy by up to 24% over prior deep models.
Accurate and fast urban noise prediction is pivotal for public health and for regulatory workflows in cities, where the Environmental Noise Directive mandates regular strategic noise maps and action plans, often needed in permission workflows, right-of-way allocation, and construction scheduling. Physics-based solvers are too slow for such time-critical, iterative "what-if" studies. We evaluate conditional Normalizing Flows (Full-Glow) for generating for generating standards-compliant urban sound-pressure maps from 2D urban layouts in real time per 256x256 map on a single RTX 4090), enabling interactive exploration directly on commodity hardware. On datasets covering Baseline, Diffraction, and Reflection regimes, our model accelerates map generation by >2000 times over a reference solver while improving NLoS accuracy by up to 24% versus prior deep models; in Baseline NLoS we reach 0.65 dB MAE with high structural fidelity. The model reproduces diffraction and interference patterns and supports instant recomputation under source or geometry changes, making it a practical engine for urban planning, compliance mapping, and operations (e.g., temporary road closures, night-work variance assessments).