FLUME-FNO: data-efficient and scalable prediction of 3D wind and temperature fields in unseen urban morphologies
arXiv:2503.19708v2 Announce Type: replace-cross Abstract: Urban microclimate, encompassing wind and temperature fields shaped by building geometry, significantly impacts energy consumption, pedestrian winds, pollutant dispersion, urban heat island, and public health. Accurately predicting microclimate is crucial yet challenging. Conventional Computational Fluid Dynamics (CFD) is computationally prohibitive for rapid assessments, while many deep learning approaches require extensive training data and struggle with generalization in unseen configurations. We present the Fast Localized Urban Micr
The increasing computational power and advancements in AI, specifically in physics-informed neural networks and surrogate modeling, are enabling more efficient urban climate simulations.
Accurate and rapid prediction of urban microclimate is critical for sustainable urban planning, energy efficiency, and public health in the face of climate change and increasing urbanization.
Traditional computationally intensive methods for urban microclimate prediction can be replaced or augmented by data-efficient AI models, accelerating urban design cycles and adaptation strategies.
- · Urban planners
- · Smart city developers
- · AI model developers
- · Energy efficiency companies
- · Traditional CFD software vendors (if they fail to adapt)
- · Urban developments without climate-conscious design
More sophisticated and rapid urban planning decisions concerning building design and infrastructure will become possible.
This could lead to significantly reduced energy consumption in cities and improved air quality, impacting public health outcomes.
The democratization of climate simulation tools could empower local governments and communities to adapt to environmental changes with greater autonomy.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG