Publikasjonsdetaljer
Tidsskrift: Proceedings - International Conference on Tools with Artificial Intelligence (ICTAI), vol. 37, 270–276, 15. desember 2025
Doi: doi.org/10.1109/ICTAI66417.2025.00042
Arkiv: hdl.handle.net/11250/5488031
Arkiv: nva.sikt.no/registration/019d0abfc22d-7bb14eb3-d361-4cf2-80f4-73337ba7bf96
Sammendrag:
Running a numerical weather model such as WRF at kilometre or sub-kilometre grid spacing over a regional domain is computationally expensive. We present physics-informed deeplearning models that ingest a single 9km WRF wind field and simultaneously predict two finer-scale wind fields at 3 km and 1 km resolution via dual decoder heads. Four representative architectures are benchmarked-Deep Residual U-Net (DeepRU), DEVINE, a bespoke 3-D Transformer, and a Fourier Neural Operator (FNO)-each trained with divergence-free, vorticity, and Navier-Stokes residual constraints plus Charbonnier and gradient perceptual losses. We train and validate our models on the city of Oslo for the year 2018. DeepRU achieves R2=0.94 (RMSE =0.050) at 3km and R2=0.89(RMSE=0.065) at 1 km. DEVINE, Transformer 3-D, and FNO yield 3 km scores of 0.91−0.93, with 1km scores lower by 0.02−0.08, illustrating the increased difficulty of finer-scale reconstruction. Physicsinformed losses improve all models compared to MSE-only baselines, and the residual architecture (DeepRU) remains most effective for this dual-scale task.