AO-PHAILGDec 20, 2023

A 3D super-resolution of wind fields via physics-informed pixel-wise self-attention generative adversarial network

arXiv:2312.13212v1h-index: 5
Originality Incremental advance
AI Analysis

This work addresses the need for efficient monitoring of greenhouse gas sources at high spatial resolution to mitigate global warming, representing an incremental improvement in domain-specific simulation methods.

The study tackled the problem of computationally expensive high-resolution 3D wind field simulations by developing a physics-informed super-resolution GAN that upscales low-resolution wind fields by 9 times, reducing computational cost by 89.7 times while maintaining high-fidelity results.

To mitigate global warming, greenhouse gas sources need to be resolved at a high spatial resolution and monitored in time to ensure the reduction and ultimately elimination of the pollution source. However, the complexity of computation in resolving high-resolution wind fields left the simulations impractical to test different time lengths and model configurations. This study presents a preliminary development of a physics-informed super-resolution (SR) generative adversarial network (GAN) that super-resolves the three-dimensional (3D) low-resolution wind fields by upscaling x9 times. We develop a pixel-wise self-attention (PWA) module that learns 3D weather dynamics via a self-attention computation followed by a 2D convolution. We also employ a loss term that regularizes the self-attention map during pretraining, capturing the vertical convection process from input wind data. The new PWA SR-GAN shows the high-fidelity super-resolved 3D wind data, learns a wind structure at the high-frequency domain, and reduces the computational cost of a high-resolution wind simulation by x89.7 times.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes