基于注意力机制从稀疏海啸计网络重建全波场海啸波
Attention-Based Reconstruction of Full-Field Tsunami Waves from Sparse Tsunameter Networks
AI总结:
本文研究基于注意力机制神经网络 Senseiver 的稀疏感知能力,用于从稀疏海啸计观测中重建高分辨率全波场海啸波,并在震中未见于训练集及生成密集观测网络等场景下显著优于传统线性插值方法。
摘要:
我们研究了基于注意力机制的神经网络架构 Senseiver 在海啸预报中用于稀疏感知的潜力。具体而言,我们聚焦于海啸数据同化方法,该方法利用海啸计网络生成预报。我们的模型被用于从极其稀疏的观测中重建高分辨率海啸波场,包括海啸震中未出现在训练集中的情况。此外,我们证明,在生成密集观测网络方面,我们的方法显著优于基于惠更斯-菲涅耳原理的线性插值方法,取得了明显更高的精度。
英文摘要:
We investigate the potential of an attention-based neural network architecture, the Senseiver, for sparse sensing in tsunami forecasting. Specifically, we focus on the Tsunami Data Assimilation Method, which generates forecasts from tsunameter networks. Our model is used to reconstruct high-resolution tsunami wavefields from extremely sparse observations, including cases where the tsunami epicenters are not represented in the training set. Furthermore, we demonstrate that our approach significantly outperforms the Linear Interpolation with Huygens-Fresnel Principle in generating dense observation networks, achieving markedly improved accuracy.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。