arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16379cs.LG
收藏

TG-PhyNN:一种用于预测时空数据的增强型物理感知图神经网络框架

TG-PhyNN: An Enhanced Physically-Aware Graph Neural Network framework for forecasting Spatio-Temporal Data

Sorbonne Center for Artificial Intelligence(索邦人工智能中心);Sorbonne University(索邦大学);Total Energies(道达尔能源)

Zakaria Elabid, Lena Sasal, Daniel Busby, Abdenour Hadid

AI总结:

提出 TG-PhyNN 框架,将物理约束融入图神经网络训练,通过两步预测策略在 GNN 内计算物理方程导数,在交通流和疾病传播等时空数据预测上显著优于传统模型。

摘要:

准确预测图上的动态过程(如交通流或疾病传播)仍然是一个挑战。虽然图神经网络(GNN)在建模和预测时空数据方面表现出色,但它们通常缺乏直接整合底层物理定律的能力。本研究提出了 TG-PhyNN,一种新颖的时序图物理信息神经网络框架。TG-PhyNN 利用 GNN 进行基于图的建模,同时在训练过程中将物理约束作为指导原则。这是通过一种两步预测策略实现的,该策略允许在 GNN 架构内计算物理方程导数。我们的研究结果表明,TG-PhyNN 在现实世界的时空数据集(如 PedalMe(交通流)、COVID-19 传播和 Chickenpox 爆发)上显著优于传统预测模型(例如 GRU、LSTM、GAT)。这些数据集均受明确定义的物理原理支配,TG-PhyNN 有效利用这些原理,在物理过程主导数据动态的各个领域提供更可靠和准确的预测。这为改进交通流预测、疾病爆发预测以及物理发挥关键作用的其他领域的预测铺平了道路。

英文摘要:

Accurately forecasting dynamic processes on graphs, such as traffic flow or disease spread, remains a challenge. While Graph Neural Networks (GNNs) excel at modeling and forecasting spatio-temporal data, they often lack the ability to directly incorporate underlying physical laws. This work presents TG-PhyNN, a novel Temporal Graph Physics-Informed Neural Network framework. TG-PhyNN leverages the power of GNNs for graph-based modeling while simultaneously incorporating physical constraints as a guiding principle during training. This is achieved through a two-step prediction strategy that enables the calculation of physical equation derivatives within the GNN architecture. Our findings demonstrate that TG-PhyNN significantly outperforms traditional forecasting models (e.g., GRU, LSTM, GAT) on real-world spatio-temporal datasets like PedalMe (traffic flow), COVID-19 spread, and Chickenpox outbreaks. These datasets are all governed by well-defined physical principles, which TG-PhyNN effectively exploits to offer more reliable and accurate forecasts in various domains where physical processes govern the dynamics of data. This paves the way for improved forecasting in areas like traffic flow prediction, disease outbreak prediction, and potentially other fields where physics plays a crucial role.

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。

↑