系外行星大气的图神经网络
Graph neural networks for exoplanet atmospheres
- University College London（伦敦大学学院）
- European Space Agency, ESAC（欧洲空间局，欧洲空间天文中心）
- King’s College London, University of London（伦敦国王学院，伦敦大学）
- Université Paris Cité and Univ Paris Est Creteil, CNRS, LISA（巴黎西岱大学与巴黎东克雷泰伊大学，法国国家科学研究中心，天体物理和行星实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出图神经网络代理模型，以节点和边表示化学物种及反应速率，用于高效模拟系外行星大气非平衡化学，误差较U-Net降低约3倍，并适用于JWST和Ariel观测精度。
AI中文摘要：
在系外行星大气反演中，计算非平衡化学仍然是一个显著的计算瓶颈。来自JWST和Ariel任务等设施的观测精度不断提高，要求在这些分析中纳入非平衡化学。先前的研究表明，神经网络可以模拟动力学化学，尽管其空间归纳偏置与化学反应网络的拓扑结构不一致。本研究引入了一种图神经网络代理模型，将化学物种表示为节点，温度依赖的反应速率表示为边，从而能够沿物理上有意义的化学路径进行信息传播。该模型在采用Venot+2020化学方案和Guillot温度-压力廓线生成的大气上训练。GNN能够准确重建采样参数空间中的非平衡丰度，并将平均丰度误差相比先前的U-Net模型降低约3倍。当应用于透射光谱时，大多数预测落在JWST和Ariel预期的观测精度范围内，仅约7%的测试大气超过20 ppm的平均光谱误差。性能变化主要出现在碳氧比接近1和低温附近的化学过渡区域。对边界情况行星WASP-39b的评估表明，在中等域偏移下模型表现有效。扰动分析表明，扰动沿化学连通性而非空间邻接性传播，证实了该架构捕捉了反应网络的结构。这些结果表明，GNN代理模型能够提供准确、计算高效的非平衡化学预测，有助于将其整合到大气反演流程中。
英文摘要：
Calculating disequilibrium chemistry in exoplanet atmospheres remains a significant computational bottleneck in atmospheric retrievals. The increasing observational precision from facilities such as JWST and the Ariel mission requires including disequilibrium chemistry in these analyses. Previous studies have demonstrated that neural networks can emulate kinetic chemistry, although their spatial inductive bias does not align with the topology of chemical reaction networks. This study introduces a graph neural network surrogate that represents chemical species as nodes and temperature-dependent reaction rates as edges, thereby enabling information propagation along physically meaningful chemical pathways. The model is trained on atmospheres generated using the Venot+2020 chemical scheme and Guillot temperature-pressure profiles. The GNN accurately reconstructs disequilibrium abundances across the sampled parameter space and reduces the mean abundance error by a factor of approximately 3 compared to the previous U-Net model. When applied to transmission spectra, most predictions fall within the observational precision expected for JWST and Ariel, with only about 7% of test atmospheres exceeding a 20 ppm mean spectral error. Performance variations are primarily observed in chemically transitional regimes near a carbon-to-oxygen ratio of one and at low temperatures. An evaluation of the boundary-case planet WASP-39b demonstrates effective performance under a moderate domain shift. Perturbation analysis indicates that disturbances propagate along chemical connectivity rather than spatial adjacency, confirming that the architecture captures the structure of reaction networks. These results suggest that GNN surrogates provide accurate, computationally efficient predictions of disequilibrium chemistry, facilitating integration into the atmospheric retrieval pipeline.
