发表机构
Center for Astrophysics and Space Science (CASS), New York University Abu Dhabi（纽约大学阿布扎比分校天体物理与空间科学中心（CASS））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对火星夜间热层建模中数据稀疏与非物理伪影问题，提出多任务物理信息神经网络，利用MAVEN数据预测四种中性成分密度，通过单调性先验减少反转，提升垂直一致性。
AI 中文摘要
由于原位采样稀疏以及输运、磁场和季节过程之间的强耦合，火星夜间热层的建模仍然具有挑战性。纯数据驱动模型在采样不足的高度区间可能产生非物理伪影，如密度反转。我们提出了一种多任务物理信息神经网络，利用超过十年的MAVEN/NGIMS观测数据（火星年32-38，2014-2025年），同时预测四种中性成分（O、CO$_2$、N$_2$和Ar）的以10为底的对数密度。共享主干网络学习夜间热层状态的公共表示，并分支为各成分特定的输出头。通过自动微分，对对数密度的正垂直梯度施加惩罚，从而引入弱单调性先验。使用轨道不相交的训练/验证/测试划分进行的实验表明，物理信息正则化在保持预测技能的同时显著减少了非物理反转，并且在最佳配置下略微提升了预测技能，以RMSE、MAE和$R^2$衡量。所得模型为夜间热层重建提供了一种计算高效的代理，并具有改进的垂直一致性。
英文摘要
Modeling the Martian nightside thermosphere remains challenging due to sparse in situ sampling and strong coupling among transport, magnetic, and seasonal processes. Purely data-driven models can produce non-physical artifacts, such as density inversions, in poorly sampled altitude regimes. We present a multi-task physics-informed neural network that simultaneously predicts the base-10 logarithmic densities of four neutral species (O, CO$_2$, N$_2$, and Ar) using more than a decade of MAVEN/NGIMS observations (MY 32-38, 2014-2025). A shared backbone learns a common representation of the nightside thermospheric state and branches into species-specific output heads. A weak monotonicity prior is incorporated via automatic differentiation by penalizing positive vertical gradients in logarithmic density. Experiments using an orbit-disjoint train/validation/test split show that physics-informed regularization substantially reduces non-physical inversions while preserving predictive skill and slightly improving it in the best-performing configuration, as measured by RMSE, MAE, and $R^2$. The resulting model provides a computationally efficient surrogate for nightside thermospheric reconstruction with improved vertical consistency.
Comments5 pages, 1 figure, 2 tables. 3rd Conference on AI in and for Space (SPAICE 2026)
