aiqbench analysis
This research introduces a physics-informed neural network to model the Martian nightside thermosphere, addressing limitations of purely data-driven approaches like non-physical density inversions. By integrating physical constraints via automatic differentiation, the model achieves improved vertical consistency and predictive skill using over a decade of MAVEN/NGIMS observations. The work represents a significant advancement in applying machine learning techniques to complex astrophysical problems where sparse sampling is common.
Physics-Informed Multi-Task Surrogate Model for the Martian Nightside Thermosphere
arXiv:2609.10077v1 Announce Type: cross Abstract: 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.
Abstract: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.
5 pages, 1 figure, 2 tables. 3rd Conference on AI in and for Space (SPAICE 2026)
Earth and Planetary Astrophysics (astro-ph.EP); Machine Learning (cs.LG)
arXiv:2609.10077 [astro-ph.EP]
(or arXiv:2609.10077v1 [astro-ph.EP] for this version)
https://doi.org/10.48550/arXiv.2609.10077 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 271 words
Related coverage
Efficient Neural Surrogates for Linear Radiation Transport on the Lattice and Hohlraum benchmarks
arXiv · Oct 7, 2026
Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations
arXiv · Aug 6, 2026
Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation
InfoQ · Sep 7, 2026
Researchers Detect Relationships in Quantum Data with 15% Greater Accuracy
Quantum Zeitgeist · Sep 25, 2026