# Physics-Informed Multi-Task Surrogate Model for the Martian Nightside Thermosphere

arXiv: https://arxiv.org/abs/2609.10077 · HTML: https://mlsanity.com/paper/2609.10077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 20 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 1 of 1)

- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)

## Abstract (arXiv)

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, CO2, N2, 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 R2. The resulting model provides a computationally efficient surrogate for nightside thermospheric reconstruction with improved vertical consistency.