Graph modeling improves multi-horizon weather forecasts for Mars atmosphere
Graph-Based Learning for Multi-Horizon Martian Atmospheric Forecasting
Software EngineeringMachine Learning
Summary
Forecasting the weather on Mars is hard because its atmosphere changes in complex ways across space, time, and altitude. The authors created a new approach called MaGMA that turns Mars atmospheric data into connected networks, or graphs, to better capture these patterns. This method uses history and vertical weather information to predict Martian atmospheric conditions over multiple future times. Tests show MaGMA predicts Martian weather well for several years, including during a major dust storm, though challenges remain for extreme events and fully using vertical data.
What this means in practice
- •For space mission planners: Provide improved atmospheric forecasts for scheduling rover and lander activities on Mars over multiple future time scales.
- •For earth system modelers: Use graph-based data structuring techniques to enhance forecasting for complex and multi-dimensional Earth atmospheric processes.
Authors
Gary Myler, James Holmes, Manish Patel, Amel Bennaceur
Abstract
Martian weather forecasting is important for future exploration, but atmospheric behaviour on Mars combines spatial, temporal, vertical, and dust-driven processes in ways that challenge current modelling and forecasting approaches. This paper introduces MaGMA (Martian Graph-based Multi-horizon Atmospheric Forecasting), a graph-based data engineering framework that transforms OpenMARS reanalysis fields into structured learning objects for Martian atmospheric forecasting. Local atmospheric patches are represented as graph nodes and linked through spatial neighbourhoods, temporal continuity, longer temporal dependencies, and dynamically similar atmospheric states. The model integrates recent atmospheric history, engineered physical descriptors, and vertical atmospheric information to support forecasting across multiple horizons. We evaluate MaGMA across five unseen Martian years, including regular years and a global dust storm year. In regular years, the model achieves overall R^2 values of approximately 0.73-0.85. For dust-column forecasting, it outperforms classical and deep temporal baselines in most year-horizon comparisons. During the global dust storm year, dust-column prediction remains strong at shorter horizons, with R^2 above 0.8 for the first two horizons, while broader multivariate performance declines. The results show that graph-based data engineering can create reusable and diagnostically useful representations for planetary atmospheric forecasting, while highlighting the need for better learning under rare extreme regimes and improved use of vertical atmospheric structure.