基于图学习的多时间尺度火星大气预测
Graph-Based Learning for Multi-Horizon Martian Atmospheric Forecasting
- The Open University（开放大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出图基框架MaGMA，将火星大气数据转化为图结构以支持多时间尺度预测，在常规年份取得高R²，并优于基线，但极端沙尘暴年份性能下降，凸显改进需求。
AI中文摘要：
火星天气预报对未来探索至关重要，但火星上的大气行为结合了空间、时间、垂直和尘埃驱动过程，其方式对当前建模和预测方法构成挑战。本文介绍了MaGMA（火星图基多时间尺度大气预测），一个基于图的数据工程框架，将OpenMARS再分析场转换为用于火星大气预测的结构化学习对象。局部大气斑块被表示为图节点，并通过空间邻域、时间连续性、较长的时间依赖性和动态相似的大气状态进行连接。该模型整合了近期大气历史、工程化物理描述符和垂直大气信息，以支持跨多个时间尺度的预测。我们在五个未见过的火星年份（包括常规年份和一个全球沙尘暴年份）上评估了MaGMA。在常规年份，模型总体R²值约为0.73-0.85。对于沙尘柱预测，在大多数年份-时间尺度比较中，它优于经典和深度时间基线。在全球沙尘暴年份，沙尘柱预测在较短时间尺度上保持强劲，前两个时间尺度的R²高于0.8，而更广泛的多变量性能下降。结果表明，基于图的数据工程可以为行星大气预测创建可重用且具有诊断价值的表示，同时强调了在罕见极端状态下更好学习的必要性，以及改进垂直大气结构利用的需求。
英文摘要：
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.
