AI 中文总结
本文提出GeoDCD框架，解决大规模时空系统因果发现难题，在Lorenz-96数据集上取得优异性能，可处理10512节点的实际数据，适用于无法干预场景的机制假设生成。
AI 中文摘要
大规模时空系统的因果发现存在诸多挑战：变量具有物理嵌入特性，候选交互随系统规模呈二次增长，且因果结构会随系统状态变化。本文提出GeoDCD，一种几何感知神经框架，利用空间坐标初始化可学习层级结构，并通过输入输出雅可比敏感性分析将训练后的非线性预测器转换为时变有向图。在混沌Lorenz-96动力学场景中，GeoDCD的F1分数达0.99，相比最强神经基线方法，结构汉明距离降低36.8%；即使在坐标无信息时，仍优于基线方法。运行时间在评估范围内近似线性扩展，可在10512节点的海平面气压网格上开展发现工作。将其应用于观测数据时，GeoDCD可识别与环流一致的通道、解析与厄尔尼诺/拉尼娜相关的结构重组，并在耦合电动汽车与道路系统中区分能量对交通、交通对能量的影响。需注意，GeoDCD的边为神经格兰杰敏感性而非干预效应，适用于无法开展干预的场景下的机制假设生成。
英文摘要
Causal discovery at large spatiotemporal scale is difficult: variables are physically embedded, candidate interactions grow quadratically with system size, and causal structure changes with system state. We introduce GeoDCD, a geometry-aware neural framework that uses spatial coordinates to initialize a learnable hierarchy and converts a trained nonlinear predictor into time-varying directed graphs through input-output Jacobian sensitivity analysis. On chaotic Lorenz-96 dynamics, GeoDCD attains an F1 score of 0.99, reducing structural Hamming distance by 36.8% relative to the strongest neural baseline, and still leads flat baselines when coordinates are uninformative. Runtime scales approximately linearly over the evaluated range, enabling discovery on a 10,512-node sea-level-pressure grid. Applied to observations, GeoDCD identifies circulation-consistent gateways, resolves El Nino/La Nina-dependent reorganization, and separates energy-to-traffic from traffic-to-energy influence in coupled electric-vehicle and road systems. Edges are neural-Granger sensitivities rather than interventional effects, positioning GeoDCD for mechanistic hypothesis generation where interventions are unavailable.
