用自适应图学习提升多水库流量预测精度，还能看懂水系连接逻辑。
Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction
- 构建动态有向图，用注意力机制自动学水利关联
- 30个水库测试中优于基线，少数据水库表现更稳
- 可解释注意力图，助决策者理解水流控制机制
水库来水预测对水资源管理至关重要，但现有方法多聚焦单水库模型，忽略互联水库间的空间依赖。本文提出AdaTrip，一种自适应、时变的图学习框架，用于多水库来水预报。该方法将水库视为节点，通过有向边表示水文连接，利用注意力机制自动识别关键时空依赖。在科罗拉多河上游流域30个水库上的评估显示，其性能优于现有基线，尤其在观测记录较少的水库上通过参数共享实现稳定提升。此外，AdaTrip提供边级别与时间步级别的可解释注意力图，揭示水文调控规律，支持运行决策。代码已开源：https://github.com/humphreyhuu/AdaTrip。
原文摘要 · Abstract (English)
Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。