用可解释概念蒸馏，让洪水预测模型既准又可信。
Context-Aware Concept Distillation for Trustworthy Flood Prediction
- 从复杂LSTM中提取水文可解释概念，构建透明替代模型
- 全球5203个流域测试，中位NSE达0.70，优于黑箱模型
- 适合灾害应急部门使用，支持责任可追溯的决策
精准洪水风险评估依赖可靠预测，但当前主流深度学习模型的“黑箱”特性阻碍了公共安全决策中的信任与问责。现有可解释AI方法仅提供局部特征重要性，无法满足灾害响应机构所需的可验证、可操作的因果解释需求。为此，我们提出与领域专家协作的上下文感知概念蒸馏（CACD）框架，将复杂的LSTM模型转化为可解释的水文感知代理模型。通过无监督方法发现“水文语言”，并引入残差超网络，根据流域静态特征动态调节概念表达。在5,203个全球流域上评估，模型实现高保真度（中位NSE 0.70），显著优于黑箱基线（如多层感知机）在未见未来数据上的表现。结果表明，人类可理解的概念足以重构洪水动态，实现了人工智能精度与环境决策透明性的平衡。
原文摘要 · Abstract (English)
Effective flood risk management relies on accurate forecasting, yet the "black box" nature of stateof-the-art Deep Learning models creates a barrier to trust and accountability in high-stakes public safety decisions. While existing Explainable AI (XAI) methods offer local attributions, they fail to provide the verifiable, operationally meaningful causal narratives required by disaster response authorities. To address this societal challenge, we propose Context-Aware Concept Distillation (CACD), a framework developed in collaboration with domain experts to distill opaque LSTMs into interpretable, hydrology-aware surrogate models. We introduce an unsupervised pipeline to discover a "Hydrological Language" and a Residual Hypernetwork that dynamically modulates these concepts based on static basin characteristics. Evaluated on 5,203 basins globally, our model achieves high fidelity (Median NSE 0.70), significantly outperforming black-box baselines (e.g., Multi Layer Perceptrons) on unseen future data. By demonstrating that human-interpretable concepts are sufficient to reconstruct flood dynamics, this work balances AI accuracy with the transparency required for responsible environmental decision-making.
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。