用人口特征优化高温死亡风险模型，提升预测准确性与可靠性。
Demographically-Informed Heat-Mortality Risk Curves via Risk Graph Neural Networks
- 基于图神经网络融合人口数据，动态调整风险曲线参数
- 2022年热浪期间误差更低，不确定性估计更接近真实水平
- 适合气候健康与城市规划研究者使用
估算高温相关死亡风险是环境流行病学的核心任务，传统方法多采用分布滞后非线性模型（DLNM），通过拟合温度-死亡时间序列获得可解释的暴露-反应曲面。但现有方法忽略人口与地理背景，而这些因素已被证实与高温脆弱性密切相关。本文提出风险图神经网络（RGNN），一种分层图神经网络编码器，利用精细的普查特征优化DLNM系数向量，在保持可解释风险曲线输出的同时显著提升预测校准性能。在英格兰与威尔士10个区域、针对两年前所未有的热浪事件进行评估，RGNN变体在2022年热浪期间不仅点预测误差更低，且不确定性覆盖接近名义水平，而基线模型则出现崩溃。
原文摘要 · Abstract (English)
Estimating heat-related mortality risk is a core task in environmental epidemiology, typically addressed with Distributed Lag Non-linear Models (DLNMs); interpretable exposure-response surfaces fitted to temperature-mortality time series. DLNMs are effective but ignore demographic and geographic context, despite well-established relevance to heat vulnerability. We propose Risk Graph Neural Networks (RGNNs), a hierarchical GNN encoder that uses granular census features to optimise DLNM coefficient vectors, preserving interpretable risk curve outputs while substantially improving predictive calibration. Evaluated across 10 regions of England and Wales on two unprecedented heat years, RGNN variants maintain both lower point-errors and near-nominal uncertainty coverage during the 2022 heatwave where baselines collapse.
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。