跳转至

文章背景与核心概要

垃圾填埋场产生的无组织排放（Fugitive emissions）经常使周边社区暴露在有毒和恶臭气体之中，然而历史上的公共卫生响应大多属于事后应对——即只有在居民遭受暴露后才对事故进行调查。本文介绍了 CAIRN（Causal-Anchored Inference for Receptor Nowcasting，用于受体临近预报的因果锚定推理） 这一机器学习框架，它仅利用常规天气变量和日历数据即可预测气体测量值，且无需人工设计特征。

通过利用与物理输送时间尺度相匹配的内部记忆机制（包括快速的小时级风载输送和缓慢的多小时天气变化），CAIRN 有效充当了一个经过验证的分级公共卫生干预触发器，有助于在排放事件发生期间而不是发生之后减少社区暴露。该研究在环境监测与人工智能的结合方面迈出了重要一步，为精细化环保治理和公众健康保护提供了创新的技术工具。

Meteorology-driven Causal Nowcasting of Fugitive Landfill Emissions Enables Proactive Public Health Response

Summary

Fugitive emissions from waste sites regularly expose nearby communities to toxic and odorous gases, yet public health responses have historically been retrospective—investigating incidents only after exposure has occurred. This paper introduces CAIRN (Causal-Anchored Inference for Receptor Nowcasting), a machine learning framework that uses routine weather variables and calendar data to forecast gas measurements without hand-engineered features. By leveraging internal memory matched to physical transport timescales (fast hour-scale wind-borne transport and slow multi-hour weather changes), CAIRN effectively acts as a validated, graded trigger for public health interventions, helping to reduce community exposure during emission events rather than after them.

垃圾填埋场产生的无组织排放经常使周边社区暴露在有毒和恶臭气体之中，然而历史上的公共卫生响应大多属于事后应对——即只有在居民遭受暴露后才对事故进行调查。本文介绍了 CAIRN（Causal-Anchored Inference for Receptor Nowcasting，用于受体临近预报的因果锚定推理） 这一机器学习框架，它仅利用常规天气变量和日历数据即可预测气体测量值，且无需人工设计特征。通过利用与物理输送时间尺度相匹配的内部记忆机制（快速的小时级风载输送和缓慢的多小时天气变化），CAIRN 有效充当了一个经过验证的分级公共卫生干预触发器，有助于在排放事件发生期间而不是发生之后减少社区暴露。

Article Details

  • arXiv ID: arXiv:2608.14254 [cs.CY]
  • Submitted On: August 14, 2026
  • Primary Subject: Computers and Society (cs.CY)
  • Other Subjects: Artificial Intelligence (cs.AI), Machine Learning (cs.LG), Atmospheric and Oceanic Physics (physics.ao-ph), Geophysics (physics.geo-ph)
  • DOI: 10.48550/arXiv.2608.14254

文章详情

  • arXiv ID: arXiv:2608.14254 [cs.CY]
  • 提交时间: 2026年8月14日
  • 主学科: 计算机与社会 (cs.CY)
  • 其他学科: 人工智能 (cs.AI)、机器学习 (cs.LG)、大气与海洋物理学 (physics.ao-ph)、地球物理学 (physics.geo-ph)
  • DOI: 10.48550/arXiv.2608.14254

Authors

  • Timothy C. Pearce
  • David J. T. Smith
  • Alec Dobney
  • Alessia Freddo

作者

  • Timothy C. Pearce
  • David J. T. Smith
  • Alec Dobney
  • Alessia Freddo

Abstract

Fugitive emissions from waste sites increasingly expose communities to toxic and odorous gases, yet public-health responses remain largely retrospective, with episodes investigated only after residents have been exposed. Here we show that the meteorological drivers of elevated hydrogen sulphide (\(\text{H}_2\text{S}\)) at a long-monitored European landfill, and the timescales over which they act, can be identified directly from routine monitoring data.

摘要

废弃物场地的无组织排放日益让周边社区暴露于有毒和恶臭气体之中，然而公共卫生响应在很大程度上仍然是事后的，往往只有在居民受到暴露后才对事件进行调查。在此，我们表明，通过常规监测数据可以直接识别欧洲某长期监测垃圾填埋场中硫化氢（\(\text{H}_2\text{S}\)）浓度升高的气象驱动因素及其作用的时间尺度。

We introduce CAIRN (Causal-Anchored Inference for Receptor Nowcasting), a machine-learning framework whose internal memory is matched to these measured timescales: a fast component tracking hour-scale wind-borne transport and a slow component tracking multi-hour weather changes. Trained to predict gas measurements, CAIRN operates using only routine weather variables and the calendar, without hand-engineered features.

我们引入了 CAIRN（Causal-Anchored Inference for Receptor Nowcasting，用于受体临近预报的因果锚定推理）这一机器学习框架，其内部记忆与这些测量到的时间尺度相匹配：一个用于追踪小时级风载输送的快速组件和一个用于追踪多小时天气变化的慢速组件。在训练以预测气体测量值时，CAIRN 仅使用常规天气变量和日历，无需人工设计的特征。

Its behaviour is consistent with the identified transport mechanisms, and the framework transfers unchanged to a second monitoring station and to co-emitted methane. Combining four such nowcasters produces a site-level, tiered alert aligned with WHO odour guidance that closely reproduces the alert generated by a direct sensor network and tracks an independent record of community odour complaints. Weather-driven nowcasting can therefore estimate community impact as an emission episode unfolds, providing public-health authorities with a validated, graded trigger for intervention and enabling exposure to be reduced during events rather than after them.

其行为与已识别的输送机制保持一致，且该框架无需修改即可迁移至第二个监测站以及同类排放的甲烷。将四个这样的临近预报器相结合，可以产生符合世界卫生组织（WHO）恶臭指导方针的场地级分级警报，该警报能够高度还原由直接传感器网络生成的警报，并追踪社区恶臭投诉的独立记录。因此，气象驱动的临近预报能够在排放事件展开时估计其对社区的影响，为公共卫生机构提供经过验证的分级干预触发器，从而在事件发生期间而不是发生之后减少暴露。

License & Resources

许可与资源