arXiv：cs.LG· Timothy C. Pearce, David J. T. Smith, Alec Dobney, Alessia Freddo·· 2 天前AI 评分27
气象驱动的垃圾填埋场逃逸气体因果临近预报：基于实测耦合时间尺度
Meteorology-driven Causal Nowcasting of Fugitive Landfill Emissions from Measured Coupling Timescales
AI 导读
研究直接从欧洲某长期监测垃圾填埋场的监测数据中识别出硫化氢（H₂S）暴露的气象驱动因素，风向、风速和气压构成因果核心，气压携带的信息占比随聚合尺度上升。团队据此初始化了 CAIRN（Causal-Anchored Inference for Receptor Nowcasting），一种带快慢记忆组件的机器学习临近预报器，仅凭地面气象测量和日历即可预报 WHO 指导值超标事件。
正文
Abstract:Which meteorological processes control exposure to fugitive gases downwind of a source, and on what timescales, have largely been inferred from dispersion theory and partial field evidence. Here we show that the meteorological drivers of elevated hydrogen sulphide (H$_2$S) exposure at a long-monitored European landfill, and the timescales over which each acts, can be identified directly from monitoring data. Wind direction, wind speed and atmospheric pressure form the causal core, with the share of directed information carried by pressure increasing with aggregation scale. The recovered timescales are consistent with those expected from the underlying atmospheric processes. We use these driver timescales to initialise CAIRN (Causal-Anchored Inference for Receptor Nowcasting), a machine-learning nowcaster with fast and slow memory components. Trained on past exceedances of WHO guideline levels, CAIRN nowcasts them from surface weather measurements and the calendar alone, without hand-engineered features. Combining four such nowcasters produces a site-level, tiered alert that agrees substantially with that generated by a direct sensor network and tracks an independent record of community odour reports. Meteorological variables can therefore serve as an inference-time proxy for exposure relative to WHO guideline levels, and they link atmospheric dynamics to community impact as an episode unfolds.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph); Geophysics (physics.geo-ph) |
| Cite as: | arXiv:2608.14254 [cs.CY] |
| (or arXiv:2608.14254v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2608.14254 arXiv-issued DOI via DataCite |
Submission history
From: Tim Pearce [view email]
[v1]
Fri, 14 Aug 2026 12:32:12 UTC (4,606 KB)
[v2]
Thu, 1 Oct 2026 16:51:25 UTC (4,499 KB)
来源：arXiv：cs.LG · arxiv.org