イタリア・パレルモにおける都市二酸化窒素予測のための物理情報機械学習
Physics-Informed Machine Learning for Urban Nitrogen Dioxide Forecasting in Palermo, Italy (原題)
(著者不明)
🤖 gxceed AI 要約
日本語
本研究は、イタリア・パレルモの高交通量幹線道路を対象に、物理モデル（SIRANE）と機械学習（XGBoost・ランダムフォレスト）を組み合わせたNO2濃度の短期予測パイプラインを提示する。6年間・時間解像度のデータで、XGBoostがt+1hでR2=0.79、t+12hで0.66と全リードタイムで優位。交通由来大気汚染管理への転用可能な手法を提供する。
English
This study presents a hybrid physics-informed machine learning pipeline for NO2 dispersion and short-term forecasting along a high-traffic corridor in Palermo, Italy, using six years of hourly data. Combining COPERT emissions, the SIRANE street-network model, and ML ensembles, XGBoost outperforms random forest at all lead times (R2 0.79 at t+1h to 0.66 at t+12h). The approach offers a transferable methodology for urban air quality management in traffic-dominated environments.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では大気汚染予測は環境省や自治体の大気監視体制と関連するが、GX開示（SSBJ・TCFD）や企業の脱炭素経営との直接的な接続は弱い。ただし、都市交通由来排出の高解像度モデリング手法は、自治体の環境政策やESG評価における大気質リスク評価に応用可能な示唆を含む。
In the global GX context
While this paper does not directly address TCFD/ISSB disclosure frameworks, its high-resolution, physics-informed ML approach to urban air quality modeling offers a transferable methodology for cities and regulators seeking to quantify traffic-related emissions and health risks. It contributes to the broader environmental data infrastructure that underpins climate and sustainability assessment, though its immediate relevance to corporate disclosure is limited.
👥 読者別の含意
🔬研究者:物理モデルとMLを組み合わせた都市大気質予測の手法論として、ハイブリッドモデリングに関心のある研究者に有用。
🏢実務担当者:交通由来大気汚染の高解像度評価手法は、都市部の環境リスク管理やESG評価における大気質指標の参考になり得る。
🏛政策担当者:自治体の大気質管理や交通政策の評価に、物理情報MLによる予測手法を活用できる可能性を示す。
📄 Abstract（原文）
Accurate forecasting of nitrogen dioxide (NO2) in high-traffic urban environments is a critical challenge for public health management and environmental policy. This study presents a hybrid physics-informed machine learning pipeline for NO2 dispersion modeling and short-term forecasting along Viale Regione Siciliana in Palermo, Italy, one of the highest traffic-density corridors in Europe, over six full years (2020–2025) of hourly data resolved at approximately 11 m. Station measurements and weather data are harmonized hourly over the OpenStreetMap road network, converted into emissions with COPERT-Italy (COmputer Program to calculate Emissions from Road Transport) factors, and dispersed with the SIRANE street-network model; the chain is also inverted to recover corridor traffic from the observed NO2. The resulting field is joined with the measured predictors in the machine learning stage, and the output is mapped in GIS Geographic Information System. The hourly scatter between observations and the SIRANE model built on 44,752 h is centered on the 1:1 line, with a Pearson correlation of r=0.83. Of two “memory-less” ensembles on an identical predictor set, XGBoost (eXtreme Gradient Boosting) returns the better R2, mean absolute error, and RMSE Root Mean Square Error at all twelve recursive lead times, declining from R2=0.79 at t+1 h to a plateau of 0.66 at t+12 h, compared to 0.76 to 0.59 for random forest; both reproduce the mean field almost exactly (r≥0.97), with the XGBoost residual staying between 1.0 and 1.7 μg m−3 at every horizon and that of random forest growing to 4.3 μg m−3 by t+12 h. The proposed pipeline offers a transferable methodology for urban air quality management in traffic-dominated environments.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/atmos17090865first seen 2026-09-12 05:17:48 · last seen 2026-09-21 04:55:05
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。