機械学習とデータフュージョンによるSentinel-5P TROPOMIダウンスケーリングを用いた施設規模炭素フットプリント推定
Facility-scale carbon footprint retrieval using Sentinel-5P TROPOMI downscaling via a machine learning and data fusion approach (原題)
Oualid Yahia, Alaa Eddine Mazouz, Van-Tam Nguyen, Evangelos Spyrakos
🤖 gxceed AI 要約
日本語
Sentinel-5P TROPOMIの粗い空間解像度を克服するため、データフュージョンと機械学習回帰を組み合わせ、250m解像度でCH₄・CO₂の炭素フットプリントを推定する手法を提案。MODIS・Sentinel-2・ERA5を入力にXGBoost等4モデルを比較し、XGBoostが最良性能(XCH₄ R²=0.85、XCO₂ R²=0.89)を達成。スコットランドの製油所停止事例で濃度低下を捉え、施設単位モニタリングの有効性を実証した。
English
This study downscales Sentinel-5P TROPOMI methane and CO2 data to 250m resolution by fusing MODIS, Sentinel-2 and ERA5 inputs with four ML regressors, validated against 12 TCCON stations. XGBoost performed best (XCH4 R²=0.85; XCO2 R²=0.89). A Scottish refinery shutdown case confirmed the models capture facility-level emission declines.
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
施設単位の排出可視化はScope 1の実測・検証やSSBJ開示における第三者検証データの高度化に直結し、日本の排出量報告・MRV高度化に関わる。
In the global GX context
Facility-level satellite carbon monitoring strengthens MRV and third-party assurance under ISSB/CSRD and supports verification of corporate Scope 1 disclosures globally.
👥 読者別の含意
🔬研究者:衛星ダウンスケーリングとML回帰を組み合わせた施設規模炭素推定のベンチマークとして参照できる。
🏢実務担当者:自社施設周辺の排出を衛星ベースで可視化・検証するMRV手段として活用余地がある。
🏛政策担当者:排出量報告の独立検証や施設単位モニタリング制度設計の参考になる。
📄 Abstract(原文)
This research addresses the limited regional applicability of Sentinel-5 Precursor (Sentinel-5P) TROPOMI, which provides daily global coverage of Methane (CH₄) and Carbon Monoxide (CO) due to its coarse spatial resolution. A downscaling methodology is proposed to estimate carbon footprint data at a finer spatial resolution (250×250 meters) by integrating data fusion, machine learning regression, and remote sensing techniques. Beyond TROPOMI-derived XCH₄ and XCO, the methodology incorporates additional data from multiple satellite platforms including MODIS and Sentinel-2, as well as ERA5 Reanalysis model outputs. These serve as inputs to four machine learning regressors: XGBoost, Random Forest (RF), Multilayer Perceptron (MLP), and Bayesian Ridge for each gas. Ground-truth measurements for training and validation were collected from 12 globally distributed TCCON stations to ensure robust generalization across diverse geographic conditions, vegetation cover thicknesses, land covers, and elevations. Among all tested models, XGBoost delivered the strongest performance. For XCH₄, it achieved an RMSE of 0.01 ppb, NRMSE of 5.92%, bias of -0.0011 ppb, MAE of 0.0073 ppb, and R² of 0.85. For XCO₂, the corresponding metrics were RMSE of 1.761 ppm, NRMSE of 5.86%, bias of -0.043 ppm, MAE of 1.26 ppm, and R² of 0.89. Qualitative validation was also conducted using the suspension of oil refinery operations in Grangemouth, Scotland in April 2025. The XGBoost models demonstrated strong correlations, capturing a pronounced decline in both CH₄ and CO₂ concentrations before (January 2023) and after (January 2026) the suspension.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1117/12.3116761first seen 2026-11-14 05:17:09
🔔 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。