A Hybrid Statistical-Machine Learning Framework for Risk-Based Screening of High-Frequency Carbon Emission Data Under Emissions Trading Systems
排出量取引制度下での高頻度炭素排出データのリスクベーススクリーニングのためのハイブリッド統計・機械学習フレームワーク (AI 翻訳)
Changyi Weng, Zhenghua Shu, Jueying Qian, Jingwei Fan, Xiaohu Luo
🤖 gxceed AI 要約
日本語
中国ETSの拡大に伴い、信頼性の高い排出データが不可欠となる中、材料ベースと煙道ガスベースの排出量の比率を利用した異常検知フレームワークを提案。Hartigan's dip testとRandom Forestを組み合わせ、セメント工場の15分間隔データで評価し、94.7%の異常期間を検出した。
English
As China's ETS expands, reliable emission data becomes critical. This study proposes a hybrid anomaly detection framework using the ratio of material-based to flue gas-based emissions, combining Hartigan's dip test and Random Forest. Evaluated on 15-min cement plant data, it detected 94.7% of anomalous periods.
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
中国ETSのデータ品質検証手法として提案。日本でもカーボンプライシング導入が進む中、高頻度データの異常検知フレームワークは参考になる。
In the global GX context
This framework addresses a key challenge in ETS data integrity as China's market grows. It offers a transferable approach for global ETS data quality assurance, particularly for energy-intensive sectors.
👥 読者別の含意
🔬研究者:Proposes a hybrid method combining statistical test and ML for anomaly detection in carbon emission data, useful for emission trading data quality research.
🏢実務担当者:Cement plants and ETS verifiers can use this framework to prioritize verification of high-risk emission periods.
🏛政策担当者:ETS regulators can consider such data-driven verification approaches to enhance market integrity.
📄 Abstract（原文）
Reliable carbon emission data are essential for the effective operation of emissions trading systems (ETS), especially as China’s ETS expands to include energy-intensive industries. This study proposes a hybrid, risk-based anomaly detection framework for high-frequency CO2 emission data by cross-validating material-based emissions with flue gas-based monitoring data. Under normal operating conditions, the ratio of material-based to flue gas-based emissions is expected to remain within a relatively stable distribution. Potential high-risk periods can therefore be identified when this relationship is distorted or when local temporal patterns deviate from expected behavior. The framework combines Hartigan’s dip test with a window-based Random Forest (RF) classifier, which is suitable for continuous monitoring data that may exhibit temporal dependence. The framework was evaluated using 15-min CO2 emission data from a cement production facility, with simulations of anomaly magnitude, duration, and mode. Results show that the dip test performs well for long-lasting or strong anomalies, whereas the RF model is more sensitive to subtle, short-term deviations. In the integrated framework, 94.7% of anomalous periods were detected by at least one method and flagged as potential data-quality risks, whereas normal periods were not flagged, supporting its use to prioritize verification efforts.
🔗 Provenance — このレコードを発見したソース
- crossref https://doi.org/10.3390/atmos17060624first seen 2026-06-25 04:53:09
🔔 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。