Trustworthy Data-Driven Hybrid Modeling of Building Energy Performance and Greenhouse Gas Emissions
信頼できるデータ駆動型ハイブリッドモデリングによる建物エネルギー性能と温室効果ガス排出の予測 (AI 翻訳)
Abdulkadir Gungor, Ahmet Nur, Sabir Rustemli, Faruk Kurker, Gökhan Şahin, Erdal Akin, Kayode S. Adewole, Andreas Jacobsson
🤖 gxceed AI 要約
日本語
本研究は、機械学習と簡易排出係数リスケーリングを組み合わせたハイブリッドデータ駆動型フレームワークを開発し、大学キャンパス全体のCO2排出量を予測する。9つの機械学習モデルを比較評価し、ニューラルネットワークが最も高い予測性能を示した。また、特徴量重要度分析によりCO2強度指標が主要な排出要因であることを特定し、高エネルギー建物への対策が効果的であることを示した。
English
This study develops a hybrid data-driven framework combining machine learning and emission factor rescaling to predict campus-wide CO2 emissions. An Artificial Neural Network achieved the best predictive performance (RMSE=2.13 ton/year, R²=0.985). Feature importance analysis identified CO2 intensity indicators as key drivers. The findings support targeted energy efficiency improvements in high-emission buildings.
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
日本でも大学キャンパスの脱炭素化が進む中、本手法は限られたデータから排出ホットスポットを特定し、効率的なエネルギー管理に貢献できる。特に、SSBJなど開示基準に対応したキャンパス単位の排出量算定に応用可能。
In the global GX context
This paper contributes to global building decarbonization by providing a data-driven, interpretable method for predicting emissions at campus scale. It aligns with ISSB and other disclosure frameworks that require granular emissions data, and offers a path for integrating machine learning into carbon management.
👥 読者別の含意
🔬研究者:This hybrid modeling approach can be replicated on other campuses or building stocks, particularly for testing physics-informed machine learning under data limitations.
🏢実務担当者:Facility managers can use the ANN model to identify high-emission buildings and prioritize energy retrofits, supporting cost-effective decarbonization.
📄 Abstract（原文）
Reducing carbon dioxide (CO2) emissions from buildings is essential for climate change mitigation, with universities representing major energy consumers. This study develops a hybrid data-driven framework combining machine learning and simplified emission factor rescaling to predict campus-wide CO2 emissions. Nine machine learning models were comparatively evaluated under both cross-sectional and temporal validation settings. Among all evaluated models, the Artificial Neural Network (ANN) demonstrated the most reliable predictive performance, achieving the best balance between prediction accuracy and generalization capability. Although the proposed physics-informed LSBoost_PI framework aimed to integrate physical priors with machine learning through residual correction, it did not improve predictive generalization under the limited sample conditions of the dataset. Time-series cross-validation further confirmed the ANN model’s temporal forecasting capability (RMSE = 2.13 ton/year, R2 = 0.985). To support trustworthy and interpretable machine learning, feature importance analysis identified CO2 intensity indicators (CO2/kWh and CO2/TEP) as the dominant drivers of emissions. The study also conducted an emission reduction assessment, revealing that a limited number of high-energy buildings dominate overall campus emissions. These findings provide actionable insights for campus-scale energy management, supporting targeted energy efficiency improvements and renewable energy integration strategies in high-emission buildings.
🔗 Provenance — このレコードを発見したソース
- crossref https://doi.org/10.3390/buildings16112260first seen 2026-06-04 05:33:31
🔔 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。