Automated IFC Generation and Machine Learning-Based λ-Correction for Embodied Carbon Estimation of Buildings
建物の体化炭素推定のための自動IFC生成と機械学習に基づくλ補正 (AI 翻訳)
Chanhyeok Kang, Bokyung Jung, Taekyu Lee, Y. Kwon, Changho Choi
🤖 gxceed AI 要約
日本語
本研究は、建物の体化炭素推定のための実用的フレームワークを提案する。最小限の入力属性（延べ床面積、階数など）から簡易IFCモデルを自動生成し、EPDデータをリンクしてベースライン排出量を算出。その結果を機械学習（LightGBM）で補正することで、精度R²=0.803、MAPE=23.3%を達成した。限られた情報からでも信頼性の高い推定が可能であることを示し、BIM-LCA統合やカーボンニュートラル設計・改修に貢献する。
English
This study proposes a practical framework for estimating embodied carbon in buildings using automated IFC model generation and machine learning correction. With minimal inputs (gross floor area, floors, etc.), baseline emissions are computed via EPD data, then corrected by LightGBM regression. The model achieved R²=0.803 and MAPE=23.3%, demonstrating reliable estimation even without detailed design documents, supporting BIM-LCA integration and carbon-neutral building strategies.
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
日本の建築業界ではZEBやライフサイクルカーボンへの関心が高まっており、本手法は既存建物の簡易な体化炭素推定を可能にする点で有用。SSBJ基準や有報でのカーボンフットプリント開示にも応用可能であり、特に設計図書が不足する中小建物への適用が期待される。
In the global GX context
Globally, embodied carbon estimation for existing buildings is a critical gap in climate disclosure (TCFD/ISSB). This approach offers a scalable, data-driven correction method that can be integrated into broader carbon accounting frameworks, enabling asset-level carbon data for portfolio management and transition finance.
👥 読者別の含意
🔬研究者:This work provides a validated ML correction for simplified IFC-based embodied carbon estimates, advancing BIM-LCA integration and data-driven carbon accounting research.
🏢実務担当者:The framework allows embodied carbon estimation of existing buildings with minimal inputs, enabling cost-effective portfolio screening and retrofit planning for carbon disclosure.
🏛政策担当者:The methodology can inform standardized simplified embodied carbon estimation protocols in building codes and carbon footprinting guidelines, especially for existing building stock.
📄 Abstract（原文）
This study proposes a practical framework for estimating embodied carbon in buildings by integrating automated generation of Industry Foundation Classes (IFC) models with X-correction techniques. Six minimal building attributes—gross floor area, number of floors, floor height, structural type, year of completion, and building use—were used to automatically generate simplified IFC models. Preset values for material thickness, density, and surcharge rates were applied, and Environmental Product Declaration (EPD) data were linked to calculate baseline emissions. The baseline IFC results, however, accounted for only 5-20% of actual embodied carbon, confirming systematic underestimation. To address this limitation, three correction methods were evaluated: global scaling with an average X, cohort-based correction using K-nearest neighbors, and machine learning regression with Light Gradient Boosting Machine (LightGBM). A dataset of 304 buildings, including 260 for training and 44 for testing, was used for validation. Results showed that scaling and cohort approaches provided limited accuracy, while the machine learning model achieved the best performance (R 2 =0.803, MAPE=23.3%). These findings demonstrate that even with minimal inputs, reliable embodied carbon estimation is feasible for existing buildings lacking design documents. The proposed framework supports BIM-LCA integration and contributes to data-driven strategies for carbon-neutral building design and retrofitting.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.1051/e3sconf/202671611008first seen 2026-06-29 06:38:12
🔔 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。