Explainable Machine Learning Framework for Strength Prediction of Sustainable Concrete Incorporating Industrial Waste SCMs with an Embodied Impact Assessment
産業副産物を用いた持続可能コンクリートの強度予測のための説明可能機械学習フレームワークと環境影響評価 (AI 翻訳)
Zeeshan Tariq, A. Bahadori‐Jahromi, Shah Room, Marwa Al Takreeti
🤖 gxceed AI 要約
日本語
本研究は、産業副産物（フライアッシュ、高炉スラグ）を混入したコンクリートの圧縮・引張強度を予測するため、複数のアンサンブル機械学習モデルを構築し、SHAPによる解釈性を付与した。最適配合（GF4）は40%置換で優れた性能を示し、ライフサイクル評価により36%の炭素排出削減を確認した。XGBoostと勾配ブースティングモデルを粒子群最適化により調整し、高い予測精度を達成した。
English
This study develops multiple ensemble machine learning models with explainable AI (SHAP) to predict compressive and tensile strength of concrete incorporating fly ash and ground granulated blast furnace slag. The optimal hybrid mix (GF4) with 40% cement replacement showed superior performance, achieving 36% embodied carbon reduction in life cycle assessment. XGBoost and Gradient Boosting models were optimized using particle swarm optimization, achieving R2 values of 0.918 and 0.879 respectively.
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
日本の建設業界ではカーボンニュートラル達成に向け、低炭素コンクリートの実用化が急務である。本論文のSCM活用とAI予測モデルは、SSBJの建設セクターにおける環境情報開示や、グリーン購入法による低炭素建材の普及政策に資する知見を提供する。
In the global GX context
This paper provides a replicable framework combining ML prediction and life cycle assessment for low-carbon concrete design, directly relevant to ISSB's requirements for embodied carbon disclosure and global efforts to decarbonize the built environment. The 36% embodied carbon reduction demonstrates quantifiable impact for transition finance and green building certification.
👥 読者別の含意
🔬研究者:Researchers can adopt this integrated ML-LCA framework for optimizing other sustainable construction materials and scaling the methodology.
🏢実務担当者:Concrete producers can utilize the SHAP-based model to predict strength and tailor mix designs for lower carbon footprint, improving regulatory compliance and market competitiveness.
🏛政策担当者:Policymakers can cite the demonstrated 36% embodied carbon reduction to promote SCM use in building codes and procurement standards.
📄 Abstract（原文）
Concrete contributes significantly to global CO2 emissions due to high energy demand for cement production. This research integrates multiple advanced ensemble ML-based prediction models by combining experimental evaluation, explainable framework, and life cycle sustainability analysis for SCM (supplementary cementitious materials)-incorporated concrete mixtures. A comprehensive experimental program was conducted to evaluate the compressive and tensile strength of concrete revealing that the hybrid mix of GF4 with a 40% replacement level of cement with fly ash (FA) and ground granulated blast furnace slag (GGBFS) exhibited optimum synergistic performance due to balanced hydration kinetics and improved microstructure characteristics. For computational model development, a k-fold cross validation technique was deployed to evaluate robustness across multiple data partitions and to control overfitting in models. Model performance was assessed through multiple metrics including R2, RMSE, and MAE with particular emphasis on the gap between training and testing performance. The best performing model was optimized using Particle Swarm Optimization (PSO) and Bayesian Optimization (BO) techniques providing an additional safeguard against overfitting. Shapley Additive Explanation (SHAP) interpretation revealed w/b ratio and curing age as key parameters for compressive strength, while fine aggregate content and curing age influenced tensile strength. For compressive strength, XGBoost model performed well with an R2 value of 0.879 which was increased to 0.918 with the PSO optimization technique. For tensile strength, the Gradient Boosting model was selected with an R2 value of 0.840 which was optimized to 0.879 after the PSO optimization technique. Moreover, life cycle assessment was performed to evaluate the environmental impacts in terms of embodied carbon and energy associated with concrete mixes. The hybrid GF4 mix demonstrated a 36% reduction in embodied carbon compared to the control mix, indicating strong potential for low carbon concrete applications. This integrated research contributes to the advancement of green construction practices and supports global efforts to reduce atmospheric impacts through the circular use of industrial byproducts.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/su18125848first seen 2026-06-29 07:20:51
🔔 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。