Mechanical assessment with data-driven hybrid machine learning-based optimization of compressive strength of sustainable biochar-concrete composite.
持続可能なバイオチャーコンクリート複合材料の圧縮強度のデータ駆動型ハイブリッド機械学習最適化による機械的評価 (AI 翻訳)
M. Uddin, Md. Samsuzzaman Sobuz, Mohamed Ghalla, Md. Kawsarul Islam Kabbo, Mita Khatun, Ratan Lal, Mehrab Hossain, S. Abubakar
🤖 gxceed AI 要約
日本語
本研究は、バイオチャーを混入したコンクリートの圧縮強度、コスト、CO2排出量を予測するため、ハイブリッド機械学習モデル（XGB-HistGB）を開発・評価した。9つの入力パラメータを用いた実験データに基づき、XGB-HistGBモデルは高い予測精度（R2=0.958）を示し、SHAP分析により微細骨材、材齢、高性能減水剤が重要な影響因子であることが判明した。さらに、ユーザーが配合を入力して即座に性能を予測できるGUIも開発された。バイオチャーを適切に最適化することで、強度と持続可能性を両立できることが示された。
English
This study developed a hybrid machine learning model (XGB-HistGB) to predict compressive strength, cost, and CO2 emissions of biochar-incorporated concrete. Using a dataset of nine input parameters, the model achieved high accuracy (R2=0.958) and identified fine aggregate, curing age, and superplasticizer as key factors via SHAP analysis. A user-friendly graphical interface was created for real-time prediction. The results demonstrate that biochar can be optimally used for sustainable concrete while balancing strength and environmental impact.
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
日本では、カーボンニュートラル達成に向けて建設分野でのCO₂削減が急務であり、バイオチャーを活用した低炭素コンクリートは有効な選択肢となり得る。本研究の機械学習による最適化手法は、日本のゼネコンや建材メーカーが実務で活用可能な予測ツールを提供し、SSBJやカーボンプライシングに対応した材料設計を支援する。
In the global GX context
Globally, the cement industry is under pressure to reduce emissions, and biochar offers a carbon-negative additive. This study's hybrid ML approach provides a scalable framework for optimizing concrete mixtures, aligning with ISSB disclosure requirements on material carbon footprint and enabling firms to demonstrate tangible decarbonization in their supply chains.
👥 読者別の含意
🔬研究者:Provides a robust method for predicting properties of biochar-concrete and identifies key parameters via SHAP, useful for further research in sustainable construction materials.
🏢実務担当者:The developed GUI allows concrete producers to quickly assess trade-offs between strength, cost, and carbon emissions for biochar mixtures, aiding in low-carbon product development.
🏛政策担当者:Highlights the potential of biochar in construction to contribute to carbon sequestration, supporting policies that incentivize low-carbon building materials.
📄 Abstract（原文）
The rapid rise in global population and industrial activity has intensified environmental challenges, particularly carbon dioxide (CO₂) emissions from the cement and concrete industry. Biochar, a carbon-rich byproduct of biomass pyrolysis, has emerged as a promising solution for sustainable construction by enhancing carbon sequestration and improving mechanical performance when partially substituting cement. This study integrates experimental evidence with advanced machine learning (ML) techniques to evaluate the compressive strength, cost-efficiency, and carbon footprint of biochar-incorporated concrete. A comprehensive dataset of nine input parameters, including cement, aggregates, silica fume, fly ash, biochar, water, superplasticizer, and curing age was modeled using multiple ML approaches. Among the models tested, the hybrid XGB-Histogram Gradient Boosting (XGB-HistGB) model consistently achieved the best overall performance, with a testing R2 of 0.958, the lowest mean absolute error (3.03), and minimal prediction bias. This model outperformed standalone algorithms and other hybrids, providing reliable accuracy across compressive strength, cost, and embodied CO₂ predictions. SHAP and partial dependence analyses confirmed fine aggregate, curing age, and superplasticizer as the most influential parameters, while biochar dosage required careful optimization to balance strength retention with sustainability benefits. A user-friendly graphical interface was also developed, enabling real-time prediction of compressive strength, material cost, and CO₂ emissions based on user-defined mix proportions. Overall, the findings demonstrate that biochar can be effectively integrated into sustainable concrete formulations, and the XGB-HistGB model offers a powerful AI-driven predictive framework to optimize both structural performance and environmental outcomes.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://www.nature.com/articles/s41598-026-59827-7_reference.pdffirst seen 2026-07-13 07:21:47
🔔 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。