Ant Colony Optimization-Driven Ensemble Learning for Carbon Emission Modelling in Fly Ash–Slag Geopolymer Concrete
Indra Kumar Pandey, Sulekh Kumar, Brajkishor Prasad, Pramod Kumar, Mizan Ahmed, Ardalan B. Hussein
🤖 gxceed AI 要約
日本語
本研究は、フライアッシュと高炉スラグを原料とするジオポリマーコンクリートの炭素排出量予測に、アリコロニー最適化（ACO）を組み込んだアンサンブル機械学習手法を適用。ACO拡張XGBoostモデルが最高精度（R2=0.97）を示したが、モデル間の性能差は僅少。硬化パラメータ（初期養生時間、温度、水酸化ナトリウム量）が炭素排出に最も影響。CatBoostとACO勾配ブースティングがノイズに対して安定している一方、XGB系は精度高いが入力変動に敏感。データ駆動型の炭素排出定量化フレームワークを提供し、持続可能な材料設計に貢献。
English
This study applies ensemble machine learning with ant colony optimization (ACO) to predict carbon emissions from fly ash and slag-based geopolymer concrete. The ACO-enhanced XGBoost model achieved the highest accuracy (R2=0.97), though differences among top models were small. Curing parameters (initial curing time, temperature, and dry sodium hydroxide dosage) were most influential. CatBoost and ACO-gradient boosting showed greater stability under noisy conditions, while XGB models were more sensitive. The work provides a data-driven framework for carbon emission quantification, advancing sustainable material design.
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
日本でも低炭素コンクリートの開発が進む中、本論文はフライアッシュ・スラグジオポリマーコンクリートの炭素排出量を高精度に予測する機械学習手法を提示しており、建設業界のGX推進に示唆を与える。
In the global GX context
This paper contributes to the global push for decarbonizing construction materials by using AI to predict embodied carbon, directly relevant to upcoming ISSB and other climate disclosure requirements that include Scope 3 emissions from materials.
👥 読者別の含意
🔬研究者:Demonstrates a novel integration of ACO with ensemble ML for carbon emission modeling, highlighting trade-offs between accuracy and robustness.
🏢実務担当者:Offers a predictive tool for optimizing geopolymer concrete mixes to minimize carbon footprint, aiding in low-carbon material selection.
🏛政策担当者:Provides evidence for incorporating data-driven modeling in standards for low-carbon concrete and embodied carbon accounting.
📄 Abstract（原文）
This study investigates the prediction of carbon emissions from fly ash and ground granulated blast furnace slag-based geopolymer concrete (GPC) using advanced ensemble machine learning (ML) techniques. Although ML has been extensively utilized to model GPC’s mechanical performance, its application in estimating environmental impacts, specifically carbon emissions, is limited. The research employs six ensemble ML models, such as random forest, gradient boosting, extreme gradient boosting (XGB), CatBoost, and light gradient boosting machine (LGBM), including versions optimized using ant colony optimization (ACO). Among them, the ACO-enhanced XGB model demonstrated the highest predictive accuracy with a coefficient of determination (R2) of 0.97, with low prediction errors (MAE = 3.92, RMSE = 6.17). However, cross-validation and uncertainty analyses indicate that the performance differences among top models are relatively small. Conversely, LGBM exhibited the least predictive reliability. Feature importance analysis revealed that curing parameters, specifically initial curing time, curing temperature, and the dosage of dry sodium hydroxide, had the most influence on carbon emissions. To evaluate model robustness and interpretability, Monte Carlo simulation and Gaussian white noise analyses were conducted. Results confirmed that CatBoost and ACO–gradient boosting (ACO-GB) demonstrated greater stability under varying and noisy conditions, whereas XGB-based models, although highly accurate, were comparatively more sensitive to input variability. Overall, the research establishes a data-driven, efficient framework for quantifying carbon emissions in GPC, highlighting the importance of evaluating both predictive accuracy and model robustness, advancing sustainable material design through intelligent modelling.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3390/ma19102168first seen 2026-06-17 05:50:17 · last seen 2026-06-17 07:14:10
🔔 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。