Room, Shah, Bahadori-Jahromi, Ali ORCID: https://orcid.org/0000-0003-0405-7146, Al Tekreeti, Marwah and Tariq, Zeeshan (2026) Experimental investigation and Machine Learning-based prediction and optimization of mechanical properties of Biochar-Enhanced High-Strength concrete. Sustainability, 18.

Preview

PDF/A RoomS_Experimental Investigation and Machine Learning Biochar_VoR.pdf - Draft Version Available under License Creative Commons Attribution. Download (8MB) | Preview

Abstract

The paper investigates the use of wood waste biochar as a partial cement replacement in high-strength concrete at 0%, 2%, 4%, and 6% by weight. The study evaluates compressive strength, split tensile strength, and flexural strength, and combines experimental testing with machine learning models. The findings show that 2–4% biochar replacement improves compressive and flexural strength, while 2% replacement gives the best split tensile strength improvement. A database of 318 mixes with 13 biochar types was used to train ML models, with Random Forest giving the strongest performance. SHAP analysis identified cement content, coarse aggregate content, and biochar dosage as key factors. The study concludes that biochar can support sustainable concrete mix design, reduce experimental effort, and help minimise cement use.

Item Type:	Article
Identifier:	10.3390/su18105088
Subjects:	Construction and engineering > Civil and structural engineering
Date Deposited:	21 May 2026
Dates:	Date Publication status 15 May 2026 Accepted 18 May 2026 Published
School, department or research centre:	School of Computing and Engineering
URI:	https://repository.uwl.ac.uk/id/eprint/14967
Sustainable Development Goals:	Goal 9: Industry, Innovation, and Infrastructure	Sustainable Development Goals:	Goal 11: Sustainable Cities and Communities	Sustainable Development Goals:	Goal 12: Responsible Consumption and Production	Sustainable Development Goals:	Goal 13: Climate Action

Downloads

Actions (admin access)