Design optimization and performance prediction of biocomposite based brick using machine learning techniques

Abstract

The construction sector’s 40% contribution to global CO₂ emissions underscores urgent demand for bio-based masonry alternatives to energy-intensive cement/clay units. This study pioneers mycelium-bound sugarcane bagasse bio-composite (BC) Brick, leveraging agro-waste (70–85 vol%) and Pleurotus ostreatus via systematic bio-fabrication—optimizing PSD (C/M/F: 55/30/15→40/40/20), spawn (5–10 wt%), growth (7–14 days), and uniaxial pressing (0.15–0.4 MPa). Comprehensive assessment yields: bulk density 268–490 kg/m³ (+ 7.5–9.6% maturation), CS 0.18–1.85 MPa (40–50%), water absorption 74–162% (-12-14%), sorptivity 0.012–0.038 mm/√min (-14-19%), thermal conductivity 0.026–0.048 W/m·K (-7-10%)—M12 optimum (70% bagasse, 40/40/20 PSD, 10% spawn, 0.4 MPa) via hyphal capillary occlusion and closed-cell refinement. Response surface methodology excels (R²>0.997, RMSE < 0.33; Adj.R²>0.998) for quadratic optimization, outperforming ANN (3-10-4; R²=0.327, RMSE = 0.289) amid biological nonlinearities. Cradle-to-gate LCA evidence 60–80% GWP abatement (32 kg CO₂ eq/m³ vs. 180 clay bricks), driven by ambient processing/waste upcycling. This novel experimental-ML-LCA paradigm positions mycelium BC as a scalable, non-structural insulation, catalysing the transition of fungal materials toward decarbonised construction.