Answers are grounded in this paper and cite their sources.
The construction sector must reduce the environmental burden of its materials while keeping structures safe, durable and affordable. Sustainable construction materials—supplementary cementitious materials (SCMs), agricultural ashes, recycled aggregates, waste-derived fillers, fibres, polymer modifiers and bio-mediated self-healing systems—offer ways to cut clinker use, conserve natural resources and divert waste from landfill. Their performance, however, is sensitive to source variability, processing, dosage, curing and exposure, which makes mixture design and quality control harder than for conventional concrete. Machine learning (ML) can help by learning the nonlinear links between composition, processing and performance from experimental data. This review summarises recent advances in the main families of sustainable materials and examines how ML is being applied across construction technology: predicting strength and durability, optimising low-carbon mixtures, building fast surrogates of structural response and automating inspection. The review finds that the value of ML depends more on data quality, representative material variability and honest validation than on the choice of algorithm, and that sustainability claims should be judged on a functional, life-cycle basis rather than on waste content alone. A simple integrated framework linking material characterisation, testing, ML and environmental assessment is proposed, and priorities for future research are identified.
No takes yet. Share an insight, caveat, or question.
Satej Shingan (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: