Table 1 Low-carbon properties prediction by different researchers.

No	Reference	Year	Algorithms used	Main raw materials¹	Predicted outputs
1	¹⁶	2024	BPNN, SI	RCA, FA	CS, CIR
2	¹⁷	2023	FQ, NLR, MLR, ANN	FA	CS
3	¹⁸	2024	LDA, AdaBoost, ANN	CSA	CS
4	¹⁹	2021	SVM, RF. AdaBoost, DT, KNN	MK	CS
5	²⁰	2020	AdaBoost	FA, Slag	CS
6	²¹	2022	LightGBM, XGBoost	MK	CIR
7	²²	2024	RF, LightGBM, XGBoost	RHA	CS
8	²³	2020	RF, GEP, ANN, DT	HSC	CS
9	²⁴	2018	MARS, M5-tree, SVM, ELM	LFC	CS
10	²⁵	2020	GEP	HSC	CS
11	²⁶	2023	RF, ANN, MARS	GPC	CS
12	²⁷	2024	ANN, SVM, M5-tree	SCC	CS, STS
13	²⁸	2022	GB, XGBoost, SVM, PSO	RCA	CS
14	²⁹	2022	DT, ET, AdaBoost, XGBoost, LightGBM, LKRR	Slag, FA	CS

RCA Recycled concrete aggregates, FA Fly ash, CIR chloride ion resistance, MK metakaolin, CSA coral sand aggregates, RHA rice husk ash, HSC high-strength concrete, GPC geopolymer concrete, SCC self-compacting concrete, BPNN Back propagation neural network, SI Swarm intelligence, FQ Full-quadratic, NLR Nonlinear regression, MLR Multi-linear regression, MARS multivariate adaptive regression spline, ELM extreme learning machine, SVM support vector machine, DT decision tree, ET extra tree, GB Gradient boosting, RF random forest, KNN k-nearest neighbors, AdaBoost Adaptive boosting algorithm, Light GBM light gradient boosting machine, XGBoost extreme gradient boosting, PSO particle swarm optimization, LKRR Laplacian kernel ridge regression, ANN Artificial neural network, GEP gene expression programming, LFC lightweight foam concrete, CS compressive strength, STS splitting tensile strength.

Quick links

Search