Geopolymer concrete offers a favourable alternative to conventional Portland concrete due to its reduced embodied carbon dioxide (CO₂) content. Engineering properties of geopolymer concrete, such as compressive strength, are commonly characterised based on experimental practices requiring large volumes of raw materials, time for sample preparation, and costly equipment. To help address this inefficiency, this study proposes machine learning-assisted numerical methods to predict compressive strength of fly ash-based geopolymer (FAGP) concrete. Methods assessed included artificial neural network (ANN), deep neural network (DNN), and deep residual network (ResNet), based on experimentally collected data. Performance of the proposed approaches were evaluated using various statistical measures including R-squared (R²), root mean square error (RMSE), and mean absolute percentage error (MAPE). Sensitivity analysis was carried out to identify effects of the following six input variables on the compressive strength of FAGP concrete: sodium hydroxide/sodium silicate ratio, fly ash/aggregate ratio, alkali activator/fly ash ratio, concentration of sodium hydroxide, curing time, and temperature. Fly ash/aggregate ratio was found to significantly affect compressive strength of FAGP concrete. Results obtained indicate that the proposed approaches offer reliable methods for FAGP design and optimisation. Of note was ResNet, which demonstrated the highest R² and lowest RMSE and MAPE values.

This article considers semi-flexible composite (SFC) pavement materials made with reclaimed asphalt planings (RAP) and geopolymer cement-based grouts. Geopolymer grouts were developed and used to fill the internal void structure of coarse RAP skeletons with varying levels of porosity. The geopolymer grouts were formulated at ambient temperature using industrial by-products to offer economic and environmental savings relative to conventional Portland cement-based grouting systems. They were characterised on flowability, setting time, and compressive strength. The effect of grout and RAP on SFC material performance was evaluated using permeable porosity, compressive strength, and ultrasonic pulse velocity. SFC performance was significantly influenced by both grout type and RAP content. Improved performance was associated with mixtures of high-flowability/high-strength grout and low RAP content. A practical limitation was identified for combination of grout with low-flowability/fast-setting time and well-compacted RAP skeletons. Solids content exceeding 49% by volume was not feasible, owing to inadequate grout penetration. A suite of SFC materials was produced offering performance levels for a range of practical pavement applications. Preliminary relationships enabling prediction of SFC elastic modulus based on strength and/or ultrasonic pulse velocity test data are given. A pavement design is given using SFC as a sub-base layer for an industrial hardstanding.