This study explored the use of coir fibers extracted from coconut husks, an agro-waste material that constitutes sanitation and environmental pollution problems, as a reinforcing element in the production of metakaolin-based geopolymer composites with improved properties. A series of sample formulations were produced with varying coir fiber content (0.5, 1.0, 1.5, and 2.0 percent weight of metakaolin powder). The investigation was conducted using a 10 M NaOH alkaline solution with a 0.24 NaOH:Na₂SiO₃ mass ratio. Samples were cured for 28 days and tested for bulk density, ultrasonic pulse velocity (UPV), and compressive and flexural strength. Microstructural examinations such as X-ray diffraction (XRD), Fourier transform infrared (FTIR) spectroscopy, and scanning electron microscopy (SEM) were also performed on samples. Compressive strength values up to 21.25 N/mm² at 0.5% fiber content and flexural strength values up to 10.39 N/mm² at 1% fiber content were achieved in this study. The results obtained showed a decreasing bulk density of geopolymer samples (2113 kg/m³ to 2045 kg/m³) with increasing coir fiber content. The geopolymer samples had UPV values varying from 2315 m/s to 2717 m/s. Coir fiber with 0.5–1.0% fiber content can be incorporated into metakaolin-based geopolymers to produce eco-friendly composite materials with improved mechanical properties for sustainable development.

This research focuses on the environmental-friendly production of Borassus fruit fibers (BNF), its characterization, and hygroscopic properties determination via Dynamic Vapor Sorption (DVS). The experimental results obtained from the hygroscopic behavior analysis were used to create a primary dataset to train and test Decision Tree Regression (DTR) and Gradient Boosting Regressor (GBR) models. The created primary dataset comprised 294 observations, from which 80% were used to train the models, and the remaining 20% were used for the testing of the two models. The models exhibited high accuracy, easy interpretability on the small-size dataset, and flexibility with regards to the nature of the relationship between the input and output variable. Both models successfully predicted the hygroscopic behavior with the Gradient Boosting Regressor outperforming Decision Tree Regression by indicating values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R², respectively, during the desorption of the BNF, and values of 0.012, 0.109, 0.059, and 0.999 for MSE, RMSE, MAE, and R², respectively, during the desorption of the BNF. This suggests that the Gradient Boosting Regressor illustrated the maximum accuracy. The outcomes can be utilized to provide an alternative for traditional methods, which can often be costly and time-consuming by improving the engineering properties of BNF. The models can be used in the construction sector to lower costs as they are able to pinpoint elements influencing the characteristics for specific applications to grasp its various properties through the prediction of its hygroscopic properties.

Earth-based materials have shown promise in the development of ecofriendly and sustainable construction materials. However, their unconventional usage in the construction field makes the estimation of their properties difficult and inaccurate. Often, the determination of their properties is conducted based on a conventional materials procedure. Hence, there is inaccuracy in understanding the properties of the unconventional materials. To obtain more accurate properties, a support vector machine (SVM), artificial neural network (ANN) and linear regression (LR) were used to predict the compressive strength of the alkali-activated termite soil. In this study, factors such as activator concentration, Si/Al, initial curing temperature, water absorption, weight and curing regime were used as input parameters due to their significant effect in the compressive strength. The experimental results depict that SVM outperforms ANN and LR in terms of R² score and root mean square error (RMSE).

The goal of this study was to explore the feasibility of production of cellulosic pulp and nanofibrillated cellulose (NFC) from prevalent plants in west and central Africa; raffia fiber (Raphia vinifera), cassava bagasse (Manihot esculenta) and ambarella (Spondias dulcis); in order to assess their suitability as source of reinforcing elements for composite. Fibers were produced using both organosolv and basic soda methods to evaluate the effect of processing on fiber properties. The morphological characterization showed pulp fibers of width 24–33 µm and length 0.2–1.1 mm while nanofibers of width 110–278 nm were obtained after nanofibrillation. FTIR confirmed that the isolation processes effectively removed amorphous content (lignin and hemicellulose) while X-ray Diffraction analysis demonstrated the increase in crystallinity when fibers were processed from pulp to nanofibrillated cellulose. Despite being fibrous in nature, ambarella did not respond to soda and organosolv pulping possibly due to high wax (18.87%) and ash (16.05%) content. The yield of raffia pulp is within the range found in conventional wood sources. The nanosize nature, high specific surface area and aspect ratio, biodegradability and renewability of nanofibrillated cellulose have demonstrated the potential of raffia fibers and cassava bagasse as suitable sources for micro/nanocellulose.