Finding alternatives to natural resources is important for a sustainable future and is essential to infrastructure projects. Among these replacements is the use of coffee waste as soil stabilizers. Coffee husk ash (CHA) is a solid waste obtained by the processing of coffee beans on a farm or factory. The main aim of this study is to determine the geotechnical properties of clay soil treated with CHA to develop a low-cost, environmentally friendly alternative composition. Laboratory tests were conducted to investigate the influence of CHA on the physical properties and the mechanical properties of clay. The CHA concentration was adjusted from 5% to 25% by the dry weight of clay in 5% increments. The clay classification of the mixture becomes coarser following the addition of the CHA. At 25% CHA, a peak UCS of 130.83 kN/m² was measured compared with the untreated clay of 89.17 kN/m². In addition, the cohesion values and internal friction angles of soil for 0% and 25% CHA increased from 80.1 kN/m² to 148.7 kN/m² and from 16.1° to 25.8°, respectively. It was found that CHA can improve the strength of clay by forming a pozzolanic and hydration process that fills soil voids and binds particles together.

Many slope failures take place during or after rainfall events. Landslides are one of the tragedies associated with slope failures and often lead to fatal accidents. A study on the effects of extreme rainfall on slope stability considering the historical rainfall data, slope characteristics and properties, and flow boundary conditions was undertaken. This study investigated the behaviour of the Sg Langat slope under the influence of extreme rainfall gathered from historical data. Sg Langat was selected as the research area because of its high riverbank failures. The focus of this study are as follows: 1) to determine the effect of slope angles on slope stability, 2) to assess the development of pore-water pressure based on the changing groundwater levels, and 3) to analyse the influence of extreme rainfall events on the slope behaviour via numerical modelling. This study enhances the understanding of certain slope conditions and contributes to the analysis of slope stability through numerical modelling, making it relatively convenient to observe the soil conditions for determining the slope stability of the research area in regards to the effect of extreme rainfall. The results were obtained with respect to the changes in the pore-water pressure and the factor of safety. It was observed that the pressure changes were different for every channel, demonstrating that the generation of negative pore-water pressure was not directly affected by the type of analysis and the rainfall infiltration alone. Moreover, the slopes on all channels presented were considered unstable because of the considerable changes in the negative pore-water pressure at a relatively shallow depth, causing soil strength reduction. The factor of safety recorded for Channel 1 was the lowest at 0.18, whereas Channel 3 had the highest factor of safety of 1.11 but was still considered unsafe as it fell below the standard safety margin of 1.3. Apart from the different rainfall intensities applied, the geometry of the slopes also affected the slope stability.

Landslides have been classified as the most dangerous threat around the world, causing huge damage to properties and loss of life. Increased human activity in landslide-prone areas has been a major contributor to the risk of landslide occurrences. Therefore, machine learning has been used in landslide studies to develop a landslide predictive model. The main objective of this study is to evaluate the most suitable sampling ratio for the predictive landslide model in the Langat River Basin (LRB) using Artificial Neural Networks (ANNs). The landslide inventory was divided randomly into training and testing datasets using four sampling ratios (50:50, 60:40, 70:30, and 80:20). A total of 12 landslide conditioning factors were considered in this study, including the elevation, slope, aspect, curvature, topography wetness index (TWI), distance to the road, distance to the river, distance to faults, soil, lithology, land use, and rainfall. The evaluation model was performed using certain statistical measures and area under the curve (AUC). Finally, the most suitable predictive model was chosen based on the model validation results using the compound factor (CF) method. Based on the results, the predictive model with an 80:20 ratio indicates a realistic finding and was classified as the first rank among others. The AUC value for the training dataset is 0.931, while the AUC value for the testing dataset is 0.964. These attempts will help a great deal when it comes to choosing the best ratio of training samples to testing samples to create a reliable and complete landslide prediction model for the LRB.

Expansive or soft soils cause significant geotechnical issues for foundations and subgrades because they show swell–shrink behaviour under wet and dry conditions. These volume changes can result in cracking, heaving, uneven settlement, and structural or pavement damage, ultimately increasing maintenance and repair costs. While traditional Portland cement and lime stabilisers effectively enhance soil strength and reduce swell–shrink behaviour, the cement production process is responsible for only approximately 7%–8% of global CO₂ emissions, prompting a transition toward sustainable alternatives. This comprehensive review consolidates recent advancements in soil stabilisation using industrial by-products, such as fly ash, ground granulated blast furnace slag (GGBS), steel slag, cement kiln dust, silica fume, bottom ash, red mud, waste foundry sand, brick dust, calcium carbide residue, water treatment sludge, etc. These materials leverage pozzolanic and latent hydraulic properties to form C-A-H, C-S-H, and N-A-S-H gels, thereby densifying the soil microstructure, improving CBR (%), UCS, and reducing plasticity and swelling potential. Optimisation studies indicate that industrial waste stabilisers often match or exceed conventional binder performance, GGBS-steel slag combinations yielding 105% higher UCS than ordinary Portland cement, and silica fume enhances cement-stabilised soils by 22% at reduced dosages. However, inherent compositional variability, long-term durability concerns including sulfate attack and freeze–thaw degradation, and the absence of standardised design guidelines restrict large-scale implementation. This review integrates mechanistic, microstructural, and sustainability insights, highlighting the need for durability research, standardised methods, and large-scale field validation to advance industrial waste-based stabilisation within circular construction practices in geotechnical engineering.