Mineral transformations often induce microstructural deteriorations during temperature variations. Hence, it is crucial to understand why and how this microstructure weakens due to mineral alteration with temperature and the correlated physical and mechanical responses. Therefore, in this study, physical, chemical, thermal, petrographic, and mechanical analyses were carried out to comprehend better the thermal behaviors of Egyptian granodiorite exposed to temperatures as high as 800 °C. The experimental results indicate that the examined attributes change in three distinct temperature phases. Strength zone (up to 200 °C): During this phase, the temperature only slightly impacts the granodiorite mass loss and porosity, and the P-wave velocity and E slightly decrease. However, the rock structure was densified, which resulted in a minor increase in strength. After that, the transition zone (200–400 °C) was distinguished by the stability of most studied parameters. For instance, mass and porosity did not significantly alter, and the uniaxial compressive strength steadily increased with an axial failure mode. When the temperature rises, transgranular cracks cause the P-wave velocity and elastic modulus to decrease moderately. The decay zone started after 400 °C and continued to 800 °C. This zone is characterized by complicated factors that worsen the granodiorite properties, lead to color shift, and produce a shear failure mode. The properties of granodiorite became worse because of chemical reactions, structural and crystal water evaporation, rising thermal expansion coefficient variation, and quartz inversion at 575 °C (α to β, according to the differential thermal analysis). Thermal damage greatly affected granodiorite’s physical and mechanical properties and microstructure at 800 °C. As a result, UCS measurements were extremely small with a complex failure pattern, making Vp and E unattainable.

The mechanical properties of rocks, such as uniaxial compressive strength and elastic modulus of intact rock, must be determined before any engineering project by employing lab or in situ tests. However, there are some circumstances where it is impossible to prepare the necessary specimens after exposure to high temperatures. Therefore, the propensity to estimate the destructive parameters of thermally heated rocks based on non-destructive factors is a helpful research field. Egyptian granodiorite samples were heated to temperatures of up to 800 °C before being treated to two different cooling methods: via the oven (slow-cooling) and using water (rapid cooling). The cooling condition, temperature, mass, porosity, absorption, dry density (D), and P-waves were used as input parameters in the predictive models for the UCS and E of thermally treated Egyptian granodiorite. Multi-linear regression (MLR), random forest (RF), k-nearest neighbor (KNN), and artificial neural networks (ANNs) were used to create predictive models. The performance of each prediction model was also evaluated using the (R²), (RMSE), (MAPE), and (VAF). The findings revealed that cooling methods and mass as input parameters to predict UCS and E have a minor impact on prediction models. In contrast, the other parameters had a good relationship with UCS and E. Due to severe damage to granodiorite samples, many input and output parameters were impossible to measure after 600 °C. The prediction models were thus developed up to this threshold temperature. Furthermore, the comparative analysis of predictive models demonstrated that the ANN pattern for predicting the UCS and E is the most accurate model, with R² of 0.99, MAPE of 0.25%, VAF of 97.22%, and RMSE of 2.04.

In many thermal geotechnical applications, liquid nitrogen (LN₂) utilization leads to damage and cracks in the host rock. This phenomenon and associated microcracking are a hot topic that must be thoroughly researched. A series of physical and mechanical experiments were conducted on Egyptian granodiorite samples to investigate the effects of liquid nitrogen cooling on the preheated rock. Before quenching in LN₂, the granodiorite was gradually heated to 600 °C for two hours. Microscopical evolution was linked to macroscopic properties like porosity, mass, volume, density, P-wave velocity, uniaxial compressive strength, and elastic modulus. According to the experiment results, the thermal damage, crack density, porosity, and density reduction ratio increased gradually to 300 °C before severely degrading beyond this temperature. The uniaxial compressive strength declined marginally to 200 °C, then increased to 300 °C before monotonically decreasing as the temperature rose. On the other hand, at 200 °C, the elastic modulus and P-wave velocity started to decline significantly. Thus, 200 and 300 °C were noted in this study as two mutation temperatures in the evolution of granodiorite mechanical and physical properties, after which all parameters deteriorated. Moreover, LN₂ cooling causes more remarkable physical and mechanical modifications at the same target temperature than air cooling. Through a deeper comprehension of how rocks behave in high-temperature conditions, this research seeks to avoid and limit future geological risks while promoting sustainability and understanding the processes underlying rock failure.

The journal retracts the article titled “Prediction of Strength Parameters of Thermally Treated Egyptian Granodiorite Using Multivariate Statistics and Machine Learning Techniques”