Deciphering the Controls of Limestone Texture, Mineralogy, Microfacies, and Diagenesis on Lime Formation through a Novel Integration of Laboratory-Based Analytical and Machine Learning Approaches.

Summary

Limestones exhibit diverse textural, mineralogical, and microstructural characteristics that reflect their complex depositional environments and diagenetic histories. These variations fundamentally govern their thermal decomposition pathways, physicochemical transformations, and energy consumption during calcination for lime production. Lime (CaO) is a strategic industrial commodity widely used in modern construction, building foundations, earthen dams, and expansive soils.

Despite extensive studies on limestone decomposition during calcination, the mechanistic relationships between microfacies characteristics, diagenetic alterations, and their influence on reaction kinetics, activation energy, surface area, and sintering behavior remain poorly constrained. Consequently, this knowledge gap limits (a) the ability to predict calcination behavior based on each limestone’s intrinsic properties and (b) the development of models linking composition, texture, microfacies, porosity, and diagenetic imprints to thermal reactivity and calcination responses. These limitations necessitate a trial-and-error approach, resulting in excessive energy consumption and reduced process efficiency.

This research proposal aims to pioneer a novel mechanistic framework that deciphers how limestone fabrics, mineralogy, porosity, and diagenetic features control thermal decomposition behavior under varying heating regimes. The proposed workflow begins with an integrative methodology combining XRD, TGA, and FTIR spectroscopy, XRF, Rock-Eval pyrolysis, quantitative point-counting using transmitted-light microscopy, and SEM imaging to analyze and quantify the microstructure, fabric, particle size distribution, pore types, and diagenetic textures of the studied limestone microfacies. These techniques will characterize the mineralogy, grain and mud content, porosity, pore morphology, organic matter, and impurity content of different quarried limestone types, providing a comprehensive dataset of their depositional and diagenetic variability. Subsequently, laboratory experiments will assess the thermal responses of representative limestone microfacies by resistant and microwave heating to investigate reaction kinetics, activation energies, mineral phase transitions, and microstructural evolution.

To establish quantitative relationships between limestone microfacies characteristics and calcination behavior, all acquired datasets will be integrated within a statistical machine learning framework. Supervised algorithms (e.g., Random Forest, XGBoost, and Artificial Neural Networks) will be applied to predict calcination performance indicators, including decomposition rate, lime yield, and hydration reactivity, based on the limestone microfacies pre-calcination characteristics. In parallel, unsupervised learning techniques (e.g., Principal Component Analysis and K-Means clustering) will classify limestone microfacies and diagenetic types according to their thermal response and lime quality. Model interpretability techniques such as SHAP (Shapley Additive Explanations) will quantify the relative importance of key predictors, including mud-to-grain ratio, pore types, and impurity content, on calcination efficiency and lime reactivity. This integrative, data-driven approach will yield robust predictive models and deepen mechanistic understanding of how limestone mineralogical and diagenetic variations influence thermal decomposition kinetics and the physicochemical properties of lime.

This research will advance theoretical understanding of limestone microfacies reactivity, mineral stability, and thermochemical pathways during calcination, while providing a scientific foundation for improving the energy efficiency of lime production. The outcomes will directly align with the environmental sustainability of Egypt’s Vision 2030 and the new Republic construction and architectural revolution, promoting a transition toward more energy-responsible and resource-efficient industrial processes.

Achievements

List of Publications from the Project

Partners

Project Members

• Mostafa Mohamed Eid
• Yasmin Gamal Ahmed
• Ahmed Mohamed Yahya Ahmed
• AbdelMonem Soltan

Project Leaders