Enhancing Kimberlite Exploration Through Quantum Support Vector Machines: A Comparative Study of Quantum and Classical SVM Approaches

Kimberlite exploration is one of the significant areas of interest for diamond mines that have generally relied on geological, geochemical, and geophysical data. All the features of the data are complex and variable; processing this data can be tedious. But, quantum computing, with possibilities of quantum parallelism and entanglement, presents prospective advantages in managing large and complex data sets. By leveraging quantum mechanical phenomena, QSVMs offer significant advantages over traditional methods in terms of accuracy and efficiency. The study reviews existing literature, compares QSVMs with classical SVMs, and explores their potential to enhance geological data classification. Results demonstrate that QSVMs consistently outperform classical SVMs in multiple performance metrics across various datasets. The quantum approach exhibits improved accuracy, precision, recall, and F1-score, highlighting its potential to significantly enhance kimberlite exploration. Quantum computing holds the promise of transforming kimberlite exploration, leading to more accurate predictions, efficient decision-making, and ultimately, more sustainable mining practices.