Published Paper Details:

The main aim of this research is to discuss how machine learning methods may be used to anticipate subterranean cavern displacement. This research presents a series of new machine learning-based deliverability prediction models for subterranean caves. One of the most dangerous occurrences that may lead to the collapse of buildings is the displacement of rock mass in tunnels and subterranean constructions. Underground engineering technologies are becoming more commonplace across the globe. Complex and unpredictable geology and geomechanics create obstacles and need novel strategies in underground geoengineering [1]. In addition to the massive overburden and extreme temperatures, these issues need complex engineering design. Oil engineering, nuclear waste disposal, energy storage and CO2 storage are only a few examples of additional environmental issues. Geotechnical data is frequently produced in enormous quantities during big projects. Using this data to make better decisions and enhance design and construction processes [1] may be very beneficial. As a result, consistent methods for gathering, organizing, and displaying collected data must be established. It is possible to examine this large data using machine learning algorithms. With regard to cavern displacement predictions, the research shows how machine learning approaches may be used.