Optimizing land mine detection across diverse mining environments: A hyperspectral data approach with regression models

The detection of landmines, namely anti-tank mines, explosive devices, and unexploded ordnance, is a formidable obstacle for the global community. The visible consequences of unobserved explosives in communities affected by war are characterized by significant devastation and human suffering. In order to effectively tackle this matter, it is imperative to use proactive strategies that focus on the identification and mitigation of these perilous substances prior to their potential infliction of harm. Nevertheless, the majority of current solutions exhibit significant deficiencies, such as exorbitant expenses, inefficiencies, and apprehensions over accuracy. These drawbacks are further compounded by the inherent trade-offs that exist between these elements, where improvements in one area often come at the expense of another. Contrarily, recent breakthroughs in the areas of deep learning, unmanned aerial vehicles, and sensor technologies are being recognized as potentially transformative elements in the domain of landmine identification and removal. This paper presents a thorough examination of recent scholarly investigations that integrate computerized technology in the field of landmine detection. To the extent of our current understanding, there has been no prior investigation that has thoroughly examined this particular domain. The main aim of this study is to investigate the incorporation of machine learning based regression methods in the field of landmine detection. The study specifically emphasizes the identification and resolution of existing issues that hinder the development of efficient automated solutions, hence enhancing performance optimization. The Sum of Sine Curve Fit Regression Model is proposed and proved a powerful and adaptable tool for extracting relevant information from this hyperspectral images.