Towards Automated Target Picking in Scalar Magnetic Unexploded Ordnance Surveys: An Unsupervised Machine Learning Approach for Defining Inversion Priors

Abstract

With advancements in both the quality and collection speed of magnetic data captured by uncrewed aerial vehicle (UAV)-based systems, there is a growing need for robust and efficient systems to automatically interpret such data. Many existing conventional methods require manual inspection of the survey data to pick out candidate areas for further analysis. We automate this initial process by implementing unsupervised machine learning techniques to identify small, well-defined regions. When further analysis is conducted with magnetic inversion algorithms, then our approach also reduces the nonlinear computation and time costs by breaking one huge inversion problem into several smaller ones. We also demonstrate robustness to noise and sidestep the requirement for large quantities of labeled training data: two pitfalls of current automation approaches. We propose first to use hierarchical clustering on filtered magnetic gradient data and then to fit ellipses to the resulting clusters to identify subregions for further analysis. In synthetic data experiments and on real-world datasets, our model successfully captures all true targets while simultaneously proposing fewer computationally costly false positives. With this approach, we take an important step towards fully automating the detection of high-risk subregions, but we wish to emphasize the importance of prudent skepticism until it has been tested and proven on more diverse data.