An unfortunate legacy of former military activities at sites designated for base realignment and closure (BRAC) and at Formerly Used Defense Sites (FUDS) is the contamination of aquatic environments with military munitions. In the United States, more than 400 underwater sites, spanning an area in excess of 10 million acres, potentially contain such munitions. The presence of these munitions is a serious threat to both humans and the environment, so remediation is necessary. But the return of these contaminated waters to public use is contingent upon the analysis and assessment of wide-area and detailed underwater surveys. Therefore, the Department of Defense (DoD) has an express need for the development of technologies that will enable the detection and classification, at high probability, of military munitions found at underwater sites. The objective of this project is to develop a novel detection and classification framework for unexploded ordnance (UXO) that exploits sonar data. The new algorithms will be based on deep-learning techniques, specifically deep convolutional neural networks (CNNs). The successful development of this approach should enable the attainment of higher probabilities of detection and classification, at much lower false alarm rates, than is possible with existing approaches. As a result, the application of these machine-learning algorithms to sonar data collected at potentially contaminated underwater sites can guide remediation efforts to effect savings. Specifically, because fewer resources will be spent investigating harmless clutter, the cost of remediation should decrease substantially.

“Deep learning” is the generic umbrella term used to denote classification algorithms with architectures characterized by a nested functional structure that engenders highly nonlinear decision surfaces. The great capacity of deep-learning algorithms, such as deep CNNs, when paired with vast amounts of data and sufficient computational resources, has translated into state-of-the-art performance in diverse domains. In the previous SERDP Exploratory Development (SEED) project, MR18-1444 “Cubist-Inspired Deep Learning with Sonar for UXO Detection and Classification,” the feasibility of using CNNs for UXO remediation was successfully demonstrated. A framework to exploit multiple representations of sonar data simultaneously was developed, and the promise of using sonar data in the form of acoustic-color plots was highlighted. In this project, a follow-on to the SEED effort, new acoustic-color-based CNNs that leverage the insights gained from the previous research will be developed for UXO detection and classification. The main objective of this work is to use the developed CNN framework in conjunction with specially controlled experiments to learn principled, explainable features that can be tied directly to the wave phenomena of the physics involved. A concerted effort will be made to develop these more mature and sophisticated CNNs with, and for, sonar data from systems currently under SERDP and ESTCP funding.

This project aims not only to develop practical algorithms for guiding UXO remediation efforts, but also to enable a deeper fundamental understanding of the physics of the problem from a principled scientific perspective. As such, this project will address the DoD’s need for robust detection and classification approaches for underwater UXO, while simultaneously augmenting the scientific community’s knowledge base. The algorithms to be developed will be functional with measured data from existing systems, and hence readily deployable in a short time frame for use in actual remediation efforts.