Improvements in signal processing for the estimation of environmental parameters with machine learning using a compact tetrahedral array and sources of opportunity

Abstract

In previous work, we showed that we could localize sound sources using a compact tetrahedral hydrophone array in a continental shelf environment south of Block Island, Rhode Island. The tetrahedral array of phones, 0.5 m on a side, was deployed to monitor the construction and operation of the first offshore wind farm in the United States. Directions of arrival (DOAs) for a number of ships were computed using a time difference of arrival technique. Given the DOAs, ranges are estimated using supervised machine learning techniques. We extended that work to estimate a number of environmental parameters including water depth and sediment composition. Here, we report on results using new spectrogram processing techniques based on high resolution PE modeling. These results include inversions for sediment parameters with estimates of error. With this new higher resolution spectrogram processing, we also report on the impact of the sediment parameters on range estimation. We generalize the technique to generic continental shelf environments. [Work supported by the Office of Naval Research.]