Automated Detection of Hydrothermal Emission Signatures From Multibeam Echo Sounder Images Using Deep Learning

Abstract

Seafloor massive sulfide deposits have attracted attention as a mineral resource, as they contain a wide variety of base, precious, and other valuable critical metals. Previous studies have shown that signatures of hydrothermal activity can be detected by a multi-beam echo sounder (MBES), which would be beneficial for exploring sulfide deposits. Although detecting such signatures from acoustic images is currently performed by skilled humans, automating this process could lead to improved efficiency and cost effectiveness of exploration for the seafloor deposits. Herein, we attempted to establish a method for automated detection of MBES water column anomalies using deep learning models. First, we compared the "Mask R-CNN" and "YOLO-v5" detection model architectures, wherein YOLO-v5 yielded higher F1 scores. We then compared the number of training classes and found that models trained with two classes (signal and noise) exhibited superior performance compared with models trained with only one class (signal). Finally, we examined the number of trainable parameters and obtained the best model performance when the YOLO-v5l model with a large trainable parameters was used in the two-class training process. The best model had a precision of 0.928, a recall of 0.881, and an F1 score of 0.904. Moreover, this model achieved a low false alarm rate (less than 0.7%) and had a high detection speed (20−25 ms per frame), indicating that it can be applied in the field for automatic and realtime exploration of seafloor hydrothermal deposits.

Applicability of Object Detection to Microfossil Research: Implications From Deep Learning Models to Detect Microfossil Fish Teeth and Denticles Using YOLO‐v7

“…Recently, we compared the performances of object detection models “Mask R‐CNN” and “YOLOv5” (Jocher et al., 2022) in detecting signals of hydrothermal activity in echo sounder images (Mimura, Nakamura, Takao, et al., 2023) and showed that the YOLOv5 model achieved much higher performance than that of the Mask R‐CNN model. Here, with reference to this, we applied “YOLOv7” (Wang et al., 2022), one of the latest versions of You Only Look Once (YOLO, Redmon et al., 2016), to solve the problem of ichthyolith detection.…”

“…Computer vision technologies are developing rapidly. In particular, image processing using deep learning has been applied to various fields, including earth science (Hoeser & Kuenzer, 2020; Mimura, Nakamura, Takao, et al., 2023). Automating previous manual observation processes saves time and provides opportunities for discoveries by increasing the number of fossils that can be observed and processed.…”