The early Paleogene is characterized by a “hothouse” environment with repetitive transient warming events known as “hyperthermals.” While these paleoenvironmental changes are well-documented in the Pacific and Atlantic Oceans, records of such changes in the Indian Ocean are limited. Here, we present a new dataset of bulk chemical composition and stable isotopic ratios of the late Paleocene–middle Eocene sediments on the Exmouth Plateau in the mid-latitude eastern Indian Ocean. The bulk δ13C and δ18O suggest a warming period called the Early Eocene Climate Optimum (EECO) and cooling towards the middle Eocene in a long-term perspective. From a short-term perspective, we identified at least five hyperthermals (PETM, H2, I1, J, and ETM3) in the studied sections. We identified six independent components (ICs) corresponding to sediment source materials and post-depositional processes by applying independent component analyses (ICA) to the bulk chemical composition data. The time-series behavior of IC3 indicates an increase in detrital material or a decrease in carbonate rain flux during both long-term (EECO) and short-term (hyperthermal) warming. Additionally, the rise in IC2 implies an increased population of high consumers in the oceanic ecosystem during warming events around the Exmouth Plateau. Other ICs (IC1, IC4, IC5, and IC6), indicators of diagenetic processes and post-depositional remobilization of elements, showed excursions across hyperthermal horizons. These observations indicate that changes in the redox state of pore or bottom water in the Exmouth Plateau are associated with hyperthermals.

Microfossils of fish teeth and denticles, referred to as ichthyoliths, provide critical information for depositional ages, paleo-environments, and marine ecosystems, especially in pelagic realms. However, owing to their small size and rarity, it is time-consuming and difficult to analyze large numbers of ichthyoliths from sediment samples, limiting their use in scientific studies. Here, we propose a method to automatically detect ichthyoliths from microscopic images using a deep learning technique. We applied YOLO-v7, one of the latest object detection architectures, and trained several models under different conditions. The model trained under appropriate conditions with an original dataset achieved an F1 score of 0.87. We then enhanced the dataset efficiently using the pre-trained model. We validated the practical applicability of the model by comparing the number of ichthyoliths detected by the model with those counted manually. This revealed that the best model can predict the number of triangular teeth without manual check, and those of denticles and irregularly shaped teeth with manual check. This object detection method can extend the applicability of deep learning to a wider array of microfossils and has the potential to dramatically increase the spatiotemporal resolution of ichthyolith records for applications across disciplines.

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 real-time exploration of seafloor hydrothermal deposits. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. 2023.2.24: This work was published by IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://ieeexplore.ieee.org/document/10052641