Aquaculture facilities are not only an important component of fisheries and local economies, but they also have significant economic and environmental impacts that require efficient and sustainable management. Additionally, knowing the exact locations of aquaculture facilities is crucial for operating ships in nearshore areas, as their presence significantly affects the safe navigation of vessels. However, current aquaculture facility data suffer from slow update cycles due to reliance on field surveys and data processing, and their low spatial resolution does not meet the accuracy requirements in the field. To address this issue, this study takes a first step toward updating aquaculture facility data in quasi-real time using satellite imagery. Specifically, we evaluated the spatial agreement between detected aquaculture facility data and existing data based on Sentinel-1 satellite imagery. While many previous studies on aquaculture facility detection have utilized optical satellites, this study aims to verify the detectability of aquaculture facilities using SAR (Synthetic Aperture Radar) imagery, which can be acquired regardless of weather conditions or time of day. The aquaculture facility data provided by the Korea Hydrographic and Oceanographic Agency is available in both polygon and point formats, with the last update date being December 19, 2024. Accordingly, we analyzed Sentinel-1 data acquired around the same time (December 20, 2024) and compared it with the polygon data. Our analysis revealed significant discrepancies between the two datasets. These findings highlight the need to update current aquaculture facility data and suggest that satellite imagery, with its ability to regularly cover broad areas, could be employed to improve the accuracy and timeliness of aquaculture data updates. This confirms the potential value and utility of satellite imagery as an effective tool for managing aquaculture facilities.

In maritime accident prevention, it is important to identify not only high-risk sea areas but also which accident-types are most likely to occur there. This study combines survey responses from 826 Korea Coast Guard practitioners with 3856 maritime accidents mapped onto an H3 grid over Korean territorial waters during 2021–2023, and proposes a practitioner-informed framework for predicting accident-type-specific risk. The survey showed limited use of quantitative, standardized accident risk criteria but high demand for AI-based prediction and area-level risk analysis. Practitioners’ perceived accident frequency differed substantially from the empirical accident distribution, whereas their prevention priorities aligned more closely with the actual pattern. Accordingly, this study treats the accident-type taxonomy not as a fixed prediction target but as a design variable of the label space for decision support. A two-stage framework first estimates accident occurrence at the H3 grid-time level and then classifies the accident-type conditional on occurrence. Comparing survey-aligned, data-aligned, union, sufficient-sample, and full administrative (7-class) framings under a common training protocol shows that accident-type organization creates trade-offs among field interpretability, coverage, class granularity, and predictive stability. The study thus reframes maritime accident prediction as an accident-type-specific decision-support problem-linking practitioner perception with empirical evidence.