Marine pollution monitoring increasingly relies on Biological Early Warning Systems (BEWSs), which use living organisms as continuous, integrative sentinels of water quality. The moon jellyfish Aurelia aurita is a sensitive but under-exploited candidate for this role. We present a computer-vision BEWS pipeline that is unsupervised at inference time and operates without labelled pollution-response data, converting side-view aquarium video of single A. aurita medusae into a binary pollution alarm. Per-frame YOLO bounding-box detections are reduced to a continuous bell-area signal and a centroid trajectory, from which eleven pulsation, kinematic, and detection-quality features are extracted on 60 s sliding windows. A per-animal baseline is fitted on a clean-water baseline (recommended ≥15 min), and a two-layer detector—fast outlier detection on the mean absolute z-score with a k-of-N rule, plus one-sided CUSUM (cumulative sum) accumulation—flags any sustained deviation. Validation on six adult medusae exposed to diesel-WAF detected all six animals (95% CI 54–100%) and produced no false alarms in 203 clean-window opportunities (exact 95% upper bound 1.8%; rule-of-three estimate ≈1.5%). First-alarm latencies ranged from 1.0 to 23.7 min, and the observed responses were described as three descriptive patterns in this pilot dataset: sharp step-change, slow drift, and mixed. The deployed anomaly scoring step contains no neural-network weights, runs in under 300 lines of Python, and is designed for field-portable use in settings where a stationary side-view camera can be positioned alongside an aquarium, although field validation remains required. Per-animal anomaly detection accommodates the strong inter-individual variability of the diesel-WAF response that limits supervised clean-versus-polluted classification at this sample size.

Background. Over the past 15 years, expeditionary studies have been conducted on the Russian Black Sea shelf. They included comprehensive measurements of the physical, chemical, and biological characteristics of the pelagic ecosystem. One of the objectives of these studies was to assess the spatial distribution of the biomass of Aurelia aurita (Linnaeus, 1758) jellyfish, a common zooplankton species. Relevance. The high abundance of jellyfish in the waters of the Black and Azov Seas currently negatively affects the quality of recreation for citizens spending their vacations on the coast. At the same time, the proliferation of jellyfish in plankton also has a positive aspect associated with their harvesting and use as food and in the production of pharmaceuticals. The aim of this study is to identify trends in long-term variability of the spatial distribution and biomass of A. aurita jellyfish in the waters of the Russian Black Sea shelf from Adler to the southern coast of Crimea. Methods. This study utilizes the data collected during summer expeditions aboard the R/V “Professor Vodyanitsky” in 2010–2025. Fieldwork on each cruise lasted 20–26 days. The abundance and size of individuals were determined in samples collected with an ichthyoplankton net with a mesh size of 400 µm. Results. It has been shown that, in the summer season, the A. aurita population is dominated by medium-sized individuals (40–50 mm) ranging from 10 to 160 mm. No statistically significant monotonic along-shelf trends were found in the spatial distribution of jellyfish biomass during field surveys conducted in the summer and autumn of 2025. The biomass varied widely: from 1 to 984 g/m2. The biomass variation coefficient during surveys extending from Adler to the southern coast of Crimea exceeded the seasonal and long-term variability coefficients. Conclusion. On the Crimean shelf (with the greatest number of sampling catches), long-term biomass variability did not show a statistically significant trend. The average long-term biomass for this region was 238±227 g/m2, and the total biomass of A. aurita on the Russian shelf (from Adler to the southern coast of Crimea) was estimated at ~2 million tons.