Abstract
Land-based aquaculture requires scalable treatment systems capable of anticipating and mitigating pathogenic risks under changing environmental conditions. In this study, we collected meteorological and bacterial data and performed correlation analyses to identify key relationships, which guided the development of an integrated, predictive treatment system. This system combines a modular total suspended solids–pathogen removal system (TSS–PRS), composed of sediment filtration, UV disinfection, and oxygen dissolution, with a deep learning-based multi-layer perceptron (MLP) model to improve water quality and forecast pathogen dynamics. The TSS–PRS effectively reduced TAN (41.1%), bacterial activity (BQV, 74.5%), and turbidity (72.8%). It also successfully eliminated hazardous fish pathogens, including Photobacterium damselae, Tenacibaculum maritimum, Vibrio harveyi, and Enteromyxum leei. The MLP model further indicated that bacterial activity markedly increased under optimal conditions of turbidity (100 NTU), pH (7.97), and water temperature (27.5 °C).
Similar content being viewed by others
Data availability
The environmental and microbial datasets generated and analyzed in this study are not publicly available due to institutional data-sharing agreements. However, they are available from the corresponding author upon reasonable request. Summary statistics, selected time-series data, and detailed descriptions of all key variables and data-processing steps are provided in the Supplementary Information.
Code availability
The code used for Spearman’s correlation analysis, MLP-based microbial risk prediction, and SEM is available from the corresponding author upon reasonable request. Detailed information on the model architecture, training parameters, and evaluation procedures is provided in the Supplementary Information.
References
Cao, L. et al. Vulnerability of blue foods to human-induced environmental change. Nat. Sustain. 6, 1186–1198 (2023).
Rowley, A. F. et al. Diseases of marine fish and shellfish in an age of rapid climate change. iScience 27, 110838 (2024).
Oh, M.-J. et al. Change of pathogenicity in olive flounder Paralichthys olivaceus by co-infection of Vibrio harveyi, Edwardsiella tarda and marine birnavirus. Aquaculture 257, 156–160 (2006).
Kang, Y. J., Kim, D. S. & Kim, K. H. Evaluation of treatment efficacy of doxycycline and albendazole against scuticociliatosis in olive flounder (Paralichthys olivaceus). Aquaculture 416-417, 192–195 (2013).
Jin, C.-N. et al. Histopathological changes of Korea cultured olive flounder, Paralichthys olivaceus due to scuticociliatosis caused by histophagous scuticociliate, Philasterides dicentrarachi. Vet. Parasitol. 161, 292–301 (2009).
Shim, J. D., Hwang, S. D., Jang, S. Y., Kim, T. W. & Jeong, J. M. Monitoring of the mortalities in oliver flounder (Paralichthys olivaceus) farms of Korea. J. Fish. Pathol. 32, 29–35 (2019).
Hamidoghli, A. et al. Nutrition and feeding of olive flounder Paralichthys olivaceus: a review. Rev. Fish. Sci. Aquac. 28, 340–357 (2020).
Avunje, S., Oh, M.-J. & Jung, S.-J. Impaired TLR2 and TLR7 response in olive flounder infected with viral haemorrhagic septicaemia virus at host susceptible 15 °C but high at non-susceptible 20 °C. Fish. Shellfish Immunol. 34, 1236–1243 (2013).
Won, K. M. et al. Pathological characteristics of olive flounder Paralichthys olivaceus experimentally infected with Streptococcus parauberis. Fish. Sci. 76, 991–998 (2010).
Bae, M.-J., Im, E.-Y., Kim, H.-Y. & Jung, S. J. The effect of temperature to scuticociliatida Miamiensis avidus proliferation, and to mortality of infected olive flounder Paralichthys olivaceus. J. Fish Pathol. 22, 97–105 (2009).
Jung, J.-Y. et al. Feed and disease at olive flounder (Paralichthys olivaceus) farms in Korea. Fishes 5, 21 (2020).
Shih, Y.-J. et al. Impact of heavy precipitation events on pathogen occurrence in estuarine areas of the Puzi River in Taiwan. PLoS ONE 16, e0256266 (2021).
Shaw, K. S., Jacobs, J. M. & Crump, B. C. Impact of hurricane Irene on Vibrio vulnificus and Vibrio parahaemolyticus concentrations in surface water, sediment, and cultured oysters in the Chesapeake Bay, MD, USA. Front. Microbiol. 5, 2014 (2014).
Suzuki, Y., Teranishi, K., Matsuwaki, T., Nukazawa, K. & Ogura, Y. Effects of bacterial pollution caused by a strong typhoon event and the restoration of a recreational beach: transitions of fecal bacterial counts and bacterial flora in beach sand. Sci. Total Environ. 640–641, 52–61 (2018).
Lin, T.-H., Chiang, C.-F., Lin, S.-T. & Tsai, C.-T. Effects of small-size suspended solids on the emission of escherichia coli from the aeration process of wastewater treatment. Aerosol Air Qual. Res. 16, 2208–2215 (2016).
Hridoy, M. A. A. M., Bordin, C., Masood, A. & Masood, K. Predictive modelling of aquaculture water quality using IoT and advanced machine learning algorithms. Results Chem. 16, 102456 (2025).
Palaiokostas, C. Predicting for disease resistance in aquaculture species using machine learning models. Aquac. Rep. 20, 100660 (2021).
Becke, C. et al. Effects of unionized ammonia and suspended solids on rainbow trout (Oncorhynchus mykiss) in recirculating aquaculture systems. Aquaculture 499, 348–357 (2019).
Rojas-Tirado, P., Pedersen, P. B. & Pedersen, L.-F. Bacterial activity dynamics in the water phase during start-up of recirculating aquaculture systems. Aquacult. Eng. 78, 24–31 (2017).
Lee, D., Park, J., Lee, H. A. & Woo, N. C. A numerical approach to evaluating groundwater vulnerability to seawater intrusion on Jeju Volcanic Island, South Korea. Sustainability 15, 3081 (2023).
Oh, Y. H. et al. Spatiotemporal change in coastal waters caused by land-based fish farm wastewater-borne nutrients: results from Jeju Island, Korea. Mar. Pollut. Bull. 170, 112632 (2021).
Kim, Y.-I., Jeong, E., Lee, J.-Y., Chia, R. W. & Raza, M. Microplastic contamination in groundwater on a volcanic Jeju Island of Korea. Environ. Res. 226, 115682 (2023).
Moon, S.-H., Lee, J.-Y., Lee, B.-J., Park, K.-H. & Jo, Y.-J. Quality of harvested rainwater in artificial recharge site on Jeju volcanic island, Korea. J. Hydrol. 414-415, 268–277 (2012).
Darvishi Cheshmeh Soltani, R., Safari, M., Rezaee, A. & Godini, H. Application of a compound containing silica for removing ammonium in aqueous media. Environmental Progress Sustain. Energy https://doi.org/10.1002/ep.11969 (2014).
Taddeo, R., Prajapati, S. & Lepistö, R. Optimizing ammonium adsorption on natural zeolite for wastewaters with high loads of ammonium and solids. J. Porous Mater. 24, 1545–1554 (2017).
Zhao, Y. et al. Adsorption of high ammonium nitrogen from wastewater using a novel ceramic adsorbent and the evaluation of the ammonium-adsorbed-ceramic as fertilizer. J. Colloid Interface Sci. 393, 264–270 (2013).
Wold, P.-A. et al. Effects of membrane filtration on bacterial number and microbial diversity in marine recirculating aquaculture system (RAS) for Atlantic cod (Gadus morhua L.) production. Aquaculture 422-423, 69–77 (2014).
Kim, J. Y. & Lee, J.-L. Correlation of total bacterial and vibrio spp. populations between fish and water in the aquaculture system. Front. Mar. Sci. 4, 2017 (2017).
Kim, J.-Y., Shin, S.-M., Kwon, S. R. & Jung, S.-J. Development of a real-time PCR assay for noninvasive detection of Miamiensis avidus in olive flounder aquaculture. J. Fish. Dis. 48, e14134 (2025).
Imai, I., Inaba, N. & Yamamoto, K. Harmful algal blooms and environmentally friendly control strategies in Japan. Fish. Sci. 87, 437–464 (2021).
Xu, Y. et al. The first recorded fish-killing bloom in the Beibu Gulf, China: caused by dinoflagellate Karenia selliformis. Front. Mar. Sci. 12, 2025 (2025).
San Diego-McGlone, M. L. et al. Fish kills related to harmful algal bloom events in southeast Asia. Sustainability 16, 10521 (2024).
Hallegraeff, G. M. et al. Overview of Australian and New Zealand harmful algal species occurrences and their societal impacts in the period 1985 to 2018, including a compilation of historic records. Harmful Algae 102, 101848 (2021).
Soto, D., León-Muñoz, J., Garreaud, R., Quiñones, R. A. & Morey, F. Scientific warnings could help to reduce farmed salmon mortality due to harmful algal blooms. Mar. Policy 132, 104705 (2021).
Karlson, B. et al. Harmful algal blooms and their effects in coastal seas of Northern Europe. Harmful Algae 102, 101989 (2021).
Jyoti, S. et al. Spatiotemporal patterns of mortality events in farmed Atlantic salmon in British Columbia, Canada, using publicly available data. Sci. Rep. 14, 32122 (2024).
Wiese, T. R., Haskell, M., Jarvis, S., Rey-Planellas, S. & Turnbull, J. Concerns and research priorities for Scottish farmed salmon welfare—an industry perspective. Aquaculture 566, 739235 (2023).
Mills, M., Mollenkopf, D., Wittum, T., Sullivan, M. P. & Lee, J. One health threat of treated wastewater discharge in urban Ohio rivers: implications for surface water and fish gut microbiome and resistome. Environ. Sci. Technol. 58, 13402–13414 (2024).
Stentiford, G. D. et al. Sustainable aquaculture through the One Health lens. Nat. Food 1, 468–474 (2020).
Roy, S., Malla, S., Dekari, D. & Choudhury, T. G. One Health Approach: Human, Environment, and Animal Health in Management of Fish Diseases (eds Mallik, S. K., Shahi, N. & Pandey, P. K.) 281–297 (Springer Nature Singapore, 2025).
Shen, L. et al. Marine aquaculture can deliver 40% lower carbon footprints than freshwater aquaculture based on feed, energy and biogeochemical cycles. Nat. Food 5, 615–624 (2024).
Free, C. M. et al. Expanding ocean food production under climate change. Nature 605, 490–496 (2022).
Stentiford, G. D. et al. A seafood risk tool for assessing and mitigating chemical and pathogen hazards in the aquaculture supply chain. Nat. Food 3, 169–178 (2022).
Hallett, S. L. et al. Density of the waterborne parasite Ceratomyxa shasta and its biological effects on salmon. Appl. Environ. Microbiol. 78, 3724–3731 (2012).
Acknowledgments
This research was supported by the Korean Institute of Marine Science & Technology Promotion (KIMST), funded by the Ministry of Oceans and Fisheries (RS-2022-KS221676). The authors thank Bong-Lae Kim and Ki-Ju Kim of Korea Aquaculture Engineering (KAE) for their technical assistance and support during field operations.
Author information
Authors and Affiliations
Contributions
H.C. and S.M.S. conceptualized the study and designed the methodology. H.C., S.M.S., S.J., and S.H.L. conducted the investigation. H.C. and S.M.S. curated and analyzed the data and prepared the original manuscript draft. S.J. and T.K. reviewed and edited the paper. S.J. and T.K. supervised the project. T.K. acquired the funding. All authors reviewed and approved the final paper.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Choi, H., Shin, SM., Jung, S. et al. Scalable predictive framework for environmental pathogen control in land-based aquaculture. npj Clean Water (2026). https://doi.org/10.1038/s41545-025-00550-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41545-025-00550-7
