Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Forecasting closures on shellfish farms using machine learningPublication . O’Donncha, Fearghal; Akhriev, Albert; Fragoso, Bruno; Icely, JohnBiotoxins and harmful algal blooms (HABs) are damaging to aquaculture operations. Occurrences lead to disrupted operations, fish kills, and significant risks to human health. The conditions leading to blooms are driven by known, but complex processes. Heuristics exist about the drivers but the nonlinearity and opaqueness of relationships make it difficult to resolve using traditional rule-based mathematical models. An alternative approach leverages machine learning to uncover the conditions that lead to the closure of farms. This paper presents a comprehensive framework that combines semi-automated machine learning with ensemble classification approaches to predict site closures. Performance is evaluated on 7 years of site closure data from a shellfish farm in Southwest Portugal, together with publicly available environmental data. The model reports an accuracy of 83% across a challenging forecasting task. The proposed framework provides a pragmatic, scalable, site-specific decision tool to help aquaculture stakeholders mitigate the impacts of HABs.
- Aquaculture in the crossroad of microplastic contaminationPublication . Bebianno, Maria; Manthopoulos, Michael; Nathan, Justine; Cristina, Sónia; Ribeiro, Laura; Luna-Araújo, Ravi; Icely, John; Dias Duarte Fragoso, Bruno; Moura, DelmindaPlastic pollution threatens life and human health, with microplastics (MP) linked to seafood consumption. MPs enter aquaculture through the environment and from aquaculture gear. During aquaculture production, plastic is used in nets and sacks for the growth process and in collecting and processing so it becomes important to expand the knowledge about how much MPs are present in seafood. The aim was to investigate the presence of MPs in three bivalve’s species; oysters (Crassostrea gigas), clams (Ruditapes decussatus), and mussels (Mytilus galloprovincialis) produced in offshore and intertidal aquaculture in two different climate conditions. Water, bivalves and sediments were collected from each site and abundance size, colour, type and composition of the MPs polymers analysed. The most common colour in offshore aquaculture was blue while in intertidal was black, and the type was fragments. Sixty per cent of bivalves did not have MPs in their tissues Bivalves from offshore aquaculture was less impacted by MPs probably due to the hydrographic conditions and distance from the coast. Most of MPs ingested by bivalves were related to the plastic type used in aquaculture materials. Transformative solutions and/or procedures to eliminate plastic from aquaculture equipment are needed, and depuration might be a practical solution.
- Aquaculture in the crossroad of microplastic contaminationPublication . Bebianno, Maria; Manthopoulos, Michael; Nathan, Justine; Cristina, Sónia; Ribeiro, Laura; Luna-Araújo, Ravi; Icely, John; Dias Duarte Fragoso, Bruno; Moura, DelmindaPlastic pollution threatens life and human health, with microplastics (MP) linked to seafood consumption. MPs enter aquaculture through the environment and from aquaculture gear. During aquaculture production, plastic is used in nets and sacks for the growth process and in collecting and processing so it becomes important to expand the knowledge about how much MPs are present in seafood. The aim was to investigate the presence of MPs in three bivalve's species; oysters (Crassostrea gigas), clams (Ruditapes decussatus), and mussels (Mytilus galloprovincialis) produced in offshore and intertidal aquaculture in two different climate conditions. Water, bivalves and sediments were collected from each site and abundance, size, colour, type and composition of the MPs polymers analysed. The most common colour in offshore aquaculture was blue while in intertidal was black, and the type was fragments. Sixty per cent of bivalves did not have MPs in their tissues. Bivalves from offshore aquaculture was less impacted by MPs probably due to the hydrographic conditions and distance from the coast. Most of MPs ingested by bivalves were related to the plastic type used in aquaculture materials. Transformative solutions and/ or procedures to eliminate plastic from aquaculture equipment are needed, and depuration might be a practical solution.
- Understanding planktonic diatoms to inform site selection for shellfish offshore aquaculture systemsPublication . Araújo Freitas, Carla Alexandra; Goela, Priscila; Icely, John; Dias Duarte Fragoso, Bruno; de Oliveira Júnior, Luciano; Cristina, Sónia; Newton, AliceSustainable bivalve aquaculture offers a solution to rising food demand. This study aimed to help identify suitable offshore shellfish aquaculture sites in coastal upwelling regions. Here, planktonic diatom abundance, crucial for bivalve growth, is a key success factor. A successful bivalve production area was analysed to understand how diatom dynamics and upwelling influence a suitable location for shellfish offshore aquaculture. A diatom-based criterion for site selection is proposed. Surface water samples were collected over two years in southwest Iberia, near a major upwelling centre. Phytoplankton abundance and composition were assessed along with chlorophyll-a concentration and wind-stress upwelling indices. Episodes of high diatom concentrations were frequent and distributed throughout the year. Most diatom blooms were dominated by Pseudo-nitzschia, particularly the delicatissima group. Although this genus is potentially toxic, the levels of amnesic shellfish poisoning (ASP) toxin-the domoic acid (DA) in bivalves were mostly low or undetectable, even during periods of high Pseudo-nitzschia abundances. Conversely, the less abundant Pseudo-nitzschia seriata group presence often coincided with detectable DA in bivalves. These findings suggest that high Pseudo-nitzschia abundance does not hinder aquaculture and may even benefit it when the delicatissima group prevails in high numbers. Focusing on the Pseudo-nitzschia seriata group in predictive models may better predict DA levels for harvest closures, minimising economic losses and health risks. This is particularly true for locations where the seriata group is the one linked to DA production. Additionally, we identified oceanographic conditions coinciding with DA levels exceeding regulatory limit.