Aquaculture International最新文献

{"title":"Nonlinear effects in finfish aquaculture: A panel threshold analysis of stocking density and water temperature in Korea","authors":"Hoonseok Cho,&nbsp;Choelhyun Kim,&nbsp;Seonghyun Sim,&nbsp;Eunji Kim,&nbsp;Yonghan Jeon","doi":"10.1007/s10499-025-01971-4","DOIUrl":"10.1007/s10499-025-01971-4","url":null,"abstract":"<div><p>This study applies the fixed-effects threshold model (FETM) to examine nonlinear dynamics and threshold effects in Korean finfish aquaculture using panel data from 2010 to 2023. The analysis identifies a critical threshold in current biomass (log-transformed 13.9483, approximately 1,142,010 fish), beyond which the marginal productivity of stocking density declines due to resource competition, oxygen depletion, and metabolic stress. Among key production inputs, feed input exhibits the highest elasticity (0.4717), confirming its dominant role in production efficiency, whereas water temperature shows a significant negative elasticity (-1.3301), highlighting the adverse impact of rising water temperatures on fish growth and survival. Additionally, many finfish aquaculture regions in Korea face severe constraints due to overuse of water surface areas, leading to diminishing marginal returns and heightened ecological stress. These findings highlight the urgent need for comprehensive environmental assessments, real-time monitoring systems, and adaptive management strategies to enhance sustainable aquaculture practices. Particularly, optimizing stocking densities based on the identified current biomass threshold and implementing spatial planning policies can balance ecological sustainability and production efficiency. This study demonstrates the effectiveness of FETM in detecting nonlinear relationships and production thresholds in aquaculture systems, providing insights for evidence-based policymaking and sustainable resource management aligned with global sustainability goals.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development profile of digestive enzymes and intestinal nutrient transporters during the early ontogeny of Himalayan snow trout, Schizothorax richardsonii","authors":"Rini Joshi,&nbsp;Biju Sam Kamalam,&nbsp;Prakash Sharma,&nbsp;Mukul Arya,&nbsp;Nahida Rasheed,&nbsp;Bhawna Gehlot,&nbsp;Debajit Sarma,&nbsp;Bipin Chandra Pathak,&nbsp;Md. Shabhaz Akhtar,&nbsp;Pramod Kumar Pandey,&nbsp;Manchi Rajesh","doi":"10.1007/s10499-025-01964-3","DOIUrl":"10.1007/s10499-025-01964-3","url":null,"abstract":"<div><p>This study characterized the ontogenic profile of key digestive enzymes and intestinal nutrient transporters in <i>Schizothorax richardsonii</i> larvae from 0 to 21 days post-hatch (dph; at 21.5 ± 0.2 °C) using biochemical and molecular approaches. The larvae exhibited an exclusive lecithotrophic phase until 8 dph, followed by an endogenous-exogenous transition phase until 15 dph (fed <i>Artemia</i> nauplii and larval diet), and complete exogenous feeding with larval diet during 15–21 dph. Regarding larval growth, weight gain exhibited an exponential trend, while the gain in total length followed a linear trend, increasing by 478% and 114%, respectively. The specific activity of trypsin and leucine aminopeptidase showed an increase at 8 dph and fluctuated thereafter during exogenous feeding, whereas total proteases and chymotrypsin activity was found to be high from 12 to 21 dph. Similarly, the expression of carboxypeptidase and peptide transporter <i>pept1</i> showed a significant increase during 15–21 dph, as compared to 5–7 dph. Concerning lipid uptake, the mRNA levels of bile-activated lipase, hepatic lipase (<i>lipc</i>), and <i>mttp</i> showed an increasing trend during exogenous feeding, with peak expression at 21 dph. The amylase activity and the mRNA abundance of maltase (<i>mgam</i>), sodium-glucose cotransporter 1 (<i>sglt1</i>), and glucose transporter-2 (<i>glut2</i>) were found to increase significantly at 15–21 dph during exogenous feeding with formulated feed, as compared to the yolk absorption phase. Conversely, the abundance of apolipoprotein-b (<i>apob</i>) transcripts during the lecithotrophic phase indicates their potential role in utilizing yolk nutrients. The alkaline phosphatase activity showed a significant increase from 15 dph and peaked at 21 dph, indicating gut maturation and its role in aiding alkaline digestion. Overall, the development profile of digestive enzymes and intestinal nutrient transporters clearly indicates dietary stimulation and regulation, which is relevant for weaning and hatchery management of this agastric teleost.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of histological stains in aquaculture and fisheries development technology","authors":"El-Sayed Hemdan Eissa,&nbsp;Alkhateib Y. Gaafar,&nbsp;Roshmon Thomas Mathew,&nbsp;Eman A. Al-Shahari,&nbsp;Ekemini Moses Okon,&nbsp;Moaheda E. H. Eissa,&nbsp;Yasmin M. Abd El-Aziz","doi":"10.1007/s10499-025-01932-x","DOIUrl":"10.1007/s10499-025-01932-x","url":null,"abstract":"<div><p>Improper husbandry techniques, environmental pollution, fluctuating weather conditions, and shifting market dynamics pose significant challenges to aquaculture and fisheries production, making fish more susceptible to diseases. Understanding and characterizing the interventions involved in disease outbreaks are crucial, as they can lead to significant financial losses in the aquaculture and fisheries sectors. Histopathology plays a vital role in fish disease diagnosis, as it involves the microscopic examination of tissue abnormalities. This study aimed to evaluate the tissue preparation procedures for aquatic organisms and provide a historical review of tissue staining techniques. Over time, histopathological staining methods have advanced, leading to the development of simpler, more precise, and more efficient techniques. While newer genetic, non-culture, immunostaining, and other advanced staining methods have largely replaced traditional staining procedures, several older techniques remain in use. To enhance their effectiveness, modern histological stains are being modified and combined with other staining methods. Additionally, emerging fields like proteomics can complement traditional approaches, such as pathogen identification and histological examination, to achieve more accurate disease diagnoses in aquaculture and fisheries.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interactive effects of temperature and dietary protein to energy ratios on the growth and physiology of marron (Cherax cainii, Austin & Ryan 2002)","authors":"Anthony J. Cole,&nbsp;Smita S. Tulsankar,&nbsp;Joel Wynhorst,&nbsp;Ravi Fotedar","doi":"10.1007/s10499-025-01961-6","DOIUrl":"10.1007/s10499-025-01961-6","url":null,"abstract":"<div><p>Determining the optimum dietary protein to energy (P:E) ratios in aquaculture species is vital to allow for protein-sparing and faster growth rates, which are highly influenced by temperature, while avoiding the adverse physiological problems associated with high dietary lipids or poor nutrition. A laboratory feeding trial was conducted to investigate the effects of three diets of varied P:E ratios and two different temperatures (18 °C, 22 °C) on the growth, condition, survival and physiology of marron (<i>Cherax cainii</i> Austin and Ryan, 2002). The marron were fed three isonitrogenous diets: LL — Low lipid (6%), ML — moderate lipid (10%) and HL — high lipid (14%), with P:E ratios of 19.1, 17.4 and 16.2 g MJ⁻¹ respectively for 120 days. At the end of the feeding trial, growth of marron increased at 22 °C in all dietary treatments. Marron cultured at 18 °C with LL had a lower Total Haemocyte Count, and there was no effect of temperature or diet on the organosomatic indices, condition or survival rate. Total meat yield was higher at 18 °C than at 22 °C overall. HL at 18 °C resulted in lower growth, lower orbital carapace length increase and a high feed conversion ratio, though there was no effect of dietary lipid content on growth at 22 °C. The temperature had an overarching effect on marron growth, and had a greater influence on marron fed a high lipid diet, where there was a greater difference in weight gain of marron between temperatures with the high lipid diet. The present study concludes that a diet with a P:E ratio of 17.4–19.1 g MJ⁻¹, a lipid level of 6–10% and an energy content of 15–16 MJ kg⁻¹ was optimal for marron under the tested experimental conditions.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10499-025-01961-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Aquaculture mathematical modelling review","authors":"Evgeny Ivashko,&nbsp;Elena Konovalchikova,&nbsp;Valentina Ivashko","doi":"10.1007/s10499-025-01928-7","DOIUrl":"10.1007/s10499-025-01928-7","url":null,"abstract":"<div><p>World aquaculture has demonstrated stable growth in production volumes for the last three decades. The competitiveness of the aquaculture market is growing steadily and the amount of data that fish-farmers have to manage is rapidly increasing. Mathematical modeling is the key factor in improving the fish farming industry and switching from experience-based to knowledge-based precision aquaculture. In this context, mathematical models are crucial tools for sustainable development. This paper presents a review of the literature on mathematical modeling in aquaculture. Using the scientific web search engine Google Scholar, we discovered 154 characteristic research papers considering mathematical models. We perform manual summarizing and classification of the papers by aquaculture problem, scale of the models, and methods used, and develop a classification. In total, we discovered mathematical models related to twenty different aquaculture problems and four scales, from cage/pool-wide to region-wide. We also describe the mathematical methods most commonly used and demonstrate examples of which specific mathematical methods are applied to solve aquaculture problems.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Insights into the utilization of Ulva prolifera hydrolysate to enhance substance production of Isochrysis galbana: a win–win strategy","authors":"Qing Liu,&nbsp;Shuo Liu,&nbsp;Fan Liu,&nbsp;Cuili Jin,&nbsp;Xiaojian Zhou","doi":"10.1007/s10499-025-01969-y","DOIUrl":"10.1007/s10499-025-01969-y","url":null,"abstract":"<div><p>Isochrysis galbana is considered a promising feed for aquaculture, but high cultivation cost well as low substance yield and quality limit its application prospects. This study explored the feasibility and regulating mechanism of green tide waste Ulva prolifera for <i>I. galbana</i> substance production. U. prolifera hydrolysate (UPH) was prepared as an alternative substrate from 5 to 50% concentrations to culture <i>I. galbana</i>. Compared to the control f/2 medium, the biomass production of I. galbana added with 40% UPH reached 318.75 mg/L, which was the most effective up to 1.24-fold increase. Meanwhile, the highest pigments, lipid, protein and carbohydrate productions were observed in the 40% UPH substrate, which were around 1.17 to 1.70 times higher than that of the control, respectively. The above parameters were the lowest with the addition of 5% UPH, except for the lipid content, which was slightly higher than control. The photosynthetic activity showed that 5% UPH blocked four electron transfer sites of <i>I. galbana</i>, including from Quinone A (Q_A) to Q_B, from plastoquinone (PQ) to photosystem I (PSI), the oxygen evolving complex (OEC) activity on the donor side and the acceptor pool on the PSI. However, 40% UPH enhanced the electron transfer beyond Q_A, from PQ to PSI and the acceptor pool of PSI. The photosynthetic parameters φPo, φE_O, PI_CS and PI_ABS, which had strong correlation with the biomass and substance accumulation of <i>I. galbana</i>, were found to be enhanced by 40% UPH. Changes in electron transfer regulated the photosynthetic activity and metabolism of <i>I. galbana</i>. Encouragingly, the production cost of cultivating <i>I. galbana</i> with UPH prepared from green tide waste was almost negligible compared with the f/2 medium (US$ 15.6). Therefore, the study provides a win–win strategy for obtaining cost-effective energy production as well as the resource utilization of green tide waste.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DeepSeek-Based Multi-dimensional Augmentation of Short and Highly Domain-Specific Textual Inquires for Aquaculture Question-Answering Framework","authors":"Liming Shao,&nbsp;Hong Yu,&nbsp;Wei Huang,&nbsp;Huiyuan Zhao,&nbsp;Lixin Zhang,&nbsp;Jing Song","doi":"10.1007/s10499-025-01948-3","DOIUrl":"10.1007/s10499-025-01948-3","url":null,"abstract":"<div><p>High-quality data are essential for accurate and timely decision-making in disease prevention and control within aquaculture question-answering (QA) framework. However, textual data reflecting conversational question–answer exchange between fishery farmers and domain experts remain scarce, hindering the progress in training and building such systems. To address this gap, we introduce a multi-dimensionalaugmentationapproach leveraging DeepSeek to generate high-quality augmented data tailored to aquaculture, concentrating on the questions side. Our method aims to provide high quality synthesized data to better train aquaculture question-answering frameworks to gain comprehensive understanding of key information from short, free-form and conversational inquiries and deduct the intention of the questions. We employ a multi-task BERT framework to assess the reliability and diversity of these augmented samples, ensuring they preserve core semantics while expanding domain-specific data availability. We benchmark our approach against ChatGPT o1 and our experimental results demonstrate that DeepSeek achieves better performance. Specifically, for domain specific key information (aka entity) recognition, it attains an accuracy of 92.08%, precision of 92.3%, recall of 92.05%, and an F1 score of 91.78%; for intent classification, the model reaches 91.67% accuracy, 93.48% precision, 91.67% recall, and 89.68% F1 score. Notably, DeepSeek surpasses ChatGPT o1 in intent classification and remains competitive in key entity recognition. Furthermore, the augmented samples exhibit robust domain reliability (Cosine similarity &lt; 0.474619) and high diversity (Distinct- 1 = 0.9776; Self-BLUE = 0.0106). These results demonstrate the efficacy of DeepSeek-based multi-dimensional text augmentation in improving data consistency and coverage for aquaculture professionals engaged in disease management. Our method places a particular emphasis on enhancing the quality and comprehensiveness of user questions, thereby laying a stronger foundation for subsequent answer generation and overall knowledge improvement in QA framework.\u0000</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of stocking density on growth, behavior, digestion, and gut health of the sea cucumber Apostichopus japonicus: new insights into land-based aquaculture","authors":"Ruihuan Tian,&nbsp;Guo Wu,&nbsp;Huiyan Wang,&nbsp;Xiyuan Huang,&nbsp;Qiuzhen Song,&nbsp;Yunjie Yang,&nbsp;Tongdan Zhang,&nbsp;Yaqing Chang,&nbsp;Chong Zhao","doi":"10.1007/s10499-025-01962-5","DOIUrl":"10.1007/s10499-025-01962-5","url":null,"abstract":"<div><p>The increasing demand stimulates the rapid development of sea cucumber aquaculture industry in China. High stocking density is commonly used in the land-based aquaculture, but greatly affects the growth rate of sea cucumbers. In the present study, two different stocking densities were set to investigate the effects on growth, fitness-related behaviors, digestion, and gut health of the sea cucumber <i>Apostichopus japonicus</i>. We found that the terminal wet weight and weight gain rate significantly reduced in sea cucumbers at high stocking density. Feeding behavior significantly decreased in those at high stocking density, while crawling behavior was not affected. Protease activity was significantly inhibited in sea cucumbers at high stocking density. This may be an important reason for the reduced feeding behavior. Intestinal morphology showed that intestinal diameter, folds height, and enterocyte height significantly reduced in sea cucumbers at high stocking density. Degenerated intestinal structure is closely related to inhibited protease activity. Furthermore, the abundance of Proteobacteria increased, but the abundance of Bacteroidetes reduced in the gut of sea cucumbers at high stocking density. This result suggests that gut health was affected in sea cucumbers at high stocking density. In conclusion, reduced feeding behavior, degradation of intestinal structure, and changed intestinal microbial composition are important reasons affecting the growth of sea cucumbers. This finding provides valuable information for the high-density land-based aquaculture of <i>A</i>. <i>japonicus</i>. </p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TDA-GLM: text data augmentation for aquaculture disease prevention and control via a small model-guided ChatGLM","authors":"Shihan Qiao,&nbsp;Hong Yu,&nbsp;Jing Song,&nbsp;Lixin Zhang,&nbsp;Huiyuan Zhao,&nbsp;Wei Huang","doi":"10.1007/s10499-025-01945-6","DOIUrl":"10.1007/s10499-025-01945-6","url":null,"abstract":"<div><p>Disease prevention and control is crucial for the healthy development of the aquaculture industry, and high-quality data are the foundation for intelligent disease management. However, textual data in this field are scarce and variable in quality. The direct use of large language models (LLMs) for data augmentation often results in poor-quality outputs. In this paper, we propose a small-sample data augmentation framework called TDA-GLM. This framework employs a strategy that combines a high-quality corpus, pretrained large model, and efficient prompts, which improves data augmentation by integrating high-quality corpora and refining prompt techniques. To address the poor adaptability of LLMs in aquaculture disease prevention and control, which leads to low-quality data augmentation, we introduce a supervised learning model. This model guides the understanding of domain knowledge and optimizes data augmentation tasks within the LLM, enabling the generation of data that are both highly similar to the original professional material and rich in content. Additionally, we design a noise removal module that filters out noise by analyzing the consistency between the augmented data and the data augmentation target, thereby increasing the overall quality of the augmented data. To verify the domain reliability of our data augmentation approach, we conducted a few-shot learning classification task experiment. The results demonstrated significant improvements by our model over existing advanced text data augmentation techniques, with the key performance indicators Acc, P, R, and F1 reaching 94.86%, 95.55%, 94.86%, and 94.62%, respectively. Furthermore, in the experiments assessing the quality of the augmented samples, the similarity and enrichment degrees reached 94.95% and 64.41%, respectively. These results indicate that our augmented samples are of very high quality, ensuring that the core semantics of the original data are preserved while increasing data diversity through appropriate variations.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid enhanced optimization architecture-based model for long-term water temperature prediction in aquaculture","authors":"Tonglai Liu,&nbsp;Min He,&nbsp;Zhuhong Che,&nbsp;Shuangyin Liu,&nbsp;Longqin Xu","doi":"10.1007/s10499-025-01958-1","DOIUrl":"10.1007/s10499-025-01958-1","url":null,"abstract":"<div><p>Addressing issues such as inadequate prediction accuracy, significant noise interference, and difficulties in capturing long-term dependencies in aquaculture environment water temperature (WT) forecasting, this paper proposes a long-term prediction model based on a hybrid enhanced optimization architecture, namely the HEOA-BiTCN-MLSTM model. This model utilizes the human evolutionary optimization algorithm (HEOA) to optimize model parameters, thereby improving prediction accuracy. It employs a bidirectional temporal convolutional network (BiTCN) to deeply extract latent features from data, enhance noise resistance, and capture long-term trends and complex nonlinear variations in WT data. Finally, it integrates a multi-head long short-term memory (MLSTM) network, which combines the long short-term memory (LSTM) network with the multi-head self-attention mechanism (MHSA), to improve the model’s ability to capture long-term dependencies and model global information when processing long sequences. This model significantly improves WT prediction performance through the synergistic effects of optimization, hybridization, and enhancement while effectively addressing noise interference and data irregularity in complex environments. Experimental results demonstrate that this model significantly outperforms traditional benchmark models such as the gated recurrent unit (GRU), backpropagation neural network (BPNN), and recurrent neural network (RNN) in long-term WT prediction. Specifically, when accurately predicting WT 4 h ahead, the model achieves <i>R</i>², MSE, MAE, and wMAPE values of 0.912, 0.352, 0.191, and 1.390%, respectively. This research provides robust support for intelligent monitoring and regulation in aquaculture environments.</p></div>","PeriodicalId":8122,"journal":{"name":"Aquaculture International","volume":"33 4","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}