Type: Peer-review
Technological innovations are driving precision aquaculture towards a future of transparent, automated, and sustainably efficient production
1. Department of Fisheries and Aquaculture, Faculty of Agriculture, University of Ankara, 06110 Ankara, Turkey
2. Department of Aquaculture and Animal Production, College of Agriculture and food Sciences, King Faisal University, Al Hofuf, Kingdom of Saudi Arabia
3. Fish and Animal Production Department, Faculty of Agriculture (Saba Basha), Alexandria University, Alexandria, 21531, Egypt
Abstract: Precision aquaculture (PA) is a major change in the fish farming industry because it incorporates Internet of Things (IoT), artificial intelligence (AI), automated technologies, and real-time solutions to efficiently monitor intensive production and minimize adverse effects in a timely manner. This review presents the current state of PA technologies, their uses, advantages, challenges, and future perspectives based on recent research. Water-quality monitoring using IoT sensor networks, fish-behavior analysis using computer-vision systems, automated feeding systems, and AI-based decision-support systems are the main technological elements of PA. Recent research shows that PA offers considerable improvements in terms of feed efficiency (30% savings), fish survival (33% higher), predictive accuracy (R2 = 0.94), and revenue increases (up to 15.51% in field trials). It also helps reduce labor costs and energy consumption. The return on investment ranges from 1–3 years depending on farm scale (with shorter periods for large-scale farms) and system complexity. However, some challenges remain, including sensor reliability, data standardization, high initial costs, and system integration. Future trends of PA point toward blockchain, digital twins, multimodal sensor fusion, autonomous robotics, explainable AI systems, and energy-harvesting systems, which will further revolutionize aquaculture operations. This revolution will drive the shift from aquaculture 4.0 (technology-driven approach) to aquaculture 5.0 (ecological sustainability and system robustness), and make aquaculture more transparent, automated, and sustainable.
Keywords: Precision aquaculture, aquaculture 5, aquaculture revolution, Internet of Things, multimodal sensor, artificial intelligence, sustainable production
Article Info.
Submitted: 11-30-2025; Revised: 01-12-2025; Accepted: 01-14-2026; Online: 01-15-2026
Cite as: Yavuzcan, H., Mansour, A. T. (2026). Technological innovations are driving precision aquaculture towards a future of transparent, automated, and sustainably efficient production. Animal Reports, 2(1): 16-34. https://doi.org/10.64636/ar.37
As global demand for seafood continues to rise, traditional fishing stocks are declining, threatening the sustainability of fisheries (Mansour et al., 2022). Accordingly, the aquaculture industry has become increasingly important for providing sufficient aquatic products at high quality and quantity (Norman et al., 2019). Currently, aquaculture production accounts for over 50% of global fish production (Roy et al., 2024). However, conventional aquaculture practices often suffer from inefficient feeding, water quality management, and disease prevention, leading to economic losses and environmental impacts (Costa-Pierce, 2022). At the same time, precision aquaculture (PA; smart aquaculture) appears as a transformative approach to fish farming that uses advanced technologies to monitor, control, and optimize aquaculture operations (D'Agaro, 2025). This could allow farmers to have the ability to monitor, control, and document biological processes in their farms (Komarudin et al., 2021).
The shift from traditional to precision-based aquaculture is a pivotal evolution toward using data as a basis for decision-making. Conventional aquaculture is predominantly based on manual observation and experience-based management, which are subjective, require substantial labor input, and are prone to high error rates (Costa-Pierce, 2022). PA, by contrast, uses combined networks of sensors, control systems, and AI to deliver constant surveillance and predictive analytics along with autonomous control (Ariyandi et al., 2025). PA possesses numerous advantages that can be used to boost production efficiency, including feed savings (Huang et al., 2025; Karimanzira, 2025), maintenance of optimal water quality (Maharmi et al., 2025), greater labor efficiency (Ragab et al., 2025), and more effective disease prediction (Yasruddin et al., 2025).
Also, PA is now not only an issue of operational efficiency but also a part and parcel of more general sustainability aims (Vettom et al., 2024). Having a beneficial impact on sustainable development goals and responsible food production, PA helps to optimize feed consumption, minimize waste, enhance fish welfare, and reduce the adverse effects on the environment (Roy et al., 2024; Lu & Kong, 2025). Emerging technological solutions in the internet of things, machine-learning algorithms and cloud computing have allowed PA systems to be more affordable and accessible to farmers of all sizes (Ariyandi et al., 2025; Maharmi et al., 2025). Though this has seen a lot of technological innovation, there is indeed a gross scarcity of integrated systems that can make real-time autonomous decisions that balance economic production efficiency and ecological sustainability in variable farm conditions. As such, the purpose of the review is to generate a general summary of the PA technologies, comprising the key parts, present applications, advantages, the current problems, and prospective opportunities. The scope also includes different aquaculture infrastructures, such as pond-based systems, recirculating aquaculture systems (RAS), and marine cage farming, with special emphasis on technological innovations.
2 Common technologies in precision aquaculture
2.1 Monitoring and sensing systems
Water-quality monitoring is a key element of PA systems; appropriate water quality supports optimal production, and early detection of changes in macro- and microaquatic environments allows precautionary measures to be taken (Verma et al., 2022; Maharmi et al., 2025). Modern IoT offers a system of sensors that monitor vital parameters, such as dissolved oxygen (DO), pH, temperature, turbidity, salinity and ammonia concentration (Mandal & Ghosh, 2024; Maharmi et al., 2025). Recent developments in sensor technology have improved accuracy and reduced costs. In a detailed work, D'Agaro (2025) revealed that with the adequate calibration of low-cost IoT sensors using professional probes, it was possible to obtain a high precision of 76-97% of the results obtained with the professional sensors to measure water quality. Beyond water quality, smart sensors can also monitor macroenvironmental conditions, including weather, water velocity, and ecosystem parameters (Narayana et al., 2024). The multiplicity of environmental variables measured within integrated sensor platforms makes the data all-encompassing and is helpful when it comes to making decisions (Chen et al., 2022). Average error: 1.25–1.65%. Multi-node sensor systems have been applied successfully in commercial shrimp ponds with a mean error of about 1.25-1.65% in field tests of pH and salinity (Islam, 2025).
Moreover, computer-vision, acoustic, and sensor technologies have improved the process of fish behavior monitoring (Chai et al., 2023; Wei et al., 2025). Stereocameras and RGB imaging systems with deep learning algorithms like Mask R-CNN and semantic segmentation also make it possible to conduct automated fish counting, biomass estimation, and behavior analysis (Wibowo et al., 2025). Sonar in two-mode and two-mode stereo-vision have been adopted to process the metrics of fish by AI cloud computing, availing precise results of the fish population and health condition (Roy et al., 2024).
Automated feeding systems are considered to be one of the most influential implementations of PA technology (Cassy & Bekaroo, 2024; Maharmi et al., 2025). These systems are based on the use of different methods such as time-based scheduling, demand-based feeding based on fish behavior, and AI-based optimization algorithms (John & Mahalingam, 2021; Silalahi et al., 2023; Dorgham et al., 2025). Recent studies have shown that feed efficiency could be greatly improved with automated systems based on fish behavior, while total feed waste could be reduced by 28% (Karimanzira, 2025). Lu and Kong (2025) designed a system with 92.3% dynamic fish recognition accuracy and feeding error of less than 10.67% in field experiments. This system incorporates computer vision for fish detection, behavioural analysis for hunger evaluation, and precision feeding mechanisms for feed delivery.
Moreover, automated water-quality management also includes systems for aeration, filtration, temperature, and chemical dosing. Fuzzy logic controllers have been effective in regulating the dissolved oxygen and salinity to be within optimal ranges. In one study, a fuzzy-logic-based IoT system was reported to have an accuracy of 98 percent while maintaining water-quality parameters within target ranges during 72 h of testing (Maharmi et al., 2025). Automated aeration systems showed particularly notable outcomes; in one study, shrimp survival was 33.3% higher than under traditional farming (Ariyandi et al., 2025).
Disease-detection and treatment systems are another application and use many technologies such as image analysis, water chemistry, and behavioral pattern recognition (Li et al., 2022; Islam et al., 2024). Early warning mechanisms are able to detect disease outbreaks before clinical manifestations are seen, making it possible to intervene quickly and minimize mortality rates (Yasruddin et al., 2025). Robotic treatment machines can provide accurate doses of drugs or therapeutic agents based on real-time health evaluations (Shao, 2001; Islam et al., 2024).
Machine-learning algorithms form the basis of any modern PA system and enable predictive analytics, pattern recognition, and autonomous decision-making. Deep-learning models have demonstrated outstanding performance in their different applications with some achieving R² = 0.94 when predicting fish growth in California bass farms (Dhamdhere et al., 2025). The models combine various data such as environmental parameters, feeding history, and fish behaviour patterns to come up with reliable predictions.
Moreover, convolutional neural networks and recurrent neural networks are usually utilized in the analysis of images and time-series prediction, respectively (Dhruv & Naskar, 2020). Vision-language models have been trained to monitor the entire feeding process of fish and have achieved an F1 score of 0.95 in recognizing behaviors in tilapia ponds (Karimanzira, 2025). Such sophisticated AI systems can recognize intricate behavioral patterns and trigger feeding in real time based on fish activity.
In addition, decision-support systems that combine AI analytics with easy-to-use interfaces provide the farmers with practicable insights and suggestions (Dhinakaran et al., 2023). Such systems are capable of handling large volumes of sensor data, determining trends or anomalies, and recommending the best management actions. By alerting operators in real time to critical conditions that demand urgent attention, these systems enable rapid responses to potential issues (Panudju et al., 2023).
Digital-twin technology is a recent development in aquaculture analytics that creates digital simulations of real farm systems for optimization and scenario testing. These computerized models allow farmers to test various management solutions and forecast the results before they make any changes in real operations (Chen et al., 2025).
Remote access to farm data from any location with internet connectivity is made possible by cloud-based monitoring platforms. Such platforms usually offer real-time dashboards, historical data analysis, mobile applications for field use, and external system integration. The most commonly used platforms are ThingSpeak, Firebase, and custom cloud solutions that are specifically developed to implement aquaculture applications (Choudhury et al., 2025). Smartphone applications are also indispensable tools in current aquaculture management, as they offer farmers a real-time overview of the system status, notifications, and control options (Dhenuvakonda & Sharma, 2020; Bujas et al., 2023). Advanced apps include features such as augmented reality, voice commands, and predictive analytics to improve user experience and application performance (Ubina & Cheng, 2022). In shrimp farming, the use of a monitoring mobile application improved user knowledge by up to 20-37% (Anand & Otta, 2022).
Moreover, wireless sensor networks use communication protocols suited to aquaculture settings to enable remote measurements and alert farm managers (Shareef & Reddy, 2018). LoRa (Long Range) technology is popular because of its low power consumption and wide range. It also supports accurate measurements and consistent, reliable data transmission, making it suitable for large pond systems and remote areas (Cai et al., 2021). The use of Wi-Fi networks offers high data transmission speeds to support applications that need real-time processing of low-volume sensor data, audio, images, and video streams, other high-volume files, and intensive data processing (de Freitas et al., 2024).
3 Applications and Case Studies
3.1 Marine Cage Farming Applications
Marine cage farming has benefited significantly from PA technologies, particularly in areas of environmental monitoring, feed monitoring, potential predator activity, and fish health management (Fig. 1) (Chang et al., 2021). Offshore cage operations face unique challenges including variable ocean conditions, limited accessibility, and harsh environmental conditions that challenge traditional monitoring methods (Coutinho & Boukerche, 2022). Recent implementations of PA have demonstrated successful deployment of autonomous monitoring systems in marine environments. Sensor buoys equipped with multi-parameter probes provide continuous monitoring of water quality, current patterns, and weather conditions. These systems utilize satellite communication for data transmission and solar power for extended autonomous operation (Williams et al., 2025).
In Taiwan, AI- and IoT-integrated management of tilapia cage culture decreased feed residues by 10%, increased fish survival by 10%, reduced human labor demand by 30%, and improved growth and FCR; profitability thereby increased by 138% in small cages and 40% in large cages. An AI image-analysis module estimated fish body length and weight with 90% accuracy and mobility monitoring enhanced early disease detection (Chang et al., 2021).
Furthermore, a marine fish cage was equipped with a smartphone-based remote feeding system as part of the AI and IoT system. This system enhanced feeding-control efficiency and monitoring accuracy and reduced labor cost, feed waste, and fish stress (Imai et al., 2019).
Fig. 1. System components of integrated AI and IoT in fish cage culture. [Adapted from (Chang et al., 2021)].
3.2 Land-based Recirculating Aquaculture Systems (RAS)
Recirculating aquaculture systems represent an ideal application for PA technologies due to their controlled conditions and integrated infrastructure. RAS operations require precise management of water quality, flow rates, filtration systems, and environmental conditions to maintain optimal growing conditions (Lindholm‐Lehto, 2023). RAS facilities have advanced sensor networks to measure a combination of multiple parameters in real-time, such as dissolved oxygen, pH, temperature, ammonia, nitrites, and turbidity at different points of the system (Verma & Gupta, 2022). Real-time data analysis allows immediate detection of system problems or deterioration in water quality, preventing possible fish losses (Shi et al., 2018).
A recent study by Singh et al. (2023) deployed an intelligent IoT-based RAS comprising smart water-quality sensors, cloud data analytics, real-time alerts, and automatic control of aeration and water-exchange systems. This system increased the stability of the water quality by 40-60%, fish survival, growth by 10-25%, and energy saving by 15-25.
3.3 Pond Aquaculture Optimization
Conventional pond aquaculture has been transformed by the adoption of precision technologies, especially in water-quality management and feeding optimization. Pond systems are characterized by distinctive challenges because they are open, have a changing environment, and interact with various ecosystems (D'Agaro, 2025). Continuous surveillance of water quality parameters such as salinity, pH and temperature was carried out in a shrimp farm using a multi-node sensor network. The measurements showed a 98:100% accuracy and yielded high-quality shrimp crops (Komarudin et al., 2021).
Multi-node sensor networks that are deployed in pond systems enable comprehensive monitoring of spatial and temporal changes in water quality. Such networks are able to identify local issues like algae blooms, zones of oxygen shortages or temperature layers that can otherwise be invisible with single-point monitoring (Islam, 2025). In addition, automated aeration systems with real-time oxygen monitoring have shown high survival and growth rates of fish. The overall analysis of the shrimp pond activities revealed that the survival rates were enhanced by 33.3 percent with automated aeration in contrast to manual management (Ariyandi et al., 2025).
Demand-fed pond systems are also precision-feeding systems that use several technologies such as demand feeders which are activated by fish movement, scheduled feeding based on a growth model, and adaptive systems which vary feeding rates depending on prevailing environmental conditions. The feeding management systems based on vision have shown impressive outcomes, and one of the studies led to a 28% reduction in feed waste, while ensuring that the fish growth rate was optimal (Karimanzira, 2025). Commercial trials of smart systems in pond culture have shown a decrease of feed cost by 15-30%, reduced mortality by 20%, and precise determination of growth of more than 90% prediction accuracy (R2 = 0.94). These conditions led to proven 22% efficiency of production and 15% cost of operation (Dhamdhere et al., 2025). Mobile autonomous feeding systems were used in a catfish farm in the southern part of the United States with behavioral monitoring. The system was able to recognize fish with an accuracy of 92.3% and minimized feeding errors to less than 10.67%. The total productivity increased by 19 percent and labor needs decreased by 40 percent (Lu & Kong, 2025).
4 Benefits and Advantages of precision aquaculture
Smart aquaculture is a set of modern technologies that enable traditional fish farming to become data driven and precision managed (Huang et al., 2025; Ragab et al., 2025). Studies report substantial changes across production indicators: feed costs are reduced by 15-30 percent, survival rates increase up to 90 percent, labor costs are reduced, and revenue is also increased by 15-20 percent. Moreover, PA improves fish welfare (Komarudin et al., 2021; Nagothu et al., 2025), farming sustainability (Ramanathan et al., 2023; Vettom et al., 2024; Vignesh et al., 2024), return on investment (Ragab et al., 2025) and can reduce energy use (Komarudin et al., 2021; Nayoun et al., 2024; D'Agaro, 2025; Nagothu et al., 2025).
4.1 Enhancing the efficiency of production.
Modern technologies are also applied in the use of PA (Table 1), including cameras for tracking fish behavior, AI/ML appetite-prediction models, and automated feeders with feedback loops (Imai et al., 2019). These technologies can optimize FCR, minimize waste, enhance growth rates and decrease operational costs due to the accuracy in feed delivery (Huang et al., 2025). Furthermore, it enables precise harvest timing, enhances product quality, optimizes production cycles, improves market size consistency, and maximizes revenue per batch (Imai et al., 2019; Kannan et al., 2024; Nayoun et al., 2024).
Table 1. Production efficiency utilizing precision aquaculture as driven by modern technologies.
|
Benefits |
Quantitative Improvements |
Technologies Used |
References |
|
Automated feeding based on real-time appetite detection and biomass estimation. |
Feed cost reduction: 15-30%. Biomass estimation accuracy: >90%. Reduced feed waste and overfeeding |
Camera-based fish behavior analytics. AI/ML appetite prediction models. Automated feeders with feedback loops. Cloud-based decision support systems |
(Imai et al., 2019; Huang et al., 2025; Karimanzira, 2025; Lu & Kong, 2025) |
|
Non-invasive, continuous monitoring of individual fish and population growth rates. |
Biomass estimation accuracy: >90%. Real-time growth tracking. Improved harvest planning precision |
Computer vision and image processing. Machine learning growth
models 3D imaging systems. Predictive analytics |
|
|
Increased production per unit area and improved product quality through optimal growing conditions. |
Production increase: 88.72 kg/ha (field trial). Revenue increase: 15.51%. Improved survival rates: 33-90% Better product consistency and quality. |
Integrated IoT/AI systems. Precision environmental control. Optimized feeding protocols. Real-time monitoring. Traceability systems |
(Chahid et al., 2021; Kassem et al., 2021; Kannan et al., 2024) |
Table 2 illustrates the benefits of smart aquaculture in maintaining optimal growing conditions, reducing stress, and mortality, preventing disease outbreaks, and enabling higher stocking densities (Nagothu et al., 2025). Early disease detection using computer-vision systems, multimodal sensors, AI/ML anomaly detection, and camera-based lesion detection helps prevent disease spread, reduce losses, improve overall stock health, and minimize medication costs (Costa-Pierce, 2022; Wu et al., 2023; Yasruddin et al., 2025). In addition, maintaining consistent enables remote management, and supports sustainable operations (Gokulnath et al., 2024).
Smart technologies enhance early warning systems, predictive analytics, and automated responses to adverse conditions, which enable faster problem detection and response and reduce catastrophic losses (Watson et al., 2018; Tzu et al., 2024; Dhamdhere et al., 2025).
Table 2. Fish welfare of aquaculture responses to utilizing precision aquaculture as driven by modern technologies.
|
4.3 Enhancing economic efficiency
The implementation of PA technology increases the revenue of fish farming projects (Wu et al., 2023; Ragab et al., 2025). The use of IoT monitoring dashboards, mobile apps for remote control, automated feeding systems, cloud-based management platforms, decision support systems, and alert and notification systems resulted in several advantages (Kassem et al., 2021; Kimothi et al., 2023). These systems reduce labor costs, operational costs, and environmental impacts; improve sustainability metrics; and enhance profitability. PA also enables evidence-based management, reduces guesswork, improves long-term planning, and improves work-life balance (Ramanathan et al., 2023; Srikanth et al., 2024; Vignesh et al., 2024).
In addition, the return on investment (ROI) of PA differs by farm scale, whereas in small-scale farms (<5 hectares), it averages 2–3 years; however, this period is reduced from 0.5 to 1.5 year in the large-scale farms (>50 hectares) (Griffin, 2018; Kantal et al., 2025; Ragab et al., 2025).
Table 3. Economic efficiency of aquaculture responses to utilizing precision aquaculture as driven by modern technologies.
|
Benefits |
Quantitative Improvements |
Technologies Used |
References |
|
Remote monitoring, automated feeding and control, reduced manual labor requirements. |
Labor cost savings: 1,768.62 yuan/ha (field trial). Production increase: 88.72 kg/ha. Revenue improvement: 15.51%. Reduced need for on-site personnel. |
IoT monitoring dashboards. Mobile apps for remote control. Automated feeding systems. Cloud-based management platforms. Alert and notification systems |
(Kassem et al., 2021; Kantal et al., 2025; Ragab et al., 2025) |
|
Real-time data collection, analysis, and predictive analytics for informed management decisions. |
Improved decision accuracy. Faster response to problems. Predictive maintenance
capabilities |
Cloud computing
platforms Machine learning models. Digital twins. Decision support systems. Data visualization dashboards |
(Kimothi et al., 2023; Ramanathan et al., 2023; Wu et al., 2023; Jais et al., 2024) |
|
Efficient use of water, feed, energy, and other inputs through precision management. |
Feed waste reduction: 15-30%. Water consumption reduction (ZWD systems). Energy efficiency improvements. Reduced chemical inputs. |
IoT sensor networks. AI optimization algorithms. Biofloc technology integration. Aquaponics coupling. Renewable energy systems. |
(Ramanathan et al., 2023; Srikanth et al., 2024; Vignesh et al., 2024) |
Table 4. The return on investment (ROI) of precision aquaculture by farm scale (Griffin, 2018; Kantal et al., 2025; Ragab et al., 2025).
|
Farm scale |
Primary benefits |
ROI Timeline |
|
Small-scale (<5 hectare) |
Labor reduction, feed optimization, remote monitoring |
2-3 years |
|
Medium-scale (5-50 hectare) |
All benefits; significant cost savings and yield improvements |
1-2 years |
|
Large-scale (>50 hectare) |
Maximum efficiency gains, data-driven optimization, scalability |
6-18 months |
4.4 Improving sustainable aquaculture production
Precision aquaculture reduces the environmental footprint through efficient resource use and waste management by zero-discharge systems, biofloc technology, and nutrient recycling systems (Vettom et al., 2024; Vignesh et al., 2024). These technologies protect investments, reduce financial risk, improve business stability, and enable better risk assessment. They also provide full monitoring of production parameters from egg to market through blockchain and cloud-based record keeping, which increases consumer confidence and supports quality certification. This facilitates premium pricing and certification, enhances market access, and builds consumer trust (Dong et al., 2022; Wu et al., 2025).
Table 5. Sustainable production of aquaculture responses to utilizing precision driven by modern technologies.
|
Benefits |
Quantitative Improvements |
Technologies Used |
References |
|
Reduced environmental footprint through efficient resource use and waste management. |
Nutrient load reduction: 15-30% (via feed optimization). Zero-water-discharge capability. Reduced greenhouse gas emissions. Waste recycling efficiency improvements. |
Zero-discharge systems. Biofloc technology. Nutrient recycling systems. GIS/GPS resource mapping. Environmental monitoring sensors. |
(Ramanathan et al., 2023; Vettom et al., 2024; Vignesh et al., 2024) |
|
Complete tracking of production parameters from egg to market. |
Full lifecycle documentation. Quality certification support. Consumer confidence enhancement. Market access improvement. |
RFID tagging systems. Blockchain integration. Cloud-based record keeping. IoT sensor data logging. Digital traceability platforms. |
|
|
Early warning systems, predictive analytics, and automated responses to adverse conditions. |
Reduced catastrophic losses. Faster problem detection and response. Improved business continuity. Better insurance outcomes. |
Multi-parameter monitoring. AI-based anomaly detection. Predictive models. Automated alert systems. Remote emergency response. |
(Watson et al., 2018; Wu et al., 2023; Tzu et al., 2024; Dhamdhere et al., 2025) |
5 Challenges and Limitations
5.1 High Initial Investment Costs
Smart aquaculture systems demand a high initial investment, which is a significant obstacle to adoption particularly in small and medium-scale enterprises (Kantal et al., 2025). Although cheaper sensors can reduce initial hardware costs, they also bring about increased long-term expenses due to their frequent calibration and replacement (D'Agaro, 2025). Moreover, integration, networking, data management, and staff training are major drivers of the total cost and may at times surpass the cost of hardware itself (Teixeira et al., 2021).
5.2 Technical Complexity and Maintenance
The technical intricacy of smart aquaculture systems is a major and continuous challenge, especially with regard to rural aquaculture communities (Kassem et al., 2021). The adoption of a wide range of technologies requires highly specific knowledge that is not always available in a rural area, and the extreme nature of the marine environment contributes to the rapid degradation of the sensors, necessitating regular and competent maintenance to overcome such challenges as biofouling and sensor drift (Ramanathan et al., 2023; Rastegari et al., 2023). Moreover, complex software with poor user interfaces may impede effective use by conventional farmers, while remote sites may experience longer downtime after equipment failures because technical support is not readily available, making reliable operation difficult and costly to maintain (Wu et al., 2023).
5.3 Problems in Data Management and Integration
Moreover, the quality and normalization of data, the lack of common data formats, measurement specifications, and quality evaluation procedures prevent intersystem comparisons and transfer of knowledge between operations (Rastegari et al., 2023). Silos of data caused by technical barriers and integration with legacy farm management systems used for record keeping, inventory, and financial tracking prevent full analysis and informed decision-making (Rastegari et al., 2023). Moreover, sensor networks and higher monitoring rates create rapidly increasing data-storage and processing needs, resulting in high cloud-storage costs, greater bandwidth demands, and the necessity to invest in new local computing infrastructure (Kaur et al., 2023).
5.4 Skills Gap and Training Requirements
The skills gap is a major issue for the establishment of PA since the technical skills needed to implement it, including sensors, networking, data analysis, and automated control systems, are usually beyond the knowledge base of conventional farmers (Wu et al., 2025). Variability in the quality and availability of training programs adds to this difficulty since, in many cases, they require free time or, in the instance of online resources, they cannot impart the required technical skills (Sidiq et al., 2025). Moreover, the fast-paced technological changes bring an ever-present and pressing need for continuous learning and training that may be difficult for busy farmers to meet.
5.5 Infrastructure and Related Problems
There are also severe infrastructure issues, mainly limited internet access in remote coastal and rural areas, although connectivity is required for cloud monitoring and remote access (Wu et al., 2025). The reliability of power infrastructure is an urgent issue because unstable electrical power at most aquaculture facilities may interfere with monitoring and automated equipment and require expensive and complicated backup power systems to support critical operations (Asgher, 2024). Moreover, in these isolated locations, cellular and satellite systems have limited communication-network coverage, making it necessary to adopt other technologies such as LoRa networks that necessitate further investment in infrastructure and technical skills (Sidiq et al., 2025).
5.6 Future directions and possible emerging trends
The ongoing evolution of PA will continue to transform the industry through the integration of blockchain, advanced AI/IoT, robotics, and sustainable technologies. Blockchain will provide immutable traceability and automate compliance, and explainable AI/IoT systems will improve decision-making and adaptability across farms. Robotics will expand the use of autonomous underwater vehicles and automated harvesting to enhance safety and efficiency.
At the same time, energy-harvesting systems (solar, wind, and wave energy), biodegradable sensors, and circular-economy models will contribute to sustainable development and reduce the negative effects on the environment. As the world market is expected to expand considerably, these converging technologies will make aquaculture more transparent, automated, and sustainable. This revolution will mark the transition from aquaculture 4 (technology-based approach) to aquaculture 5 (ecological sustainability and robust systems).
6 Conclusion
Due to the increase in the demand for seafood around the globe and the need to ensure sustainability, PA will be an unavoidable necessity. PA is able to deal with many of the problems that conventional aquaculture activities have. The integration of IoT, sensors, AI, automated systems, and real-time monitoring has resulted in significant improvements in economic performance, fish welfare, environmental sustainability, and production efficiency. The challenges that this technology faces include high initial expenses, limitations in infrastructure (energy, remote connection), lack of expertise, technical complexity, and issues in data management. To address these challenges, researchers, technology firms, and farmers should collaborate on the future development of precision aquaculture.
Funding:
This research did not receive any specific grant from funding agencies.
Hijran Yavuzcan and Abdallah Tageldein Mansour: Conceptualization; writing—original draft preparation; writing—review and editing. All authors have read and approved the submission of the manuscript.
Ethical approval
Not applicable.
Informed consent:
Not applicable.
Conflict of interest:
The authors declare no conflicts of interest.
Data availability:
Not applicable.
Declaration of using AI Technology
The author(s) declared that they used QuillBot to rephrase some text in the manuscript to increase clarity and readability. After using this tool, the authors reviewed and edited the content as needed and took full responsibility for the publication's content.
References
Anand, P. R., & Otta, S. K. (2022). Development of a mobile application for Pacific white shrimp (Penaeus vannamei) farming and evaluation of its efficiency in technology communication and feedback. Aquaculture International, 30(6), 2725-2739. https://doi.org/10.1007/s10499-022-00930-7
Ariyandi, Z., Taufiq, T., & Nunsina, N. (2025). Design of an Internet of Things (IoT)-Based Fish Feeder System Using an Android Application. Journal of Applied Informatics and Computing, 9(4), 1593-1601. https://doi.org/10.30871/jaic.v9i4.10072
Cai, H., Li, F., Lv, P., Ran, L., & Zou, L. (2021). Intelligent aquaculture environment monitoring system based on LoRa communication technology. INMATEH-Agricultural Engineering, 63. https://doi.org/10.35633/INMATEH-63-11
Chahid, A., N’Doye, I., Majoris, J. E., Berumen, M. L., & Laleg-Kirati, T. M. (2021). Model predictive control paradigms for fish growth reference tracking in precision aquaculture. Journal of Process Control, 105, 160-168. https://doi.org/10.1016/j.jprocont.2021.07.015
Chang, C.-C., Wang, J.-H., Wu, J.-L., Hsieh, Y.-Z., Wu, T.-D., Cheng, S.-C., . . . Hsu, T.-H. (2021). Applying artificial intelligence (AI) techniques to implement a practical smart cage aquaculture management system. Journal of Medical and Biological Engineering, 41(5), 652-658. https://doi.org/10.1007/s40846-021-00621-3
Chen, J., Chen, S., Fu, R., Li, D., Jiang, H., Wang, C., . . . Hicks, B. J. (2022). Remote sensing big data for water environment monitoring: Current status, challenges, and future prospects. Earth's Future, 10(2), e2021EF002289. https://doi.org/10.1029/2021EF002289
Chen, J., Xu, Y., Li, H., Zhao, X., Su, Y., Qi, C., . . . Cui, Z. (2025). The Application of Digital Twin Technology in the Development of Intelligent Aquaculture: Status and Opportunities. Fishes, 10(8), 363. https://doi.org/10.3390/fishes10080363
Costa-Pierce, B. A. (2022). The anthropology of aquaculture. Frontiers in Sustainable Food Systems, 6, 843743. https://doi.org/10.3389/fsufs.2022.843743
Coutinho, R. W., & Boukerche, A. (2022). Towards a novel architectural design for IoT-based smart marine aquaculture. IEEE Internet of Things Magazine, 5(3), 174-179. https://doi.org/10.1109/IOTM.001.2200065
D'Agaro, E. (2025). Fish Farming 5.0: Advanced Tools for a Smart Aquaculture Management. Preprints, 2025090785. https://doi.org/10.20944/preprints202509.0785.v1
Dhamdhere, P. B., Dixit, S. M., Tatiya, M., Shinde, B. A., Deone, J., A., K., . . . Waware, S. Y. (2025). AI-based monitoring and management in smart aquaculture for ocean fish farming systems. Applied Chemical Engineering, 8(3), 5746. https://doi.org/10.59429/ace.v8i3.5746
Dhinakaran, D., Gopalakrishnan, S., Manigandan, M., & Anish, T. (2023). IoT-Based environmental control System for Fish farms with sensor Integration and machine learning decision support. arXiv preprint arXiv:2311.04258. https://doi.org/10.48550/arXiv.2311.04258
Dhruv, P., & Naskar, S. (2020). Image classification using convolutional neural network (CNN) and recurrent neural network (RNN): A review. Machine learning and information processing: proceedings of ICMLIP 2019, 367-381. https://doi.org/10.1007/978-981-15-1884-3_34
Dong, K. T. P., Matsuishi, T. F., Duc, N. M., Hoa, N. T. N., Saito, Y., & Dan, T. Y. (2022). Does application of quality assurance certification by shrimp farmers enhance feasibility of implementing traceability along the supply chain? Evidence from Vietnam. Journal of Applied Aquaculture, 34(2), 402-424. https://doi.org/10.1080/10454438.2020.1856751
Dorgham, H. M., Badran, M. F., & El-Dakar, A. Y. (2025). Evaluation of smart fish feeding system using artificial intelligence and internet of things under desert regions. Mediterranean Aquaculture Journal, 12(1), 40-51. https://doi.org/10.21608/maj.2025.433749
Griffin, T. W., Shockley, J. M., & Mark, T. B. (2018). Economics of precision farming. Precision agriculture basics. American Society of Agronomy. https://doi.org/10.2134/precisionagbasics.2016.0098
Islam, M. M. (2025). Prediction Model of Aqua Fisheries Using IoT Devices. arXiv preprint arXiv:2501.10430. https://doi.org/10.48550/arXiv.2501.10430
Islam, S. I., Ahammad, F., & Mohammed, H. (2024). Cutting‐edge technologies for detecting and controlling fish diseases: Current status, outlook, and challenges. Journal of the World Aquaculture Society, 55(2), e13051. https://doi.org/10.1111/jwas.13051
Jais, N. A. M., Abdullah, A. F., Kassim, M. S. M., Abd Karim, M. M., & Muhadi, N. A. (2024). Improved accuracy in IoT-Based water quality monitoring for aquaculture tanks using low-cost sensors: Asian seabass fish farming. Heliyon, 10(8), e29022. https://doi.org/10.1016/j.heliyon.2024.e29022
Kannan, A. D., Lean, C. P., Chen, L., Kong, F. Y., Ng, P. K., & Khan, M. R. B. (2024). Improving fish quality and yield: an automated monitoring system for intensive aquaculture. Malaysian Journal of Science and Advanced Technology, 4(2), 159-168. https://doi.org/10.56532/mjsat.v4i2.296
Kantal, D., Arun, K., & Ganie, P. A. (2025). Economic Implications of Information Technology in Aquaculture and Fisheries. In Information Technology in Fisheries and Aquaculture (pp. 227-250). Springer. https://doi.org/10.1007/978-981-97-8553-7_13
Karimanzira, D. (2025). Comprehensive Fish Feeding Management in Pond Aquaculture Based on Fish Feeding Behavior Analysis Using a Vision Language Model. Aquaculture Journal, 5(3), 15. https://doi.org/10.3390/aquacj5030015
Kassem, T., Shahrour, I., El Khattabi, J., & Raslan, A. (2021). Smart and sustainable aquaculture farms. Sustainability, 13, 10685. https://doi.org/10.3390/SU131910685
Kaur, G., Adhikari, N., Krishnapriya, S., Wawale, S. G., Malik, R., Zamani, A. S., . . . Osei-Owusu, J. (2023). Recent advancements in deep learning frameworks for precision fish farming opportunities, challenges, and applications. Journal of Food Quality, 2023(1), 4399512. https://doi.org/10.1155/2023/4399512
Kimothi, S., Thapliyal, A., Singh, R., Rashid, M., Gehlot, A., Akram, S. V., & Javed, A. R. (2023). Comprehensive database creation for potential fish zones using IoT and ML with assimilation of geospatial techniques. Sustainability, 15(2), 1062. https://doi.org/10.3390/su15021062
Li, D., Li, X., Wang, Q., & Hao, Y. (2022). Advanced techniques for the intelligent diagnosis of fish diseases: A review. Animals, 12(21), 2938. https://doi.org/10.3390/ani12212938
Lindholm‐Lehto, P. (2023). Water quality monitoring in recirculating aquaculture systems. Aquaculture, Fish and Fisheries, 3(2), 113-131. https://doi.org/10.1002/aff2.102
Maharmi, B., Fadli, I., Machdalena, M., Syabriyana, M., & Mirfaturiqa, M. (2025). Implementation of an IoT-Integrated Feedback Control System for Water Quality and Feeding Automation in Aquaculture. Journal of Ocean, Mechanical and Aerospace-science and engineering-, 69(2), 99-105. http://dx.doi.org/10.36842/jomase.v69i2.547
Mandal, A., & Ghosh, A. R. (2024). Role of artificial intelligence (AI) in fish growth and health status monitoring: A review on sustainable aquaculture. Aquaculture International, 32(3), 2791-2820. https://doi.org/10.1007/s10499-023-01297-z
Mansour, A. T., Ashour, M., Alprol, A. E., & Alsaqufi, A. S. (2022). Aquatic Plants and Aquatic Animals in the Context of Sustainability: Cultivation Techniques, Integration, and Blue Revolution. Sustainability, 14, 3257. https://doi.org/10.3390/su14063257
Nagothu, S. K., Bindu Sri, P., Anitha, G., Vincent, S., & Kumar, O. P. (2025). Advancing aquaculture: fuzzy logic-based water quality monitoring and maintenance system for precision aquaculture. Aquaculture International, 33(1), 32. https://doi.org/10.1007/s10499-024-01701-2
Narayana, T. L., Venkatesh, C., Kiran, A., Kumar, A., Khan, S. B., Almusharraf, A., & Quasim, M. T. (2024). Advances in real time smart monitoring of environmental parameters using IoT and sensors. Heliyon, 10(7), e28195. https://doi.org/10.1016/j.heliyon.2024.e28195
Nayoun, M. N. I., Hossain, S. A., Rezaul, K. M., Siddiquee, K. N. e. A., Islam, M. S., & Jannat, T. (2024). Internet of Things-Driven Precision in Fish Farming: A Deep Dive into Automated Temperature, Oxygen, and pH Regulation. Computers, 13(10), 267. https://doi.org/10.3390/computers13100267
Norman, R., Crumlish, M., & Stetkiewicz, S. (2019). The importance of fisheries and aquaculture production for nutrition and food security. Revue scientifique et technique (International Office of Epizootics), 38(2), 395-407. https://doi.org/10.20506/rst.38.2.2994s
Panudju, A. T., Rahardja, S., & Nurilmala, M. (2023). Decision Support System in Fisheries Industry: Current State and Future Agenda. International Journal on Advanced Science, Engineering & Information Technology, 13(2), 599-610. https://doi.org/10.18517/ijaseit.13.2.17914
Ragab, S., Hoseinifar, S. H., Van Doan, H., Rossi, W., Davies, S., Ashour, M., & El-Haroun, E. (2025). Overview of aquaculture Artificial Intelligence (AAI) applications: Enhance sustainability and productivity, reduce labor costs, and increase the quality of aquatic products. Annals of Animal Science, 25(2), 441-453. https://doi.org/10.2478/aoas-2024-0075
Ramanathan, R., Duan, Y., Valverde, J., Van Ransbeeck, S., Ajmal, T., & Valverde, S. (2023). Using IoT sensor technologies to reduce waste and improve sustainability in artisanal fish farming in southern brazil. Sustainability, 15(3), 2078. https://doi.org/10.3390/su15032078
Rastegari, H., Nadi, F., Lam, S. S., Ikhwanuddin, M., Kasan, N. A., Rahmat, R. F., & Mahari, W. A. W. (2023). Internet of Things in aquaculture: A review of the challenges and potential solutions based on current and future trends. Smart Agricultural Technology, 4, 100187. https://doi.org/10.1016/j.atech.2023.100187
Shao, Z. J. (2001). Aquaculture pharmaceuticals and biologicals: current perspectives and future possibilities. Advanced drug delivery reviews, 50(3), 229-243. https://doi.org/10.1016/S0169-409X(01)00159-4
Shareef, Z., & Reddy, S. (2018). Wireless sensor network for aquaculture: Review, survey, and case study of aquaculture practices in western Godavari region. Journal of Ambient Intelligence and Smart Environments, 10(5), 409-423. https://doi.org/10.3233/AIS-180498
Shi, B., Sreeram, V., Zhao, D., Duan, S., & Jiang, J. (2018). A wireless sensor network-based monitoring system for freshwater fishpond aquaculture. biosystems engineering, 172, 57-66. https://doi.org/10.1016/j.biosystemseng.2018.05.016
Sidiq, M. J., Ganie, P. A., Posti, R., Magloo, A. H., & Bhat, R. A. H. (2025). Current Challenges in Fisheries and Aquaculture Sector: A Technological Perspective. In Information Technology in Fisheries and Aquaculture (pp. 35-57). Springer. https://doi.org/10.1007/978-981-97-8553-7_3
Silalahi, A. O., Sinambela, A., Panggabean, H. M., & Pardosi, J. T. (2023). Smart automated fish feeding based on IOT system using Lora TTGO SX1276 and Cayenne platform. EUREKA: Physics and Engineering, 3, 66-79. https://doi.org/10.21303/2461-4262.2023.002745
Singh, M., Sahoo, K. S., & Gandomi, A. H. (2023). An intelligent-IoT-based data analytics for freshwater recirculating aquaculture system. IEEE Internet of Things Journal, 11(3), 4206-4217. https://doi.org/10.1109/JIOT.2023.3298844
Teixeira, R. R., Puccinelli, J. B., Poersch, L., Pias, M. R., Oliveira, V. M., Janati, A., & Paris, M. (2021). Towards precision aquaculture: A high performance, cost-effective IoT approach. arXiv preprint arXiv:2105.11493. https://doi.org/10.48550/arXiv.2105.11493
Tzu, N. L., Farha, W. A. R. W. E., Musa, N., Rifqi, M. M., Hidayati, S., Pratiwi, H., . . . Abd Aziz, M. F. H. (2024). Sensing Technologies and Automation: Revolutionizing Aquaculture Towards Sustainability and Resilience. Semarak International Journal of Agriculture, Forestry and Fisheries, 1(1), 10-18.
Ubina, N. A., & Cheng, S.-C. (2022). A review of unmanned system technologies with its application to aquaculture farm monitoring and management. Drones, 6(1), 12. https://doi.org/10.3390/drones6010012
Verma, D. K., Satyaveer, N. K. M., Kumar, P., & Jayaswa, R. (2022). Important water quality parameters in aquaculture: An overview. Agriculture and Environment, 3(3), 24-29.
Verma, U. S., & Gupta, N. (2022). RAS Enhancement of Wireless Sensor Network Using Hybrid Approach. Wireless Personal Communications, 124(4), 3355-3374. https://doi.org/10.1007/s11277-022-09516-1
Vignesh, P., Antony, C., Selvaraj, S., & Venkateshwara, D. (2024). Precision aquaculture-a data driven farming method for sustainable aquaculture. Journal of Aquaculture in the Tropics, 39(1-4), 30-38. http://doi.org/10.32381/JAT.2024.39.1-4.4
Watson, J. R., Armerin, F., Klinger, D. H., & Belton, B. (2018). Resilience through risk management: cooperative insurance in small-holder aquaculture systems. Heliyon, 4(9), e00799. https://doi.org/10.1016/j.heliyon.2018.e00799
Wei, Y., Ji, L., & An, D. (2025). Review on Quantitative Methods of Fish School Behaviors. Reviews in Aquaculture, 17(3), e70023. https://doi.org/10.1111/raq.70023
Wibowo, B., Ramadhani, N. P., Alfianza, F., Rizky, F. A., & Hidayat, T. (2025). Smart Aquaculture: Automated Fish Feeding with Blynk Alerts. Jurnal Komputer dan Elektro Sains, 3(2), 10-13. https://doi.org/10.58291/komets.v3i2.299
Williams, Z., Soto Calvo, M., Lee, H. S., Aljber, M., & Jeong, J.-S. (2025). A Low-Cost Autonomous Multi-Functional Buoy for Ocean Currents and Seawater Parameter Monitoring, and Particle Tracking. Journal of Marine Science and Engineering, 13(9), 1629. https://doi.org/10.3390/jmse13091629
Wu, A.-Q., Li, K.-L., Song, Z.-Y., Lou, X., Hu, P., Yang, W., & Wang, R.-F. (2025). Deep Learning for Sustainable Aquaculture: Opportunities and Challenges. Sustainability, 17(11), 5084. https://doi.org/10.3390/su17115084
Yasruddin, M., Husin, Z., Ismail, M., & Keong, T. (2025). Smart aquaculture: an advanced intelligent predictive analysis of disease risks and recommendation system for managing fish health. Neural Computing and Applications, 37, 14499–14520. https://doi.org/10.1007/s00521-025-11295-2