Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

Abstract

The digital transformation of aquaculture is reshaping the sector by integrating advanced technologies that enhance efficiency and sustainability. This transformation is primarily driven by the adoption of Artificial Intelligence (AI), biological models and sophisticated data acquisition systems, which enable real-time monitoring and management of aquaculture operations. This chapter explores the applications of AI, robotics and biological models in various facets of aquaculture, highlighting their roles in enhancing productivity, sustainability and operational precision. AI-based solutions optimize feeding strategies, disease detection and water quality management by analyzing sensor data to ensure optimal conditions for fish growth and health, reducing manual intervention and minimizing environmental risks. Biological models simulate fish growth patterns, supporting informed decision-making, while IoT sensors and cloud computing enhance data acquisition, improving traceability and resource management. Robotics automate labour-intensive tasks, such as feeding and harvesting, with precision. Automated feeding systems, use robotic arms and computer vision, to precisely dispense feed based on fish feeding behavior, minimizing waste and ensuring optimal nutrition. Harvesting robots, guided by algorithms, sort and handle fish efficiently, reducing stress and enhancing yield quality. The integration of AI and robotics boosts operational efficiency, reduces labour costs and supports sustainable practices by optimizing resource use and minimizing environmental impacts. However, challenges like high initial investments, scalability and regulatory considerations remain significant. These technologies are advancing precision aquaculture, maximizing production outputs and environmental stewardship while reducing human intervention. Continued research and development are essential to address existing challenges and unlock the full potential of digital transformation in aquaculture.

Full text

23
The digital transformation of aquaculture is reshaping the sector by integrating
advanced technologies that enhance efficiency and sustainability. This
transformation is primarily driven by the adoption of Articial Intelligence (AI),
biological models and sophisticated data acquisition systems, which enable
real-time monitoring and management of aquaculture operations. This chapter
explores the applications of AI, robotics and biological models in various facets
of aquaculture, highlighting their roles in enhancing productivity, sustainability
and operational precision. AI-based solutions optimize feeding strategies, disease
detection and water quality management by analyzing sensor data to ensure optimal
conditions for sh growth and health, reducing manual intervention and minimizing
environmental risks. Biological models simulate sh growth patterns, supporting
informed decision-making, while IoT sensors and cloud computing enhance data
acquisition, improving traceability and resource management. Robotics automate
labour-intensive tasks, such as feeding and harvesting, with precision. Automated
feeding systems, use robotic arms and computer vision, to precisely dispense feed
based on sh feeding behavior, minimizing waste and ensuring optimal nutrition.
Harvesting robots, guided by algorithms, sort and handle sh efciently, reducing
stress and enhancing yield quality. The integration of AI and robotics boosts
operational efciency, reduces labour costs and supports sustainable practices
by optimizing resource use and minimizing environmental impacts. However,
challenges like high initial investments, scalability and regulatory considerations
remain signicant. These technologies are advancing precision aquaculture,
maximizing production outputs and environmental stewardship while reducing
human intervention. Continued research and development are essential to address
existing challenges and unlock the full potential of digital transformation in
aquaculture.
*Corresponding author’s e-mail: masternagendra123@gmail.com
Sravani, G., Nagendr asai, K., Prasannalaxmi, U., Akamad, K.D., Venkat, C.S.S., 2025. Fish, Tech and Future:
The role of automation and digital tools for sustainable tomorrow. In: Aquaculture Reimagined: Modern
Approaches to Sustainable Fish Farming. (Eds.) Saini, V.P., Paul, T., Singh, A.K., Biswal, A. and Samanta,
R. Biotica Publications, India. pp. 23-40. DOI: https://doi.org/10.54083/978-81-980121-3-5_03.
Fish, Tech and Future: e Role of Automation and
Digital Tools for Sustainable Tomorrow
Guntapalli Sravani1, Kurapati Nagendrasai2*, Uppalanchi Prasannalaxmi1,
Akamad Kamil D.1 and Chundru Sri Sai Venkat3
1Aquaculture Division, 2Aquatic Environment and Health Management Division, 3Fish Nutrition,
Biochemistry and Physiology Division, ICAR-CIFE, Mumbai, Maharashtra (400 061), India
Abstract
DOI: https://doi.org/10.54083/978-81-980121-3-5_03
Aquaculture Reimagined: Modern Approaches to Sustainable Fish Farming Chapter 3
Aquaculture, Capacity building, Education, Training
Keywords
How to cite:

24
1. Introduction
Fisheries play a critical role in global food security and economic development,
contributing signicantly to the livelihoods of millions. According to recent
statistics, global sh production has steadily increased, with total production
including capture sheries and aquaculture reaching over 178 million
tonnes annually. However, as demand for sh products continues to grow,
the industry faces numerous challenges such as overshing, environmental
changes and resource management inefciencies. To address these issues,
the sector is increasingly embracing digitalization and automated technologies
aligned with the principles of Industry 4.0 (Luna et al., 2016). Industry 4.0
signies the next stage of the industrial revolution, focusing on the integration
of digital technologies, automation and data-driven decision-making. For
sheries and aquaculture, embracing these advanced technologies is vital
to improving productivity, sustainability and resilience. Tools like AI-based
monitoring systems, IoT-enabled sensors and smart feeding solutions provide
real-time insights and analytics, enhancing operational efciency while
lowering labour costs and minimizing environmental impact. The transition
to these technologies is not only a response to increasing production needs
but also a strategic approach to ensure the future sustainability of sheries
in a rapidly changing environment.
2. Automation
Automation in aquaculture refers to the application of technology and
machinery to perform tasks and processes in sh and seafood farming
without direct human intervention (Li et al., 2024). It encompasses a wide
range of activities, from feeding and water quality management to data
monitoring and harvesting. Automation is crucial in modern aquaculture
due to its ability to enhance efciency, precision and sustainability. It helps
address challenges such as labour shortages, environmental concerns and
the need for increased production. Automation in aquaculture systems refers
to the integration of technology to manage and control various aspects of
sh or aquatic organism farming. This can encompass several areas:
• Feeding Systems: Automated feeding systems can dispense precise amounts
of feed at scheduled times, reducing labour and ensuring consistent feeding
regimes that optimize the growth and health of the sh (Pratiwy et al., 2022).
• Water Quality Management: Sensors can monitor parameters such as
dissolved oxygen levels, pH, temperature and ammonia concentrations.
Automated systems can adjust aeration and water ow, or initiate water
exchanges to maintain optimal conditions.
• Monitoring and Control: Remote sensing technologies allow for real-time
monitoring of environmental conditions and sh behavior. This data can be
used to adjust parameters like water quality, feeding rates and environmental
conditions automatically (Luna et al., 2016).
• Recirculating Aquaculture Systems (RAS): RAS relies heavily on automation
to maintain water quality and manage waste. Automated lters, oxygenation
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

25
systems and waste removal mechanisms help maintain stable and clean
water conditions (Saha et al., 2018).
• Harvesting and Sorting: Automated systems can facilitate the harvesting
process by sorting sh based on size or species, reducing handling stress
and improving efciency.
• Health Monitoring: Automated systems can detect early signs of disease
through image recognition, water quality analysis, or behavioral changes,
allowing for timely intervention and reducing losses.
• Data Analytics and Decision Support: Integration of automation with data
analytics enables farmers to make informed decisions based on trends and
predictive models, optimizing production efciency and resource utilization
(Li et al., 2024).
2.1. Principles of Automation
Automation in aquaculture is guided by fundamental principles aimed at
improving efciency, precision and sustainability. It involves real-time data
collection, automation systems rely on sensors and monitoring devices to
continuously gather data on crucial parameters such as water quality,
temperature and sh behavior. Integration of control systems, effective
automation integrates various control systems, including feeding, water
quality management and environmental control, to create a cohesive
and responsive operation. Articial intelligence (AI) decision-making, AI
algorithms analyze the collected data to make informed decisions, optimizing
resource allocation and farm management (Sasikumar et al., 2024). Resource
optimization and automation seek to optimize resource utilization, reducing
waste and ensuring the efcient use of energy, water and feed. Error
reduction, by minimizing human intervention, automation reduces the risk
of human error, leading to more consistent and reliable results.
2.2. Procedures for Implementing Automation
• Needs Assessment: Begin by assessing the specic needs and challenges
of the aquaculture operation. Identify areas where automation can bring
the most signicant benets, such as feeding, water quality management,
or data monitoring.
• Technology Selection: Choose appropriate automation technologies and
equipment based on the identied needs. Consider factors like system
compatibility, scalability and cost-effectiveness.
• Integration: Integrate the selected automation systems seamlessly into the
aquaculture facility. Ensure that all components work together harmoniously
and can communicate efciently.
• Monitoring and Control: Establish a robust monitoring and control protocol
to oversee automated processes. Regularly check system performance and
make adjustments as necessary to optimize operations.
• Maintenance: Develop a proactive maintenance plan to ensure the
continuous functionality of automation systems. Regular inspections,
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

26
servicing and software updates are essential to prevent downtime.
• Training: Train aquaculture personnel to operate and troubleshoot
the automation systems effectively. Knowledgeable staff are critical for
maximizing the benets of automation (Sasikumar et al., 2024).
2.3. History of Automation in Aquaculture
1950s-1960s: Early automation in aquaculture focused on simple mechanical
feeders and pond aeration systems.1970s-1980s: Introduction of basic sensor
technologies for water quality monitoring. Automated sh-feeding systems
gained popularity. 1990s-2000s: Advancements in sensor technology led to
more accurate data collection and control systems. Automated sh grading
and sorting systems were developed. 2010s-Present: Emergence of smart
aquaculture systems using IoT and AI for real-time monitoring by robots for
assessing sh health and underwater inspections like sediment and ocean
oor inspections and decision-making (Simbeye et al., 2018; Pratiwy et al.,
2022).
2.3.1. Milestones and Breakthrough
1970: First automated pond aerators were introduced, improving oxygen
levels. 1995: Automated feeders with programmable timers became widely
available. 2005: Adoption of sensors for monitoring water parameters such
as pH, dissolved oxygen and temperature. 2012: The use of remote sensing
and satellite technology for aquaculture monitoring (Simbeye et al., 2018)
expanded. 2018: AI-driven predictive analytics began to optimize feeding
schedules and disease detection. 2020: Development of underwater robots
for efcient monitoring and maintenance (Figure 1).
Figure 1: Key milestones in the history of aquaculture automation
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

27
2.4. Future Possibilities
Advancements in aquaculture leverage AI for decision-making, robotics
for underwater tasks and automation in breeding and genetic programs.
Integration with aquaponics promotes sustainable food systems, while
automation reduces waste and enhances resource efficiency. These
innovations drive smarter, eco-friendly practices, transforming aquaculture
into a more efcient and sustainable industry (Figure 2).
Figure 2: Future scope of Articial Intelligence (AI) in aquaculture
• AI for Decision-Making: Advanced AI algorithms will play a pivotal role in
optimizing operations, from feed management to disease control.
• Robotics and Autonomous Vehicles: Robots will perform underwater
inspections, cleaning and maintenance tasks.
• Genetic and Breeding Automation: Automation may enhance selective
breeding and genetic improvement programs.
• Aquaponics Integration: Automation will facilitate the integration of
aquaculture with hydroponics or aquaponics systems.
• Sustainable Aquaculture: Automation will contribute to more sustainable
and environmentally friendly practices by reducing waste and resource
consumption (Pratiwy et al., 2022).
3. Articial Intelligence (AI)
Artificial intelligence (AI) is transforming industries worldwide and
aquaculture is no exception. As global demand for seafood rises, the
aquaculture sector faces challenges such as optimizing production efciency,
enhancing environmental sustainability and ensuring economic viability. AI
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

28
technologies offer promising solutions by enabling precise monitoring, data-
driven decision-making and automation of critical processes. In aquaculture,
AI encompasses a range of applications, from real-time monitoring of
water quality and sh health to optimizing feeding regimes and managing
environmental factors. Machine learning algorithms analyze vast datasets
collected from sensors, cameras and other sources, providing insights that
traditional methods cannot match. These insights enable aquaculture
operators to adjust parameters such as feeding schedules, water ow
and oxygen levels dynamically, thereby improving growth rates, reducing
disease risks and minimizing environmental impacts (Pratiwy et al., 2022).
Furthermore, AI-driven predictive models help anticipate challenges such
as disease outbreaks or adverse weather conditions, allowing for proactive
management strategies. Autonomous systems, including underwater drones
and robotic platforms, contribute to enhancing monitoring and operational
efciency in aquaculture facilities, reducing labour costs and human error.
While AI presents signicant opportunities for innovation in aquaculture,
challenges such as data privacy, regulatory frameworks and the need for
specialized expertise must be navigated. By leveraging AI technologies
effectively, the aquaculture industry can achieve sustainable growth while
meeting the growing global demand for seafood.
3.1. Application of AI in Aquaculture
3.1.1. AI-based Feeding Device in Aquaculture Systems
An advanced AI feeding device has been developed by the Indonesian
aquaculture company, e-Fishery (Li et al., 2024). The system integrates
motion sensors to monitor fish behavior and detect appetite levels,
automatically dispensing feed when sh display signs of hunger. This
innovation is capable of reducing feed costs by approximately 21%, enhancing
feed efciency and reducing waste. The technology includes proprietary
software that allows sh farmers to remotely monitor feeding activities in real
time and make adjustments as needed through their smartphones. Similarly,
Observe Technologies offers an AI-based solution that tracks and analyzes
feeding patterns in aquaculture systems. The platform provides objective
data and empirical insights, guiding farmers on the optimal feed quantities
required based on the real-time behavior of the sh and ensuring precise
feed management. In Singapore and Japan, the aquaculture tech company
has introduced the Umitron Cell, a smart feeding system controlled remotely.
This device leverages data-driven decision-making algorithms to optimize
feeding schedules, allowing farmers to customize feed distribution patterns,
thereby improving the efciency and sustainability of feeding practices.
3.1.2. AI-Driven Drones in Aquaculture
Autonomous drones equipped with advanced sensors can continuously
monitor essential water quality parameters, such as turbidity, temperature,
dissolved oxygen levels and even the physiological responses of sh, including
heart rates (Simbeye et al., 2018). These real-time data are transmitted to a
centralized system, which can be accessed via smartphones or other digital
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

29
devices, enabling efcient monitoring and management of aquaculture
environments. Expanding on these innovations, researchers have developed
a bio-inspired robotic system known as ‘Shoal.’ These autonomous robotic
sh are designed to detect contaminants and monitor environmental health
around aquaculture sites. Equipped with high-precision sensors, they
navigate independently within the aquatic environment and communicate
via low-frequency acoustic signals, enabling collective data gathering and
coordinated responses to changes in water quality (Sasikumar et al., 2024).
3.1.3. Disease Prevention in Aquaculture
The Norwegian Seafood Innovation Cluster launched an advanced cloud-
based platform, AquaCloud, in April 2017 to support aquaculture farmers
in mitigating the risk of sea lice infestations in net pens. By leveraging real-
time data analytics and predictive modelling, the system effectively aids in
reducing sh mortality rates and minimizing reliance on costly chemical or
mechanical treatments for parasite control.
3.1.4. Articial Intelligence in Shrimp Aquaculture
Eruvaka Technologies, based in India, provides AI-powered solutions
specically designed for shrimp aquaculture (Al-Hussaini et al., 2018). These
include real-time water quality monitoring, automated voice alerts, intelligent
appetite-based feeding systems and autonomous aerator management.
Deployed across around 1,000 hectares in regions such as Surat, Goa andhra
Pradesh and Pondicherry, Eruvaka’s innovations help optimize feeding
efciency and maintain ideal pond conditions. As a result, the technology
enhances farm management, boosting both productivity and sustainability
in shrimp farming.
3.1.5. Biomass Estimation
Minnowtech, a U.S.-based aquaculture technology company has developed
a software-imaging platform to estimate shrimp abundance (Daoliang et al.,
2020; Li et al., 2024). A sonar device collects data from shrimp ponds and
provides farmers with a weekly biomass estimate. Tracking biomass enables
farmers to better calculate average daily growth and feed conversion ratio.
3.1.6. Routine Stock Assessment in Aquaculture
AI-driven vision-based sensors facilitate real-time monitoring of cultured
aquatic species by analyzing their swimming behavior, growth patterns
and physical condition, including any injuries. One notable innovation is
XperCount, an AI-powered device developed by the aquaculture technology
company XpertSea (Karningsih et al., 2021). This device employs machine
learning algorithms and integrated camera systems to rapidly measure,
count, image and size shrimp within seconds. The data collected is processed
for comprehensive health assessments, enabling timely intervention and
management of stock health.
3.1.7. AI in Open Sea Fisheries
The Global Fishing Watch Platform, an independent organization, has
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

30
partnered with Google, Oceana and SkyTruth, non-prot digital mapping
organization, to leverage AI and satellite imagery for tracking global shing
activities. This initiative enables precise monitoring of Illegal, Unreported
and Unregulated (IUU) vessels, as well as detecting poaching, overshing
and at-sea transshipments (the transfer of catches between vessels). AI-
based surveillance systems can also capture critical information on vessel
dimensions and the types of shing gear employed, facilitating enhanced
regulation and sustainable sheries management Li et al., 2024).
3.1.8. AI for Conservation of Endangered Marine Species
AI-enabled drones equipped with visual sensors and high-resolution
cameras are revolutionizing the monitoring of endangered sh populations
by providing rapid and accurate habitat assessments. For larger marine
species, such as sharks and humpback whales, researchers can deploy
telemetry transmitters attached to their ns, allowing for real-time tracking
and behavioral analysis. These technologies signicantly enhance the
efciency of conservation efforts by enabling more precise data collection,
contributing to improved strategies for protecting vulnerable marine fauna
(Saha et al., 2018).
3.2. Advantages of AI in Fisheries
The integration of AI technology in fisheries management enhances
operational efficiency across the entire value chain, from hatchery
operations to post-harvest processing. By employing predictive analytics,
AI can accurately forecast potential threats, such as disease outbreaks or
deterioration in water quality, enabling proactive measures to safeguard
stock health (Al-Hussaini et al., 2018). Additionally, AI applications can
optimize feeding practices, water parameters and growth conditions,
thereby maximizing production and minimizing resource wastage (Figure
3). AI systems, through continuous learning and adaptation, offer versatile
solutions tailored to various aquaculture settings. These technologies not
only streamline routine management tasks but also reduce the need for
manual labour, thereby cutting operational costs. Furthermore, AI-driven
monitoring and automation ensure greater product quality and uniformity
by maintaining optimal environmental conditions and precision feeding,
ultimately contributing to sustainable aquaculture practices.
3.3. Disadvantages of AI in Fisheries
The adoption of articial intelligence in the sheries and aquaculture sectors
often requires substantial nancial investment, which may be prohibitive
for small and medium-scale operators. The initial setup costs, coupled with
ongoing maintenance and software updates, can signicantly strain nancial
resources. Furthermore, the integration of AI-driven automation systems
can lead to reduced demand for manual labour, potentially displacing
workers who rely on employment within these industries. Although these
advancements may boost efciency and protability for farm owners, they
pose socio-economic challenges for communities dependent on traditional
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

31
sheries employment. To address this, it is crucial to implement policies
and training programs aimed at reskilling the workforce, enabling them to
take on new roles in managing and operating AI systems, thereby ensuring
a balanced transition that benets both productivity and social equity
(Daoliang et al., 2020).
4. Robotics
Robotics in aquaculture represents a burgeoning eld where technological
advancements are reshaping traditional farming practices. This integration
of robotics offers novel solutions to challenges in labour efciency, resource
management and environmental sustainability within aquaculture operations
(Vásquez-Quispesivana et al., 2022). One of the primary applications of
robotics in aquaculture is in automated feeding systems. These systems
use robotic arms equipped with sensors and cameras to dispense precise
amounts of feed based on real-time data on sh behavior and growth
rates. By optimizing feeding schedules and reducing waste, robotic feeders
contribute to improved feed conversion ratios and overall economic efciency.
Additionally, robotics play a crucial role in monitoring and maintaining water
quality. Autonomous underwater vehicles (AUVs) equipped with sensors
can navigate aquaculture facilities, collecting data on parameters such as
dissolved oxygen levels, pH and temperature (Albalawi et al., 2021). This
continuous monitoring helps aquaculturists detect potential issues early,
such as oxygen depletion or contamination, allowing for prompt corrective
actions and reducing the risk of sh stress or mortality. Harvesting is another
area where robotics shows signicant promise. Automated systems can sort
and harvest sh based on size, species, or maturity, minimizing handling
Figure 3: Key advantages and applications of AI in aquaculture systems
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

32
stress and ensuring high-quality yields. Robotic harvesters not only enhance
efciency but also reduce reliance on manual labour, which can be costly
and labour-intensive. Moreover, robotics contribute to sustainability efforts
in aquaculture by reducing environmental impacts. Automated systems
can optimize water usage, minimize feed waste and manage efuents more
efciently, thus mitigating potential pollution and resource depletion. While
the adoption of robotics in aquaculture brings numerous benets, challenges
such as high initial costs, technological complexity and the need for
specialized training and maintenance persist. Overcoming these challenges
requires collaboration between technology developers, aquaculture operators
and regulatory bodies to ensure the safe, effective and sustainable integration
of robotics into aquaculture practices.
4.1. Novel Robotics Advances in Aquaculture
Robotics and AI innovations, such as autonomous vehicles, drones and
automated systems, are transforming aquaculture by improving efciency,
monitoring and sustainability while enhancing sh health and optimizing
critical tasks like feeding, cleaning and vaccination (Zhao et al., 2021). There
are many advanced underwater robots for various applications in the eld
of sheries and aquaculture (Figure 4).
Figure 4: Various advanced underwater robots used in sheries and
aquaculture
4.1.1. Robot Fish Herding
An exemplary innovation in this eld is the ‘RangerBot’, developed by
the Queensland University of Technology, Australia. It is the world’s rst
vision-based autonomous underwater robotic system engineered specically
for coral reef ecosystems. Equipped with advanced computer vision and
machine learning algorithms, RangerBot is capable of monitoring critical reef
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

33
health parameters such as coral bleaching, water quality and overall reef
structure through precise mapping and inspection (Albalawi et al., 2021).
One of RangerBot’s primary functions is the management of Acanthaster
planci (crown-of-thorns starsh) populations, a signicant coral predator
threatening reef stability. By emulating the behavior of natural sh species,
RangerBot can navigate complex reef terrains to locate and target these
starsh (Vásquez-Quispesivana et al., 2022). Upon detection, the robot
deploys a lethal injection specically formulated to eradicate the starsh
without harming the surrounding marine environment, providing an
ecologically sustainable method of controlling invasive species and protecting
coral reef biodiversity.
4.1.2. Unmanned Surface Vehicles (USVS)
Example: Saildrone, a company that specializes in USVs, has developed
autonomous sailboats equipped with various sensors for environmental
monitoring. These USVs collect data on water quality, temperature and other
relevant parameters in aquaculture settings, helping farmers make informed
decisions about water management (Albalawi et al., 2021).
4.1.3. Submersible Inspection Robots
Example: The “BlueROV2” by Blue Robotics. It is a remotely operated
underwater vehicle (ROV) used for various tasks, including inspecting
underwater infrastructure like cages and nets in aquaculture farms. Its HD
cameras and lights allow operators to assess the condition of equipment and
monitor sh health (Al-Hussaini et al., 2018).
4.1.4. Underwater 3D Printing
Researchers are exploring underwater 3D printing technology for creating
and repairing structures in aquaculture facilities. This technology can be
used to produce custom components, such as coral nurseries or articial
reefs, to enhance the habitat for aquatic organisms. Underwater 3D printing
enables the rapid construction of articial reefs directly on-site, reducing the
time and resources required for transportation and installation. This speed
is particularly crucial in areas where natural reefs have been damaged or
destroyed due to human activities or natural disasters (Karningsih et al.,
2021).
4.1.5. Aquatic Weed Removal Robots
Example: The “Weed-IT” robot, developed in the Netherlands, is designed
to autonomously remove aquatic weeds from sh ponds and water bodies.
Equipped with cameras and sensors, it identies and targets the weeds,
reducing the need for manual removal and chemical treatments (Teja et
al., 2020).
4.1.6. Autonomous Net Cleaning Robots
Example: Robots like the “Ecomerdenet Cleaner” and “Remora” (the rst
fully autonomous net cleaner and inspector) are specically designed for
cleaning sh nets in aquaculture operations (Yongqiang et al., 2019). These
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

34
robots use high-pressure water jets to remove fouling organisms and debris
from the nets, ensuring water ow and maintaining the health of the sh.
4.1.7. Aquatic Drone Feeding Systems
Example: Companies like XpertSea have developed autonomous drone-based
feeding systems equipped with cameras and AI algorithms. These drones
can y over aquaculture ponds, analyze sh behavior and feeding patterns
and dispense the appropriate amount of feed to optimize growth rates and
minimize waste (Kruusmaa et al., 2020).
4.1.8. Fish Vaccination Robots
Example: Norwegian company Stingray Marine Solutions has developed an
automated system known as the “Stingray” for vaccinating farmed salmon
(Teja et al., 2020). The robot identies individual sh in a cage, positions
them for vaccination and administers precise doses of vaccines, reducing
stress and the risk of disease transmission. Different organizations and
companies are involved in the development and deployment of robotics
technologies for aquaculture.
4.1.9. Blue Robotics
Blue Robotics specializes in underwater robotics and provides remotely
operated vehicles (ROVs) and components that are widely used in aquaculture
for inspection and monitoring tasks.
4.1.10. Saildrone
Saildrone designs and deploys unmanned surface vehicles (USVs) equipped
with various sensors for environmental monitoring, including applications
in aquaculture.
4.1.11. Stingray Marine Solutions
Stingray Marine Solutions offers automated systems for sh vaccination in
aquaculture, helping to improve sh health and reduce stress during the
vaccination process (Lee, 1995).
4.1.12. Liquid Robotics (a subsidiary of Boeing)
Liquid Robotics develops autonomous marine robots, including Wave Gliders,
which have applications in environmental monitoring and data collection
for aquaculture (Kassem et al., 2021).
4.1.13. C-Worker (by L3Harris) and Other AUV Manufacturers
Various autonomous underwater vehicle (AUV) manufacturers, such as
L3Harris, offer AUVs for underwater inspection and data collection in
aquaculture (Yongqiang et al., 2019).
5. Data Acquisition Systems
Data acquisition systems are essentially tools that allow us to collect and
analyze data from various sources within an aquaculture operation. This
information provides valuable insights into the health and productivity of
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

35
sh populations, water quality and overall system performance. By using
these systems, we can make informed decisions that lead to increased
efciency, improved yields and ultimately, a more sustainable industry
(Lee, 1995). Data acquisition systems are devices used to collect, process
and store data from various sources in real-time. They can be thought of as
the brain of any monitoring or control system, as they enable the system to
gather information about its environment and respond accordingly. These
systems typically consist of three main components: sensors to measure
physical quantities such as temperature and pressure, a signal conditioning
circuit to convert the sensor output into a suitable form for processing and
a data acquisition device to capture the conditioned signal and store it in
memory for subsequent analysis. The data can then be analyzed using
specialized software to extract meaningful information about the system
under observation (Albalawi et al., 2021).
5.1. Benets of Implementing Data Acquisition Systems
Increased efciency, real-time monitoring allows farmers to make data-
driven decisions and rapidly respond to changes in the environment. This
improves yield and reduces costs. Improved animal welfare, with constant
monitoring, farmers can detect and address potential threats before they
become emergencies, ensuring that their animals are healthy and well-cared
for. Sustainability gains, by reducing waste and optimizing resources, data
acquisition systems can help farmers operate with a lower environmental
impact (Daoliang et al., 2020).
5.2. Types of Data Acquisition Systems in Aquaculture
There are several types of data acquisition systems used in aquaculture,
each with its own unique set of functions and advantages. One such system
is the sensor-based data acquisition system, which uses sensors to measure
various environmental parameters such as water temperature, pH levels and
dissolved oxygen (Vásquez-Quispesivana et al., 2022). Another type of data
acquisition system used in aquaculture is the remote monitoring system,
which allows farmers to monitor their farms from a distance. This system
typically includes cameras and other sensors that can be accessed remotely
via a computer or mobile device. Remote monitoring systems are particularly
useful for farmers who have multiple farms or who need to travel frequently,
as they allow them to keep an eye on their operations from anywhere
in the world. It is used in water quality monitoring, feed management,
environmental conditions, sh behavior and health, sh behavior and
health, remote monitoring, optimization and decision-making, regulatory
compliance, research and development, energy efciency, traceability and
quality assurance (Karningsih et al., 2021).
5.3. Real-World Examples of Data Acquisition Systems in Aquaculture
One example of a successful implementation of data acquisition systems
in aquaculture is at a salmon farm in Norway. By using sensors to monitor
water temperature, oxygen levels and sh behavior, the farm was able to
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

36
optimize feeding schedules and reduce mortality rates by 20%. This not only
improved production but also reduced costs associated with overfeeding and
disease management (Kruusmaa et al., 2020).
Another example is a shrimp farm in Thailand that implemented a data
acquisition system to monitor water quality and detect early signs of disease.
This allowed the farm to quickly respond and treat infected shrimp, reducing
losses and improving overall yield. The system also helped to reduce water
usage and improve sustainability practices (Kassem et al., 2021).
6. Biological Models and Automatic Control Systems: The Future of
Aquaculture.
As the world’s population continues to grow, so does the demand for food.
Aquaculture has become an increasingly important industry in meeting this
demand and automatic control systems are essential for ensuring the efcient
and sustainable production of aquatic organisms. Biological models play a
crucial role in these automatic control systems (Zhao et al., 2021). By using
mathematical and computational models to simulate the behavior of living
organisms, we can better understand and predict how they will respond to
changes in their environment. This allows us to optimize the conditions in
which they are raised, leading to healthier and more productive sh farms.
Biological models are simplied versions of intricate biological systems,
designed to analyze and predict their behavior (Von Borstel et al., 2013). In
aquaculture, these models simulate sh growth, population dynamics and
the interactions within aquatic ecosystems. Using mathematical equations
and computer simulations, researchers can explore various scenarios and
forecast the effects of different management approaches. The role of biological
models in aquaculture is crucial, especially as demand for seafood rises and
pressures on wild sh stocks intensify. As aquaculture becomes an essential
food source, managing sh populations and preserving ecosystem health
remains a complex challenge. Biological models serve as valuable tools to
help researchers and managers better understand these processes and make
well-informed decisions (Von Borstel et al., 2013).
6.1. Types of Biological Models
There are several types of biological models used in aquaculture, each
with their own unique characteristics and applications. One type is the
empirical model, which is based on observations and measurements of
real-world systems. These models are often used to predict the behavior of
complex systems and can be used to optimize feeding strategies or water
quality management. Another type of model is the mathematical model,
which uses mathematical equations to describe the behavior of a system
(Lee, 1995). These models are often used to simulate the effects of different
environmental conditions or management practices on sh growth and
health. Mathematical models can also be used to optimize feeding regimes or
to design new aquaculture systems. Some of the biological models are growth
models, nutrient cycling models, population dynamics models, disease
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

37
spread models, feed conversation models, water quality models, behavioural
models, ecological models, optimization models and multi-trophic models.
7. Advantages of Automation in Aquaculture
Increased efciency, Automation streamlines tasks, leading to greater
operational efciency in feeding, monitoring and harvesting processes.
Precision and consistency, automated systems ensure precise and consistent
execution of tasks, reducing variability and improving overall productivity.
Labor savings, automation reduces the dependency on manual labor,
addressing labor shortages and minimizing operational costs. Data collection
and analysis, automation provides real-time data collection, enabling data-
driven decision-making for farm management and optimization. Reduced
human error, automated processes minimize the risk of human errors,
ensuring higher product quality and environmental compliance. Resource
management, automation optimizes resource utilization, reducing waste
and resource consumption, contributing to sustainability (Wu et al., 2022).
Environmental monitoring, continuous monitoring of water quality and
conditions help maintain optimal environmental parameters and minimize
environmental impacts. 24/7 operation, automation systems can provide
round-the-clock monitoring and control, addressing issues promptly and
reducing the risk of emergencies. Improved product quality, automation
systems like sorting and grading ensure uniformity and high standards
in the nal product. Farms that implement automation gain a competitive
advantage by enhancing efciency, lowering operational costs and producing
higher-quality products. This technological edge enables them to stay
ahead in a rapidly evolving market. Sustainable practices, automation
contributes to more sustainable aquaculture practices by minimizing
environmental impacts and conserving resources (Yongqiang et al., 2019).
Future-proong, as technology advances, automation continues to play a
pivotal role in meeting the growing demand for seafood while addressing
industry challenges.
8. Disadvantages of Automation in Aquaculture
High initial investment, automation systems often require a signicant
upfront investment in technology and infrastructure. Technical complexity,
implementing and maintaining automation systems can be technically
challenging and may require specialized knowledge and training. Dependence
on technology, overreliance on automation can pose risks in case of system
failures or technical glitches, potentially disrupting operations. Energy
consumption, some automation systems, such as recirculating aquaculture
systems (RAS), can have high energy demands, leading to increased
operational costs (Wu et al., 2022). Maintenance costs, automation systems
require regular maintenance and occasional repairs, which can add to
operational expenses. Compatibility issues, integrating different automation
components and systems may face compatibility issues, requiring additional
efforts for seamless operation.
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

38
9. Conclusion
The integration of robotics, AI and automation in aquaculture represents
a transformative leap toward sustainable and efcient seafood production.
By leveraging technologies such as underwater drones, smart sensors
and data acquisition systems, robotics optimize feeding practices, monitor
water quality and enhance disease detection, leading to healthier and more
productive aquatic environments. These innovations reduce environmental
impact by minimizing waste and resource usage while also improving
operational efciency. Additionally, advancements like underwater 3D
printing for customized structures and autonomous vehicles for precise
data collection drive further innovation. Biological models play a crucial
role by helping us understand complex interactions between organisms
and their environment, allowing for more efcient management strategies.
Automation revolutionizes aquaculture by optimizing feeding, monitoring
and harvesting, thus reducing labour and errors. As the demand for seafood
grows, the adoption of these technologies ensures competitiveness, resilience
and alignment with sustainability goals, positioning automation as the future
of aquaculture and addressing global food security challenges.
10. References
Albalawi, H.I., Khan, Z.N., Valle-Pérez, A.U., Kahin, K.M., Hountondji, M.,
Alwazani, H., Schmidt-Roach, S., Bilalis, P., Aranda, M., Duarte, C.M.,
Hauser, C.A., 2021. Sustainable and eco-friendly coral restoration
through 3D printing and fabrication. ACS Sustainable Chemistry &
Engineering 9(37), 12634-12645. DOI: https://doi.org/10.1021/
acssuschemeng.1c04148.
Al-Hussaini, K., Zainol, S.M., Ahmed, R.B., Daud, S., 2018. IoT monitoring
and automation data acquisition for recirculating aquaculture system
using fog computing. J. Comput. Hardw. Eng. 1(1), 1-12. DOI: https://
doi.org/10.63019/jche.v1i2.610.
Daoliang, L.I., Chang, L.I.U., 2020. Recent advances and future outlook
for articial intelligence in aquaculture. Smart Agriculture 2(3), 1. DOI:
https://doi.org/10.12133/j.smartag.2020.2.3.202004-SA007.
Karningsih, P.D., Kusumawardani, R., Syahroni, N., Mulyadi, Y., Saad,
M.S.B.M., 2021, February. Automated sh feeding system for an
offshore aquaculture unit. In: IOP Conference Series: Materials Science
and Engineering 1072(1), 012073. IOP Publishing. DOI: https://doi.
org/10.1088/1757-899X/1072/1/012073.
Kassem, T., Shahrour, I., El Khattabi, J., Raslan, A., 2021. Smart and
sustainable aquaculture farms. Sustainability 13(19), 10685. DOI:
https://doi.org/10.3390/su131910685.
Kruusmaa, M., Gkliva, R., Tuhtan, J.A., Tuvikene, A., Alfredsen, J.A., 2020.
Salmon behavioural response to robots in an aquaculture sea cage.
Royal Society Open Science 7(3), 191220. DOI: https://doi.org/10.1098/
rsos.191220.
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

39
Lee, P.G., 1995. A review of automated control systems for aquaculture
and design criteria for their implementation. Aquacultural Engineering
14(3), 205-227. DOI: https://doi.org/10.1016/0144-8609(94)00002-I.
Li, X., Ju, P., Zhao, S., Zhang, H., Zhao, J., 2024. Research idea of underwater
autonomous operating robot based on marine industry of Shandong
Province. Automation and Machine Learning 5(1), 1-6. DOI: https://
dx.doi.org/10.23977/autml.2024.050101.
Luna, F.D.V.B., de la Rosa Aguilar, E., Naranjo, J.S., Jagüey, J.G., 2016.
Robotic system for automation of water quality monitoring and feeding
in aquaculture shadehouse. IEEE Transactions on Systems, Man and
Cybernetics: Systems 47(7), 1575-1589. DOI: https://doi.org/10.1109/
TSMC.2016.2635649.
Pratiwy, F.M., Cahya, M.D., Andriani, Y., 2022. Digitization of aquaculture:
A review. International Journal of Fisheries and Aquatic Studies 10(1),
18-22. DOI: https://doi.org/10.22271/sh.2022.v10.i1a.2623.
Saha, S., Rajib, R.H., Kabir, S., 2018. IoT based automated sh farm
aquaculture monitoring system. In: 2018 International Conference on
Innovations in Science, Engineering and Technology (ICISET) (201-206).
IEEE. DOI: https://doi.org/10.1109/ICISET.2018.8745543.
Sasikumar, R., Lourdu Lincy, L., Sathyan, A., Chellapandi, P., 2024. Design,
development and deployment of a sensor-based aquaculture automation
system. Aquaculture International 32, 6431-6447. DOI: https://doi.
org/10.1007/s10499-024-01472-w.
Simbeye, D.S., Yang, S.F., 2014. Water quality monitoring and control for
aquaculture based on wireless sensor networks. Journal of Networks
9(4), 840-849. DOI: https://doi.org/10.4304/jnw.9.4.840-849.
Teja, K.B.R., Monika, M., Chandravathi, C., Kodali, P., 2020, July.
Smart monitoring system for pond management and automation in
aquaculture. In: 2020 International Conference on Communication
and Signal Processing (ICCSP). pp. 204-208. IEEE. DOI: https://doi.
org/10.1109/ICCSP48568.2020.9182187.
Vásquez-Quispesivana, W., Inga, M., Betalleluz-Pallardel, I., 2022. Articial
intelligence in aquaculture: basis, applications and future perspectives.
Scientia Agropecuaria 13(1), 79-96. DOI: https://dx.doi.org/10.17268/
sci.agropecu.2022.008.
Von Borstel, F.D., Suárez, J., de la Rosa, E., Gutiérrez, J., 2013. Feeding
and water monitoring robot in aquaculture greenhouse. Industrial
Robot: An International Journal 40(1), 10-19. DOI: https://doi.
org/10.1108/01439911311294219.
Wu, Y., Duan, Y., Wei, Y., An, D., Liu, J., 2022. Application of intelligent
and unmanned equipment in aquaculture: A review. Computers and
Electronics in Agriculture 199, 107201. DOI: https://doi.org/10.1016/j.
compag.2022.107201.
Yongqiang, C.H.E.N., Shaofang, L.I., Hongmei, L., Pin, T., Yilin, C.H.E.N.,
2019. Application of intelligent technology in animal husbandry and
aquaculture industry. In: 2019 14th International Conference on
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow

40
Computer Science & Education (ICCSE). pp. 335-339. IEEE. DOI: https://
doi.org/10.1109/ICCSE.2019.8845527.
Zhao, S., Zhang, S., Liu, J., Wang, H., Zhu, J., Li, D., Zhao, R., 2021.
Application of machine learning in intelligent sh aquaculture: A
review. Aquaculture 540, 736724. DOI: https://doi.org/10.1016/j.
aquaculture.2021.736724.
Fish, Tech and Future: The Role of Automation and Digital Tools for Sustainable Tomorrow