Analysis of Marine Pollution using IOT

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 10 | Oct 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 307
Analysis of Marine Pollution Using IOT
Hemant.R.Somannavar1 and Dr. Umadevi R2
1Dept. of Master of Computer Applications, CMR University, Bangalore, India.
2Associate Professor, School of Science Studies, CMR University, Bangalore, India.
----------------------------------------------------------------------***-----------------------------------------------------------------------
Abstract - In today's modern era, Marine Pollution is the
most compelling problem that has been affecting all the
oceans throughout the decenniums. It has been influenced
by human movements such as the disposal of sludge, Oil
flow, agricultural wastes into the ocean, etc. without
disciplinary measures. The consequence of Oceanic
pollution is destruction and impacts Ocean Life, the
environment, and finally Humans. IoT in the modern world
have played an important role in solving the critical
problem of marine pollution detection and prevention. By
integrating IoT technologies into marine pollution
monitoring, several sensors, devices, and data analytics
systems work together to improve our ability to detect,
monitor, and respond to pollution events. Then, we propose
an IoT system called 'SmartComputingSensor' using
technical detectors and intelligent computing tools,
specifically designed for onsite observation of microplastics
in natural submarine surroundings. Controlling marine
pollution needs carrying out various methods, activities,
and certain measures. Primarily, we must reduce the usage
of plastic as it threatens marine life. Through certain
management techniques, the government ensures that
proper waste disposal facilities are available. Next, Clean-
up measures are essential. By clearing marine debris such
as plastic covers, nets for fishing, and other remains there
will be a decrease in pollutants. Various policy measures
play a vital role in preventing and controlling marine
pollution.
Key Words: Marine Pollution, Internet-of-Things,
sensors, detection, control, microplastics, IOT Smart
Buoy
1. Introduction
Oceanic pollution is a blend of chemicals and residuals,
the utmost of which appear on land and are washed down
or thrown into the ocean along with the increasing threat
of marine pollution caused by disposable plastics, like
bottles, straws, plastic bags, and packaging materials. The
ecology, the health of all living things, and the global
economic system are all adversely affected by this
pollution. Marine pollution exploration has been
conducted for over 20 years.
Marine pollution is a global issue in many ways. This
has implications for the world's ocean life, regardless of
the country's level of development. In addition, each
country has a say in certain parts of the situation [22]. Our
ocean is inundated with two categories of pollutants,
chemicals, and garbage. Chemical or nutrient
contamination is a problem for the environment, human
health, and business profitability. This type of pollution
occurs when lethal conditioning, particularly the use of
toxins on farms, causes chemicals to leak into aqueducts
that eventually flow into the ocean. Because of the
widespread usage of agricultural chemicals for different
applications, pesticide residues may present a main
source of pollution, which poses risks to human health,
animals, and plants. Fungicides are the category of
pesticides with the greatest potential risk to humans, as
approximately 90 percent of fungicides currently or in the
recent past have demonstrated carcinogenic effects in
animal studies [24].
The increased attention to chemicals analogous to
nitrogen and phosphorus in coastal swell encourages the
development of algal blooms, which can be toxic to
wildlife and dangerous to humans. With the increasing
reliance on plastics as everyday objects and the rapid
increase in the amount of plastics consumed, it is a serious
problem to consider the environmental impact of plastics
in their manufacturing and subsequent disposal. There are
various advantages of plastics similar as persistence and
objection to deterioration, which conversely affect the
environment [16]. One of the most commonly seen
pollutants in the sea is microplastics. The phrase
microplastics was coined in 2004 to characterize very
minuscule fragments of plastic contained within the
water's column and detritus at a depth of 50 meters.
Microplastic particles include microscopic-sized
manufactured plastics such as Scrubbers, or industrial
pellets. Microplastics consist of a very heterogeneous
collection of parts that differ in size, color, shape, specific
gravity, chemical constituents, and other attributes. Plastic
degradation processes are extremely slow, so
microplastics may remain in the aquatic ecosystem for a
very long time [13]. Microplastics have been practically
discovered everywhere in the open and closed seas,
including beaches, surface waters, water columns, and the
deep-sea floor [16].
Microplastics generally fall into two kinds: primary and
secondary.
Primary microplastic is the microplastic that the
manufacturer creates in a specific small size for a specific
function. Typically, what we've heard most about is

microbeads. These are microscopic plastic beads used to
exfoliate or scrub in face washes, cosmetics, and
toothpaste. Typically, polyethylene (polypropylene,
polyethylene terephthalate, or nylon) is used.
Microspheres, capsules, fibers, and granules, among
others, are instances of primary microplastics.
Secondary microplastic is microplastic that is liberated
into the environment when larger fragments of plastic
degrade over time. The plastic is shattered into smaller
fragments by environmental factors such as waves,
sunlight, and other physical stresses. Typically, it
originates from improperly managed refuse. Cosmetics,
personal care products, cleaning brushes, textiles, virgin
resin pellets, water and beverage receptacles, food
containers, and plastic bags are instances of secondary
microplastics. [6]
Numerous consequences of ocean pollution have direct
and indirect effects on marine life and humans. Here are
some of the most prevalent impacts on marine life.
Fish:
Recent NPCG studies indicate that mesopelagic fish
consume microplastics (fibers, fragments, and coatings).
Estuarine ecosystems and their inhabitants such as fish
include catfish, Ariidae (23% of examined individuals),
and estuarine drums, which live their entire lives in
estuaries are also susceptible to plastic pollution.
Sea Birds:
Numerous studies have addressed the consumption of
marine debris by seabirds. Microplastics and small plastic
particles have been segregated from birds as well as from
their cadavers, regurgitated samples, and feces. Nearly 50
species of Procellariiformes (fulmars, petrels,
shearwaters, albatrosses) that are known to feed
opportunistically at the surface of the ocean contained
microplastics in their intestines.
Marine Mammals:
It is valued that marine plastics contribute to the
mortality of over one hundred thousand marine mammals
annually. Plastic can impact marine life in numerous ways,
including entanglement, injury, ingestion, and hazardous
contamination. The primary determinant is the quantity of
plastic, which can negatively affect various species in
various ways and over varying timescales.
To date, only a single study has been published on
marine mammals' microplastic ingestion. In 2013, Bravo
Rebolledo et al. discovered microplastics in the stomachs
and intestines of harbor(common) seals (Phoca vitulina).
Other marine mammal species have not been observed
directly ingesting microplastics. Nonetheless, bulkier
plastic objects were discovered in the abdomens of several
cetaceans. It may also happen via filter feeding, inhalation
at the water-air interface, or trophic transmission from
prey. Baleen whales (Mysticetes) may unintentionally
catch microplastics as they strain water between their
baleen plates to catch planktonic creatures and small fish
(Nemoto, 1970). Additionally, oceanic mammals may be
exposed to microplastics through trophic transfer from
prey species. For instance, microplastics were found in the
feces of fur seals (Arctocephalus spp.), which are thought
to have started from lanternfish (Electrona subasperma).
Sea Turtles:
Although every sea turtle species consume
macroplastic, only one study has found plastic particles in
the stomachs of herbivorous green turtles (Chelonia
mydas). Depending on their dietary preferences, it is
highly probable that other sea turtle species also ingest
microplastics, either directly or indirectly. Carnivorous
turtles such as the loggerhead's (Caretta caretta) and the
Kemps ridley (Lepidochelys kempii) feed on crustaceans
and mussels that have consumed microplastics.
Microplastic Effect on Habitats:
Floating organisms inhabit the surfaces of
microplastics that are buoyant. Similarly, plastics provide
a habitat for bacterial colonization on the surface of water.
Microorganisms such as Bacillus bacteria and diatoms
have been detected on plastic objects found in the
Northern Pacific Gyre. Due to the reality that microplastics
increase substrate permeability and decrease thermal
diffusivity, they may have significant consequences for
marine life. This may affect processes that are
temperature-dependent. For instance, alterations in
incubation temperatures can influence the sex ratios of
sea turtle embryos. At 30 °C, an equal number of male
embryo and female embryo develop, whereas at 28 °C,
only male embryos develop.

Figure 1. Marine life interaction with microplastics
Changes in sediment temperature may also have an
impact on infaunal organisms by altering enzymatic and
any other physiological methods, feeding and
progression rates, locomotory velocities, reproduction,
and ultimately community dynamics.
In addition to the characteristics of each plastic
polymer, environmental factors such as ocean currents,
horizontal and vertical mixing, wind mixing, and biofilm
formation affect the spread of microplastics. [16]
1.1 Detection process/methods
Currently, laboratory-based methods [13] for
monitoring microplastics are extremely popular and
require traveling to various locations to obtain water
samples for further analysis. This approach can occupy a
considerable amount of time and other resources, and its
success rate is uncertain.
Very few tries have been conducted to monitor
microplastic debris in marine environments using
multimodal computer vision that integrates visual (VI),
infrared (IR), and ultraviolet (UV) spectral bands [21].
Here, I offer a smart administration system called
SmartComputingSensor (plastic monitoring using smart
sensors and intelligent computing). The
SmartComputingSensor system will be using an 'Internet
of Things (IoT)' architecture along with smart machine-
learning algorithms.
In this architecture, feature selection techniques that
combine growth algorithms can be used to effectively deal
with pollution material (objects) that are difficult to
localize, detect, and classify in a dynamic and perpetually
changing water environment.
1.2 Controlling Marine Pollution
Layer chromatography, gas chromatography, and high-
implementation liquid chromatography are some of the
most popular instrumental approaches utilized to address
challenging issue of marine pollution. However, if they are
being used, additional factors such as the necessity for
substance pre-treatment, cost, time, and analytical
complexity must also be taken into account. Chemometric
techniques, such as UNMIX and PMF (positive matrix
factorization), are alternatives to instrumental techniques.
Recommendations for plastic pollution reduction:
1)Encourage Use of Recyclable Plastics:
To reduce the usage of single-use plastics, use fewer
items like bags, water bottles, straws, cups, cutlery, and
takeout containers. Purchase reusable versions of these
items to persuade businesses to offer substitutes. Avoid
using single-use plastics that aren't needed and encourage
businesses to offer substitutes. You might decrease your
everyday impact on the environment by doing this.
2)Promote laws that reduce the use of plastics and waste:
To combat ocean plastic pollution, legislation must be
introduced to reduce plastic production, improve waste
management, and make plastic producers accountable.
Support local, national, and international legislation to
address plastic pollution. The 2021 Plastic-Pollution
Break-Free Act in the US and state-level initiatives to
introduce extended producer responsibility (EPR)
legislation make plastic producers and distributors liable
for their products and packing. A global plastics treaty and
legislation limiting Individual use of plastic items, such as
bags and foodware, have been successful in reducing
pollution.
3)Responsible Recycling:
Recycle single-use plastics because just 9% of plastic is
recycled globally. Recycling helps to keep plastic out of the
water and reduces the creation of new plastic. Consult
Earth911's recycling directory for a list of nearby
recycling facilities and details on whether they accept
specific types of plastic.

4)Participation in River and Marine Cleanup:
Join or lead beach or waterway clean-ups to help
reduce ocean plastic waste. This straightforward and
fruitful strategy includes gathering plastic debris on your
own or with companions, as well as participating in
regional groups or global activities like the Global Ocean
Cleanup or the International Coastal Cleanup.
5)Avoid using items that contain microbeads.:
Microbeads, tiny plastic particles, are a significant
source of ocean plastic pollution. They are found in face
cleansers, toothpaste, and bodywashes, entering oceans
and waterways through drainage systems. To avoid plastic
microbeads, check ingredient labels for "polyethylene"
and "polypropylene" in cosmetic products.
6)Promote awareness:
We can educate everyone about plastic pollution and
raise consciousnessby sharing information, organizing
screenings, or watching documentaries such as A Plastic
Ocean, Junk Island, Bag It, Addicted to Plastic, or Garbage
Island. In addition to IT technology, continued advanced
technologies include sensor use, better waste
management, and the creation of novel materials including
remote sensing, big data analytics, artificial intelligence,
and real-world simulations.
7) Help Organizations Fighting Plastic Pollution:
The Plastic Pollution Coalition, 5 Gyres, Algalita, and
the Plastic Soup Foundation are just a few of the charity
organizations that are helping to reduce ocean plastic
pollution. In order to address the growing issues, we can
join the Blue Habits Club, which is committed to taking
daily actions to support ocean health.
8) Through governmental initiatives, public education,
and regular use of primarily biodegradable materials.
2. Literature Review
The authors Usha Jain and Muzzammil Hussain, in
[14] examines the significance of real-time observing of
maritime homes and borders for nonmilitary operations,
boundary protection, and the conservation of marine
resources. It emphasizes the difficulties associated with
maritime surveillance, analogous to enormous abysms,
ever-changing surroundings, and the need for continuous
surveillance. The authors propose a security medium for
wireless sensor networks that focuses on sensor knot
configuration, communication protocols, and advanced
data recycling ways for trouble discovery. The system
employs anomaly discovery algorithms and data analytics
to identify implicit hazards and notify nonmilitary
authorities. The authors illuminate the benefits of WSN-
predicated surveillance for enhancing situational
awareness, preventing maritime hazards, and speeding up
response strategies.
The authors Arijit Khan and Lawrence Jenkins, in
[15] discusses the importance of preventing ocean
pollution and the negative impact of human activities on
marine ecosystems. It highlights the drawbacks of
conventional monitoring techniques and proposes the
adoption of Undersea Wireless Sensor Networks as a
practical approach. The network consists of strategically
placed underwater sensor nodes gathering environmental
data, such as water quality, temperature, salinity, and
pollutants. The authors emphasize the significance of real-
time data collection and observation, as well as a pollution
detection and alarm system integrated into Undersea
Wireless Sensor Networks. Data visualization and
decision-support tools are crucial for understanding
pollution trends and identifying hotspot areas.
The authors Han et al., in [12] discusses the
importance of routing techniques in aquatic wireless
sensor networks, addressing challenges like restricted
bandwidth, long propagation delay, and challenging
channel necessities. It also discusses the challenges of
routing data in the constantly changing aquatic
environment, node mobility, limited communication
range, energy limitations, and network connectivity
during node failures. The authors classify routing rules
into flat-based, location-based, and hierarchical-based
categories, evaluating their effectiveness through
simulations and comparisons. The authors emphasize the
need for selecting suitable routing strategies that align
with specific application needs and underwater
environment characteristics.
In order to assure effective data gathering, the authors
Nasrin et al. in [18] emphasizes the relevance of spotting
anomalies in aquatic wireless sensor networks. Due to
noise, a large propagation delay, and a limited bandwidth,
anomaly detection in underwater situations is challenging.
To precisely identify abnormalities, the authors describe a
novel method that combines statistical analysis and
machine learning methods. Using labeled data, the model
is taught to recognize typical behavior conditions and spot
irregularities. The authors examine real-world aquatic
sensor data and contrast it with methods currently in use
to evaluate the efficacy of their suggested anomaly
discovery method.
In [11] by Gkikopouli et al., the Undersea Sensor
Network is crucial for marine monitoring and exploration,
but it faces challenges such as restricted bandwidth,
propagation delay, and severe underwater conditions.
Designing aquatic sensor nodes is essential, and strong,
waterproof enclosures are essential. Communication
techniques include acoustic and hybrid methods, and
energy-saving tactics like duty cycling and adaptive power
control are discussed. Localization and placement

techniques are crucial for tracking underwater sensor
nodes, and solutions like ranging and trilateration are
suggested. The survey investigates data collection and
routing techniques to reduce transmission and prolong
the network's lifespan. Overall, this research paper is
valuable for researchers, engineers, and practitioners in
the field of aquatic wireless sensor networks, contributing
to the enhancement of aquatic exploration and monitoring
capabilities.
The authors Xu et al., in [27] highlights the use of
Wireless sensor-network in marine systems and the
importance of managing the marine environment and
protecting ecosystems. It explores methods of collecting
data, assessing water quality standards, studying marine
pollution, and observing marine biodiversity. Focusing on
acoustic communication and state-of-art surface
propagation pathways, this article reviews sensor node
design, deployment, message rules, and data transmission
strategies for underwater surveillance. Wireless sensor
networks may be deployed to improve marine research
and data collection for mission-critical marine protection
and operational tasks
In [9] by Fattah et al., the significance of aquatic
wireless sensor networks in a number of fields, such as
environmental monitoring, marine exploration, and
disaster avoidance, is highlighted in this research. It deals
with issues like long propagation delays, bandwidth
restrictions, and harsh underwater environments. Aquatic
wireless sensor network components and processes are
categorized by the taxonomy, and more recent
developments include energy-efficient algorithms,
localisation strategies, and flexible whipping schemes. In
order to optimize aquatic wireless sensor networks in
realistic scenarios, the authors underline both the
advantages and difficulties of these novel strategies. They
also stress the need for continued study.
The authors Zhang et al., in [28] explain the
significance of maritime research and pollution
monitoring is emphasized in this paper, along with the
difficulties in obtaining current data from a variety of
marine fields. WSNs, or wireless sensor networks, have
benefits like real-time data collecting, adaptation to
various environmental conditions, and economical
management. Beacon clustering improves network
coverage while using less energy. Recycling ideas provide
continual maritime environment observation while
ensuring network sustainability and long-term usability.
WSNs are crucial for managing maritime resources,
protecting the environment, enhancing our understanding
of the ocean, and reducing pollution.
The authors Ramamoorthy and Loganathan in [20]
for secured Data Transmission in Military Applications
using video steganography concept, security level
improved by 24 percent.
The authors Schnurr et al., in [23] emphasizes the
rising danger of marine contamination brought on by
individual-use plastics including bottles, straws, bags, and
packaging supplies. It draws attention to the negative
ecological effects of individual-use plastics on marine life,
such as entanglement, ingestion, and habitat destruction.
For plastic pollution to be reduced, behavioral change and
public awareness are essential. To stop individual-use
plastics from polluting the ocean, the authors stress the
value of international agreements, collaborations, and
concerted action.
The authors Xanthos and Walker, in [26] discusses
plastic marine pollution, highlighting the negative effects
of disposable plastics on aquatic ecosystems, wildlife, and
humans well-being. It analyzes successful policy
implementations, including bans, taxes, levies, and
regulations, and evaluates their effectiveness in reducing
plastic bag waste. It also discusses microbeads in cosmetic
products and their contribution to marine pollution,
highlighting the need for coordinated international
standards. The paper also discusses international
agreements and initiatives like the Basel Convention,
Clean Seas Programme, and Stockholm Convention,
fostering cooperation among nations to battle plastic
pollution. Challenges include resistance from the industry,
inconsistent enforcement mechanisms, and improved
waste minimization and recycling infrastructure. The
paper emphasizes the importance of global cooperation
and coordinated action to combat plastic marine pollution
from single-use plastics.
3. Proposed Method
3.1 SmartComputingSensor Architecture and Logic for
Microplastics Detection
SmartComputingSensor will incorporate multifaceted
data fusion, intelligent computation strategies, and a
control system to detect the microplastics in the ocean.
Data fusion will employ images in the visible, infrared, and
ultraviolet spectral bands as well as a variety of particular
sensors to facilitate the measurement of various physical
and chemical attributes in dynamic environments. In
addition, the proposed design must be highly scalable and
expandable for massive geographical areas.
Propagation and Screening Methods:
The following are two potential design alternatives for the
system:
In-situ observation and detection: This strategy aims to
reduce transmission costs by detecting and analyzing
signals on-site. This method can be very useful when
deploying a huge quantity of sensors over a large
geographical area. In this case, the limitation is the need to
connect and deploy potent processing computer hardware

at every location. In-situ sensing and processing are now
more feasible with recent developments.
Monitoring in-place and server-based detection: In this
implementation, signal processing is performed on a
server located remotely from the measuring instruments.
Advantages include a comparatively simple architecture
and minimal signal processing on-site. In the case of high-
volume signals, the greatest drawback of this method can
be a prohibitively expensive transmission fee.
Finally, the implementation of such hardware is rather
inexpensive and readily accessible.
SMARTCOMPUTINGSENSOR ARCHITECTURE
The development of the SmartComputingSensor
system can benefit from a number of structural and
computational ideas. The two most complementary
strategies that can be used are presented below.
Portable Sensors with Internet of Things (IoT): Wireless
sensors are efficient of being equipped with various types
of sensors to observe temperature, salinity, etc or two-
dimensional (images) variables. Batteries and wireless
transceivers power these sensors so electrical cables
involved. IoT and wireless sensors are a significant part of
the solution to an issue like marine small particle
monitoring.
Multimodal camera-based detection techniques: In
situations with limited illumination and other visual
restrictions, a single camera may not be sufficient.
Additional modalities, such as infrared and ultraviolet,
enhance the detection process by expanding the available
spectrum. Several computational techniques, such as data
fusion and learning classifiers, can be utilized to address
data processing problems.
3.2 IoT-Enabled Smart Buoys for Controlling Marine
Pollution
IoT-Enabled Smart Buoys are sophisticated marine
monitoring systems that utilize the IoT (Internet of
Things) to collect, transmit, and analyze environmental
data from oceans, rivers, and other water sources. These
buoys are outfitted with an assortment of sensors and
communication devices that provide real-time data on
water quality, weather conditions, pollution levels, and
other pertinent parameters. Here is a more
comprehensive explanation of how IoT-enabled Smart
Buoys function and their benefits:
Functional Components:
Sensors: The sensors on smart vessels include pH
sensors, temperature sensors, dissolved oxygen sensors,
and turbidity sensors, among others. These sensors
perpetually collect water quality-related data.
Communication Devices: These vessels are equipped
with communication devices such as cell modules, satellite
modems, and radio transceivers. These devices allow
vessels to transmit data to remote servers or control
centers.
Data Processing: The collected data is sent to the cloud
or a centralized server for processing, analysis, and
visualization. Using sophisticated data analytics
techniques and machine learning methods, it is possible to
extract insights from the data.
Real-time Monitoring: Researchers, scientists, and
environmental authorities have remote, real-time access
to the data. This enables the monitoring of real-time
changes in water quality, pollution levels, and other
parameters.
Advantages and Applications
Early Pollution Detection: Intelligent buoys can detect
pollution incidents such as oil-spills, chemical leakage, and
excessive nutrient levels. Early detection allows for
prompt response and mitigation measures.
Environmental Monitoring: These buoys provide a wealth
of information for assessing the condition of ocean and
marine ecosystems. They contribute to the comprehension
of the effects of climate change, pollution, and other
factors on marine life.
Research and Analysis: The collected data can be used for
researching long-term trends, predicting the behavior of
marine ecosystems, and formulating effective
conservation strategies.
Emergency Response: In the event of natural calamities
such as tsunamis or hurricanes, intelligent buoys can
provide vital information for assessing the situation and
predicting potential impacts on coastal areas.
Data-Driven Decision Making: Smart buoy data enables
authorities to make informed judgments regarding marine
resource management, pollution control, and emergency
response.
Public Awareness: Sharing visualizations and reports
derived from the data collected by smart buoys can
increase public awareness of marine environmental
concerns.
4. Experimental Setup
4.1 MDCS System for detection of marine pollution
The meaning of the acronym MDCS is " Multidimensional
Data Capture System."

It provides the design and implementation of a
multifaceted surveillance system at both the software and
hardware levels. In this architecture, spectral cameras, as
well as illuminators, are utilized. These cameras are linked
to computer components via USB connections. This
computer functions as a server and is responsible for all
data acquisition software implementation. Matlab
software libraries are utilized for the evaluation of data.
The primary component of the HMDAS system (see Fig. 2)
is a multi-camera device that includes the microscope
camera(s). Cameras are equipped with the proper
illuminators and lenses. These cameras communicate with
the controller subsystem through standard I/O
communication ports (USB, Wi-Fi, etc.).
Figure 2. Microscope-relied monitoring node integrated
into a multi-camera unit.
The MDCS architecture employs a layered approach for
various data processing operations.
The architecture's topmost stratum is responsible for data
acquisition via multiple cameras and/or wireless sensors.
In contrast, the subsequent layers are implemented with
feature extraction, optimization, and classification
techniques. The base layer is a repository that stores data
in raw, feature, and result formats. A suitable user
interface will be created to conclude this adoption
procedure. Thus, for microplastics, a complete system
with data surveillance can be ensured.
IoT Utilization
An Internet of Things (IoT) strategy was created in
order to provide a geographically extensive detection
system. multiple MDCS systems where each unit will be
outfitted with a 5G mobile gateway to establish
connectivity with a cloud-based application server . In this
study, we also employ a similar strategy for data
collection, which consists of a cluster of MDCS data
acquisition subsystems. This method assures the
scalability of the monitoring solution for microplastics in
aquatic systems.
SmartComputingSensor's IoT-based architecture
consists of four main software and hardware layers (Fig.
3). The bottom layer facilitates the deployment of MDCS
sensory nodes in the field. The communication layer
facilitates the transmission of data to the layers above.
This layer generates a vast quantity of data that is
converted into feature form and then processed using
intelligent computation techniques to detect the presence
of microplastic particles. The topmost layer employs
presentation and analytic capabilities to visualize the
results of the discovery. The architecture seeks to provide
a fullproof solution by addressing security, load-balancing,
and fault-recovery mechanisms. The proposed IoT
construction may be a viable method for detecting the
presence of microplastics in water columns.
Figure 3. SmartComputingSensor's layered design is
built on the Internet of Things.
Detection Results:
Location Type/Equipment
Used
Amount(±SD)
Pacific Ocean
Heugnam Beach,
South Korea
PS spheres
Fragments
Pellets
874 (±377)m−2
25 (±10) m−2
41 (±19) m−2
Coastal beaches,
New Zealand
Pellets >1,000 m−1

Easter Island, Chile Fragments and pellets
1–10 mm
805 m−2
Atlantic Ocean
North Atlantic Continuous plankton
recorder (CPR)
1960–1980: 0.01
m−3
1980–2000: 0.04
m−3
Caribbean Neuston net 60.6–180 km−2
South Atlantic Bight Neuston net Mean weight:
0.03–0.08 mg m−2
North Sea
Harbor sediment,
Sweden
Fragments 20 and 50 kg−1
Arabian Sea and Indian Ocean
Mumbai, India Fragments 41.85 % of total
plastics
Coastline,
Singapore
Fibres, grains,
fragments
36.8 ± 23.6 kg−1
Gulf of Oman Pellets >50–200 m−2
Arabian Gulf Pellets >50–80,000 m−2
Table 1: Mean microplastic abundance (±SD) in
sediments from various seas and oceans
Table 2: Interactions of Microplastics with Marine
Organisms
Species Numb
er
Studi
ed
Perce
ntage
with
plasti
cs(%)
Mean
number
of
particle
s per
individu
al(±SD)
Type and
Size
ingested(
mm)
Location
Green
turtle
(Chelonia
mydas)
24 / Total:
11
pellets
<5 mm Rio
Grande do
Sul, Brazil
Longnosed
lancetfish
(Alepisauru
s ferox)
144 24 2.7
(±2.0)
68.3
(±91.1)
North
Pacific
Pearly
lanternfish
(Myctophu
m
nitidulum)
25 16 1.5 Longest
dimensio
n 5.46
North
Pacific
Cat
fish(Cathor
ops spp.)
60 33.3 0.55 1-4 Goiana
estuary,
Brazil
Brown
shrimp(Cra
ngon
crangon)
110 / 11.5
fibres
per 10g
shrimp
95%
fibres,
5% films
300-1000
µm
Belgium

4.2 The Architecture of IoT-Enabled Smart Buoys
Figure 4. The IoT- Enabled Smart Buoys architecture.
IoT- Enabled Smart Buoys are designed with an
armature that facilitates the collection, transmission, and
analysis of environmental data from marine and submarine
surroundings. These buoys use Internet of effects( IoT)
technology to construct a networked system that provides
real-time data on water quality, rainfall conditions, and
pollution situations, among other variables. The
architecture is classified as:
Sensors and Information Gathering:
Sensor Array: The detectors on smart vessels include
pH detectors, temperature detectors, turbidity detectors,
saltness detectors, and dissolved oxygen detectors, among
others. varied environmental parameters are measured by
these detectors.
Data Collection: Detectors measure the physical and
chemical characteristics of the ambient water in a nonstop
manner. This information is also digitized and made
transmission-ready.
Processing Unit
Microcontroller/Processor: A microcontroller or
processor is embedded in the container to reuse detector
data and prepare it for transmission. It can also perform
the necessary data pre-processing and aggregation.
Communication:
Communication Modules: Communication modules
similar to cellular modems, satellite transceivers, and radio
communication bias are installed in intelligent buoys.
These modules allow vessels to connect to remote waiters
or command centers.
Data Transmission: Through the communication modules,
reused data is transmitted to centralized waiters or all
platforms.
Cloud Platform:
Cloud Servers: Multiple vessels transmit their data to
cloud servers for storage and analysis. The scalability of
cloud platforms is required to manage large volumes of
data from numerous vessels.
Data Processing: The collected cloud-based data can be
analyzed using sophisticated techniques and algorithms. It
is possible to train machine learning models to identify
patterns and anomalies in data.
Data Analysis and Visualization:
Data Analytics: Data analysis can yield insights
regarding water quality, pollution levels, and weather
patterns, among other topics. Trends and correlations can
be uncovered with the aid of statistical analysis and
machine learning algorithms.
Visualization: Through interfaces, graphs, and maps,
data insights can be visualized. This makes it easy for
researchers, scientists, and stakeholders to comprehend
the information.
Remote Monitoring and Control:
Web and Mobile Interfaces: Users can remotely access
collected data via web and mobile applications. They are
able to monitor real-time data, observe historical trends,
and receive alerts for important events.
Control and Commands: Some intelligent vessels may be
able to receive remote commands. Adjustments to sensor
settings and communication frequency, for instance, can be
made via a centralized control interface.
Power Source:
Power Supply: Solar panels, batteries, or a combination of
both power smart vessels. To ensure continuous data
collection and transmission, efficient power management is
crucial.
Security and Data Privacy:
Encryption: Encryption protocols are used to safeguard
data transmission and storage from unauthorized access.
Authentication: Authentication mechanisms restrict system
access, ensuring that only authorized personnel can
interact with buoys and data.
IoT-Enabled Smart Buoys' architecture incorporates
sensors, communication technologies, cloud platforms,

data analytics, and visualization to create a comprehensive
marine monitoring system. This system improves our
knowledge of marine ecosystems, aides in pollution
control, and facilitates scientific research and decision-
making.
5. Conclusion
Microplastics have been discovered in practically all
marine habitats on Earth, and the consistency of the plastic,
ocean currents, and other surrounding factors all appear to
have substantial outcomes on how broadly they are
classified. Concerns about the interactions and potential
impacts of microplastics on aquatic life are raised by their
widespread distribution and accumulation. Here, a concept
for an IoT-based architecture, its justification, and an
introductory assessment of the classification of
microplastics are described. In order to show the system
proficiencies that are to be implemented in the problem
environment, the ideas of the Internet of Things and
multimodal computer vision are presented. The suggested
IoT-based system architecture can be constructed
extremely fast using commercial off-the-shelf and open-
source hardware and software components. Using the
explained MDCS data collection system, we can easily
monitor and find microplastics in coastal areas, rivers and
streams, coral reefs, and the deep sea. With the many
methods and approaches mentioned, we can tackle marine
pollution and by implementing the latest new technologies
we can stop the pollution of open oceans and water
surfaces with microplastics. Finally, the purpose of this
study project is to provide a comprehensive analysis of
how to lower marine pollution. It aims to support ongoing
efforts to preserve the integrity of our marine ecosystems
by studying their causes and impacts.
Reference
[1] Afonso-Olivares, Cristina, et al. “Analytical Tools
Employed to Determine Pharmaceutical Compounds in
Wastewaters After Application of Advanced Oxidation
Processes.” Environmental Science and Pollution Research,
vol. 23, no. 24, Springer Science and Business Media LLC,
Aug. 2016, pp. 24476–94. Crossref,
https://doi.org/10.1007/s11356-016-7325-6.
[2] Alam, Muhammad, and Elyes Hamida. “Wearable
Wireless Sensor Networks: Applications, Standards, and
Research Trends.” Emerging Communication Technologies
Based on Wireless Sensor Networks, CRC Press, Apr. 2016,
pp. 59–88. Crossref, https://doi.org/10.1201/b20085-6.
[3] Ansari, T. M., et al. “Heavy Metals in Marine Pollution
Perspective–A Mini Review.” Journal of Applied Sciences,
vol. 4, no. 1, Science Alert, Dec. 2003, pp. 1–20. Crossref,
https://doi.org/10.3923/jas.2004.1.20.
[4] Armbrust, Michael, et al. “A View of Cloud Computing.”
Communications of the ACM, vol. 53, no. 4, Association for
Computing Machinery (ACM), Apr. 2010, pp. 50–58.
Crossref, https://doi.org/10.1145/1721654.1721672.
[5] Borowik, Grzegorz, et al., editors. “Computational
Intelligence and Efficiency in Engineering Systems.” Studies
in Computational Intelligence, Springer International
Publishing, 2015. Crossref, https://doi.org/10.1007/978-
3-319-15720-7.
[6] Chaczko, Zenon, et al. “Towards an IOT Based System
for Detection and Monitoring of Microplastics in Aquatic
Environments.” 2018 IEEE 22nd International Conference
on Intelligent Engineering Systems (INES), IEEE, June 2018.
Crossref, https://doi.org/10.1109/ines.2018.8523957.
[7] Clark, Robert Bernard, Chris Frid, and Martin Attrill.
Marine pollution. Vol. 4. Oxford: Clarendon press, 1997.
[8] DUBINSKY, ZVY, and NOGA STAMBLER. “Marine
Pollution and Coral Reefs.” Global Change Biology, vol. 2,
no. 6, Wiley, Dec. 1996, pp. 511–26. Crossref,
https://doi.org/10.1111/j.1365-2486.1996.tb00064.x.
[9] Fattah, Salmah, et al. “A Survey on Underwater
Wireless Sensor Networks: Requirements, Taxonomy,
Recent Advances, and Open Research Challenges.” Sensors,
vol. 20, no. 18, MDPI AG, Sept. 2020, p. 5393. Crossref,
https://doi.org/10.3390/s20185393.
[10] Galgani, Francois, et al. “Marine Pollution: Let Us Not
Forget Beach Sand.” Environmental Sciences Europe, vol.
23, no. 1, Springer Science and Business Media LLC, Dec.
2011. Crossref, https://doi.org/10.1186/2190-4715-23-
40.
[11] Gkikopouli, A., et al. “A Survey on Underwater
Wireless Sensor Networks and Applications.” 2012 20th
Mediterranean Conference on Control & Automation
(MED), IEEE, July 2012. Crossref,
https://doi.org/10.1109/med.2012.6265793.
[12] Han, Guangjie, et al. “Routing Protocols for
Underwater Wireless Sensor Networks.” IEEE
Communications Magazine, vol. 53, no. 11, Institute of
Electrical and Electronics Engineers (IEEE), Nov. 2015, pp.
72–78.Crossref,
https://doi.org/10.1109/mcom.2015.7321974.
[13] Hidalgo-Ruz, Valeria, et al. “Microplastics in the
Marine Environment: A Review of the Methods Used for
Identification and Quantification.” Environmental Science
& Technology, vol. 46, no. 6, American Chemical Society
(ACS), Mar. 2012, pp. 3060–75. Crossref,
https://doi.org/10.1021/es2031505.

[14] Jain, Usha, and Muzzammil Hussain. “Security
Mechanism for Maritime Territory and Frontier
Surveillance in Naval Operations Using Wireless Sensor
Networks.” Concurrency and Computation: Practice and
Experience, vol. 33, no. 17, Wiley, Apr. 2021. Crossref,
https://doi.org/10.1002/cpe.6300.
[15] Khan, Arijit, and Lawrence Jenkins. “Undersea
Wireless Sensor Network for Ocean Pollution Prevention.”
2008 3rd International Conference on Communication
Systems Software and Middleware and Workshops
(COMSWARE ’08), IEEE, Jan. 2008. Crossref,
https://doi.org/10.1109/comswa.2008.4554369.
[16] Lusher, Amy. “Microplastics in the Marine
Environment: Distribution, Interactions and Effects.”
Marine Anthropogenic Litter, Springer International
Publishing, 2015, pp. 245–307. Crossref,
https://doi.org/10.1007/978-3-319-16510-3_10.
[17] Mearns, Alan J., et al. “Effects of Pollution on Marine
Organisms.” Water Environment Research, vol.89, no.10,
Wiley, Oct. 2017, pp.1704–98.
Crossref,https://doi.org/10.2175/106143017x15023776
270647.
[18] Nasrin, Fatema, et al. “Anomaly Detection Method for
Sensor Network in Under Water Environment.” 2021
International Conference on Information and
Communication Technology for Sustainable Development
(ICICT4SD), IEEE, Feb. 2021.Crossref,
https://doi.org/10.1109/icict4sd50815.2021.9396943.
[19] Nuseibeh, B. “Weaving Together Requirements and
Architectures.” Computer, vol. 34, no. 3, Institute of
Electrical and Electronics Engineers (IEEE), Mar.
2001,pp.115–19. Crossref,
https://doi.org/10.1109/2.910904.
[20] Ramamoorthy, Umadevi, and Aruna Loganathan.
“Analysis of Video Steganography in Military Applications
on Cloud.” The International Arab Journal of Information
Technology, vol. 19, no. 6, Zarqa University, 2022.
Crossref, https://doi.org/10.34028/iajit/19/6/7.
[21] Ritchie, Jerry C., et al. “Remote Sensing Techniques to
Assess Water Quality.” Photogrammetric Engineering &
Remote Sensing, vol. 69, no. 6, American Society for
Photogrammetry and Remote Sensing, June 2003, pp. 695–
704. Crossref, https://doi.org/10.14358/pers.69.6.695.
[22] Schachter, Oscar, and Daniel Serwer. “Marine
Pollution Problems and Remedies.” American Journal of
International Law, vol. 65, no. 1, Cambridge UP (CUP), Jan.
1971, pp. 84–111. Crossref,
https://doi.org/10.2307/2199296.
[23] Schnurr, Riley E. J., et al. “Reducing Marine Pollution
From Single-use Plastics (SUPs): A Review.” Marine
Pollution Bulletin, vol. 137, Elsevier BV, Dec. 2018, pp.
157–71. Crossref,
https://doi.org/10.1016/j.marpolbul.2018.10.001.
[24] Suárez-Araujo, Carmen Paz, et al. “Supervised Neural
Computing Solutions for Fluorescence Identification of
Benzimidazole Fungicides. Data and Decision Fusion
Strategies.” Environmental Science and Pollution
Research, vol. 23, no. 24, Springer Science and Business
Media LLC, July 2016, pp. 24547–59. Crossref,
https://doi.org/10.1007/s11356-016-7129-8.
[25] Valentukevičienė, Marina, and Evelina Brannvall.
“Marine Pollution: An Overview.” Geologija, vol. 50, no. 1,
Portico, Jan. 2008, pp. 17–23. Crossref,
https://doi.org/10.2478/v10056-008-0002-9.
[26] Xanthos, Dirk, and Tony R. Walker. “International
Policies to Reduce Plastic Marine Pollution From Single-
use Plastics (Plastic Bags and Microbeads): A Review.”
Marine Pollution Bulletin, vol. 118, no. 1–2, Elsevier BV,
May 2017, pp.17–26.Crossref,
https://doi.org/10.1016/j.marpolbul.2017.02.048.
[27] Xu, Guobao, et al. “Applications of Wireless Sensor
Networks in Marine Environment Monitoring: A Survey.”
Sensors, vol. 14, no. 9, MDPI AG, Sept. 2014, pp. 16932–54.
Crossref, https://doi.org/10.3390/s140916932.
[28] Zhang, et al. “Marine Observation Beacon Clustering
and Recycling Technology Based on Wireless Sensor
Networks.” Sensors, vol. 19, no. 17, MDPI AG, Aug. 2019, p.
3726. Crossref, https://doi.org/10.3390/s19173726.
[29] Zubir Din . (1996).“Coastal marine pollution and
toxicology : overview of current research and future
needs.” First national conference on environmental health
research - state of the art in Malaysia today : proceedings :
Vol II, (p. 599). Malaysia: Ministry of Health Malaysia.

Analysis of Marine Pollution using IOT

More Related Content

Similar to Analysis of Marine Pollution using IOT (20)

More from IRJET Journal (20)

Recently uploaded (20)

Analysis of Marine Pollution using IOT