Deleted Journal,
Год журнала:
2025,
Номер
14, С. 85 - 98
Опубликована: Апрель 4, 2025
Lagoons
have
a
great
importance
for
society,
and
activities
such
as
fishing
or
tourism
are
essential
these
areas,
this
reason
it
is
important
to
monitoring
system
in
terms
of
water
quality.
The
central
axis
project
was
the
design
implementation
sensor
network
based
on
Internet
Things,
collecting
data
using
an
ESP32
Thingspeak
platform
visualization
storage.
Data
analyzed
MATLAB,
allowing
obtain
estimation
quality
index
Laguna
Jucutuma
indicating
average
rating
40,
well
Machine
Learning
techniques
models
with
error
margin
below
3%.
MATEC Web of Conferences,
Год журнала:
2024,
Номер
392, С. 01179 - 01179
Опубликована: Янв. 1, 2024
This
research
explores
the
integration
of
predictive
analytics
and
Internet
Things
(IoT)
to
transform
sustainable
urban
transportation
systems.
project
intends
examine
transformational
effect
on
mobility,
using
empirical
data
gathered
from
IoT
devices.
The
includes
information
vehicle
speed,
traffic
density,
air
quality
index
(AQI),
meteorological
conditions.
study
use
modeling
estimate
congestion,
volume.
allows
for
evaluation
prediction
accuracy
its
correspondence
with
actual
data.
reveals
a
direct
relationship
between
increased
density
decreased
while
unfavorable
weather
conditions
correspond
congestion.
Predictive
models
demonstrate
significant
in
forecasting
congestion
quality,
accurate
volume
poses
inherent
complications.
comparison
expected
real
results
demonstrates
dependability
AQI,
thereby
confirming
their
effectiveness.
interventions
led
by
25%
decrease
levels,
as
well
notable
12.7%
enhancement
despite
little
1.4%
rise
impact
highlights
efficacy
these
solutions,
showcasing
favorable
mitigating
promoting
environmental
sustainability.
Ultimately,
this
emphasizes
that
may
have
improving
transportation,
enabling
more
intelligent
decision-making,
creating
environments
driven
data-driven
insights
proactive
actions.
Water,
Год журнала:
2024,
Номер
16(24), С. 3616 - 3616
Опубликована: Дек. 15, 2024
Surface
waterbodies
are
heavily
exposed
to
pollutants
caused
by
natural
disasters
and
human
activities.
Empowering
sensor
technologies
in
water
quality
monitoring,
sufficient
measurements
have
become
available
develop
machine
learning
(ML)
models.
Numerous
ML
models
quickly
been
adopted
predict
indicators
various
surface
waterbodies.
This
paper
reviews
78
recent
articles
from
2022
October
2024,
categorizing
utilizing
into
three
groups:
Point-to-Point
(P2P),
which
estimates
the
current
target
value
based
on
other
at
same
time
point;
Sequence-to-Point
(S2P),
utilizes
previous
series
data
one
point
ahead;
Sequence-to-Sequence
(S2S),
uses
forecast
sequential
values
future.
The
used
each
group
classified
compared
according
indicators,
availability,
model
performance.
Widely
strategies
for
improving
performance,
including
feature
engineering,
hyperparameter
tuning,
transfer
learning,
recognized
described
enhance
effectiveness.
interpretability
limitations
of
applications
discussed.
review
provides
a
perspective
emerging
Heliyon,
Год журнала:
2025,
Номер
11(3), С. e42404 - e42404
Опубликована: Фев. 1, 2025
This
study
presents
a
semi-automated
approach
for
assessing
water
quality
in
the
Sundarbans,
critical
and
vulnerable
ecosystem,
using
machine
learning
(ML)
models
integrated
with
field
remotely-sensed
data.
Key
parameters-Sea
Surface
Temperature
(SST),
Total
Suspended
Solids
(TSS),
Turbidity,
Salinity,
pH-were
predicted
through
ML
algorithms
interpolated
Empirical
Bayesian
Kriging
(EBK)
model
ArcGIS
Pro.
The
predictive
framework
leverages
Google
Earth
Engine
(GEE)
AutoML,
utilizing
deep
libraries
to
create
dynamic,
adaptive
that
enhance
prediction
accuracy.
Comparative
analyses
showed
ML-based
effectively
captured
spatial
temporal
variations,
aligning
closely
measurements.
integration
provides
more
efficient
alternative
traditional
methods,
which
are
resource-intensive
less
practical
large-scale,
remote
areas.
Our
findings
demonstrate
this
technique
is
valuable
tool
continuous
monitoring,
particularly
ecologically
sensitive
areas
limited
accessibility.
also
offers
significant
applications
climate
resilience
policy-making,
as
it
enables
timely
identification
of
deteriorating
trends
may
impact
biodiversity
ecosystem
health.
However,
acknowledges
limitations,
including
variability
data
availability
inherent
uncertainties
predictions
dynamic
systems.
Overall,
research
contributes
advancement
monitoring
techniques,
supporting
sustainable
environmental
management
practices
Sundarbans
against
emerging
challenges.
