Intelligent Decision Technologies,
Год журнала:
2024,
Номер
unknown, С. 1 - 10
Опубликована: Сен. 10, 2024
Air
pollution
has
become
an
international
calamity,
a
problem
for
human
health
and
the
environment.
The
ability
to
predict
air
quality
becomes
crucial
task.
usual
approaches
assessing
are
exhausted
when
extracting
complicated
non-linear
relationships
long-term
dependence
features
embedded
in
data.
Long-
short-term
memory,
recurrent
neural
network
family,
emerged
as
potent
tool
addressing
mentioned
issues,
so
computer-aided
technology
essential
aid
with
high
level
of
prediction
best-in-class
accuracy.
In
this
study,
we
investigated
classic
time-series
analysis
based
on
Improved
Long
memory
(ILSTM)
improve
performance
index
prediction.
predicted
AQI
value
25
days
lies
97.63%
Confidence
interval
zone
highly
adoptable
metrics
such
R-Square,
MSE,
RMSE,
MAE
values.
Journal of Advanced Computational Intelligence and Intelligent Informatics,
Год журнала:
2025,
Номер
29(1), С. 138 - 151
Опубликована: Янв. 19, 2025
Air
quality
issues
have
become
a
major
environmental
concern,
with
severe
air
pollution
significantly
reducing
and
posing
threats
to
human
health.
Accurate
prediction
is
crucial
for
preventing
individuals
from
suffering
the
detrimental
effects
of
pollution.
Recently,
deep
learning
methods
based
on
spatiotemporal
graph
neural
networks
(GNNs)
made
considerable
progress
in
modeling
temporal
spatial
dependencies
within
data
by
integrating
GNNs
sequential
models.
Unfortunately,
previous
work
often
treats
as
independent
components,
neglecting
intricate
interactions
between
them.
This
oversight
prevents
models
fully
exploiting
complex
data,
adversely
affecting
their
predictive
performance.
To
address
these
issues,
we
propose
general
interaction
framework
prediction.
bidirectional
data-driven
manner.
Furthermore,
designed
feature
extraction
module
dynamic
adversarial
adaptive
this
framework.
We
introduce
Spatial-Temporal
Interaction
Dynamic
Adversarial
Adaptive
Graph
Neural
Network,
capable
capturing
topology
among
sites
incorporating
competitive
optimization
concept
generative
networks.
Extensive
experiments
two
real-world
datasets
demonstrate
effectiveness
proposed
method,
outperforming
existing
baseline
Atmosphere,
Год журнала:
2025,
Номер
16(3), С. 292 - 292
Опубликована: Фев. 28, 2025
PM2.5
in
air
pollution
poses
a
significant
threat
to
public
health
and
the
ecological
environment.
There
is
an
urgent
need
develop
accurate
prediction
models
support
decision-making
reduce
risks.
This
review
comprehensively
explores
progress
of
concentration
prediction,
covering
bibliometric
trends,
time
series
data
characteristics,
deep
learning
applications,
future
development
directions.
article
obtained
on
2327
journal
articles
published
from
2014
2024
WOS
database.
Bibliometric
analysis
shows
that
research
output
growing
rapidly,
with
China
United
States
playing
leading
role,
recent
increasingly
focusing
data-driven
methods
such
as
learning.
Key
sources
include
ground
monitoring,
meteorological
observations,
remote
sensing,
socioeconomic
activity
data.
Deep
(including
CNN,
RNN,
LSTM,
Transformer)
perform
well
capturing
complex
temporal
dependencies.
With
its
self-attention
mechanism
parallel
processing
capabilities,
Transformer
particularly
outstanding
addressing
challenges
long
sequence
modeling.
Despite
these
advances,
integration,
model
interpretability,
computational
cost
remain.
Emerging
technologies
meta-learning,
graph
neural
networks,
multi-scale
modeling
offer
promising
solutions
while
integrating
into
real-world
applications
smart
city
systems
can
enhance
practical
impact.
provides
informative
guide
for
researchers
novices,
providing
understanding
cutting-edge
methods,
systematic
paths.
It
aims
promote
robust
efficient
contribute
global
management
protection
efforts.
