Journal of Environmental Management,
Journal Year:
2024,
Volume and Issue:
368, P. 122107 - 122107
Published: Aug. 9, 2024
In
China,
population
growth
and
aging
have
partially
negated
the
public
health
benefits
of
air
pollution
control
measures,
underscoring
ongoing
need
for
precise
PM
Environment International,
Journal Year:
2023,
Volume and Issue:
175, P. 107931 - 107931
Published: April 15, 2023
This
study
uses
machine
learning
(ML)
models
for
a
high-resolution
prediction
(0.1°×0.1°)
of
air
fine
particular
matter
(PM2.5)
concentration,
the
most
harmful
to
human
health,
from
meteorological
and
soil
data.
Iraq
was
considered
area
implement
method.
Different
lags
changing
patterns
four
European
Reanalysis
(ERA5)
variables,
rainfall,
mean
temperature,
wind
speed
relative
humidity,
one
parameter,
moisture,
were
used
select
suitable
set
predictors
using
non-greedy
algorithm
known
as
simulated
annealing
(SA).
The
selected
simulate
temporal
spatial
variability
PM2.5
concentration
over
during
early
summer
(May-July),
polluted
months,
three
advanced
ML
models,
extremely
randomized
trees
(ERT),
stochastic
gradient
descent
backpropagation
(SGD-BP)
long
short-term
memory
(LSTM)
integrated
with
Bayesian
optimizer.
distribution
annual
average
revealed
population
whole
is
exposed
pollution
level
above
standard
limit.
changes
in
temperature
moisture
humidity
month
before
can
predict
May-July.
Results
higher
performance
LSTM
normalized
root-mean-square
error
Kling-Gupta
efficiency
13.4%
0.89,
compared
16.02%
0.81
SDG-BP
17.9%
0.74
ERT.
could
also
reconstruct
observed
MapCurve
Cramer's
V
values
0.95
0.91,
0.9
0.86
SGD-BP
0.83
0.76
provided
methodology
forecasting
at
high
resolution
peak
months
freely
available
data,
which
be
replicated
other
regions
generating
maps.
Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(2), P. 358 - 358
Published: Jan. 6, 2023
Atmospheric
fine
particles
(PM2.5)
have
been
found
to
be
harmful
the
environment
and
human
health.
Recently,
remote
sensing
technology
machine
learning
models
used
monitor
PM2.5
concentrations.
Partial
dependence
plots
(PDP)
were
explore
meteorology
mechanisms
between
predictor
variables
concentration
in
“black
box”
models.
However,
there
are
two
key
shortcomings
original
PDP.
(1)
it
calculates
marginal
effect
of
feature(s)
on
predicted
outcome
a
model,
therefore
some
local
effects
might
hidden.
(2)
requires
that
for
which
partial
is
computed
not
correlated
with
other
features,
otherwise
estimated
feature
has
great
bias.
In
this
study,
PDP’s
analyzed.
Results
show
contradictory
correlation
temperature
can
given
by
Furthermore,
spatiotemporal
heterogeneity
PM2.5-AOD
relationship
cannot
displayed
well
The
drawbacks
PDP
make
unsuitable
exploring
large-area
effects.
To
resolve
above
issue,
multi-way
recommended,
characterize
how
concentrations
changed
temporal
spatial
variations
major
meteorological
factors
China.
Atmosphere,
Journal Year:
2025,
Volume and Issue:
16(3), P. 292 - 292
Published: Feb. 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.