Efficient ozone concentration trend prediction using ANN and K-means clustering
Earth Science Informatics,
Год журнала:
2025,
Номер
18(1)
Опубликована: Янв. 1, 2025
Язык: Английский
Deep Learning Calibration Model for PurpleAir PM2.5 Measurements: Comprehensive Investigation of the PurpleAir Network
Atmospheric Environment,
Год журнала:
2025,
Номер
unknown, С. 121118 - 121118
Опубликована: Фев. 1, 2025
Язык: Английский
Observing Lower‐Tropospheric Ozone Spatiotemporal Variability With Airborne Lidar and Surface Monitors in Houston, Texas
Journal of Geophysical Research Atmospheres,
Год журнала:
2025,
Номер
130(6)
Опубликована: Март 26, 2025
Abstract
Surface‐level
ozone
is
a
trace
gas
regulated
by
the
Environmental
Protection
Agency
as
its
oxidizing
properties
are
detrimental
to
air
quality,
impacting
human
and
environmental
health.
Satellite
observations
provide
spatially
continuous
intraurban
distributions,
potentially
filling
in
gaps
within
monitoring
networks.
However,
near‐surface
difficult
retrieve
from
columns
due
large
signal
stratosphere
lack
of
sensitivity
lower
troposphere
ultraviolet
wavelengths.
Airborne
lidar
measurements
profiles
present
opportunity
assess
vertical,
geospatial,
temporal
variability
tropospheric
(0–2
km)
subcolumn
products
for
quality
analyses.
This
study
uses
first
city‐wide
airborne‐lidar
collected
National
Aeronautics
Space
Administration
High‐Spectral
Resolution
Lidar‐2
instrument
over
Houston,
Texas
during
September
2021
Tracking
Aerosol
Convection
ExpeRiment–Air
Quality
campaign
alongside
surface‐monitoring
ozone‐sonde
examine
diurnal
city.
In
situ
ground
subcolumns
were
well
correlated
(
r
=
0.87)
with
2×
larger
differences
observed
morning
than
afternoon
reflecting
impacts
chemical
titration
at
surface.
Matched
also
0.96,
bias
1.3
ppb)
suggesting
biases
between
surface
reflect
vertical
distribution
not
biases.
Finally,
if
Tropospheric
Emissions:
Monitoring
Pollution
achieves
precision
requirement,
we
find
this
product
may
be
able
detect
enhanced
city
like
Houston
up
55%
capturing
variability,
particularly
exceedance
events.
Язык: Английский
Deep learning-based forecasting of daily maximum ozone levels and assessment of socioeconomic and health impacts in South Korea
The Science of The Total Environment,
Год журнала:
2025,
Номер
983, С. 179684 - 179684
Опубликована: Май 22, 2025
Язык: Английский
Optimized Ozone Concentration Prediction in Seoul Districts Using ANN and K-means Clustering for Accuracy Enhancement
Research Square (Research Square),
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 18, 2024
Abstract
Ozone
is
a
dangerous
greenhouse
gas
and
air
pollutant
in
urban
areas,
with
significant
negative
impacts
on
climate
change
human
health.
Predicting
ozone
concentrations
critical
factor
environmental
issues
such
as
pollution
management,
risk
assessment,
public
health,
global
warming.
Since
an
early
prediction
model
of
essential
for
building
warning
system,
research
needed
indicators
that
explain
whether
status
will
rise
or
fall.
This
study
proposed
trained
using
artificial
neural
network
(ANN)-based
classification
training
data
divided
into
specific
time
periods
through
k-means
clustering
to
predict
concentrations.
lowers
the
cost
owing
around
30%
reduced
period,
also
applicable
variety
features.
Air
quality
was
collected
from
2019
2020
25
districts
Seoul,
South
Korea
used
testing
concentration
changes
after
one
hour
during
07:00
18:00.
The
yielded
3%
higher
F1
score
3-4%
accuracy
comparison
other
models.
As
result,
this
showed
improved
performance
while
reducing
environment.
Язык: Английский
An Advanced Hybrid Model Based On Stochastic - Eulerian Numerical Approach: Application To Atmospheric Pollution
Romanian Journal of Physics,
Год журнала:
2024,
Номер
69(9-10), С. 808 - 808
Опубликована: Дек. 15, 2024
In
this
paper,
we
propose
for
the
first
time
to
best
of
our
knowledge,
extend
application
a
stochastic
Eulerian
numerical
approach
based
on
Extended
Kalman
Filter
(EKFE.N.M.)
address
limitations
air
pollution
model
CHIMERE.
This
integrates
comprehensive
set
processes,
including
advection,
turbulence,
chemical
reactions,
emissions,
and
deposition,
dynamics
pollutant
mass
concentration.
The
EKF
technique
is
employed
transform
nonlinear
dynamic
problems
into
succession
locally
linearized
ones,
which
are
then
used
estimate
system
states
adjust
concentrations
measured
data.
tested
through
two
scenarios:
one
without
external
forces
or
control
terms,
another
that
incorporates
factors
like
temperature,
wind
speed,
nitrogen
dioxide
as
ozone
precursors.
A
comparison
obtained
results
with
those
from
standard
CHIMERE
studies
literature
demonstrates
accuracy
effectiveness
proposed
method.
Язык: Английский