Constructing the 3D Spatial Distribution of the HCHO/NO2 Ratio via Satellite Observation and Machine Learning Model
Environmental Science & Technology,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 20, 2025
The
satellite-based
tropospheric
column
ratio
of
HCHO
to
NO2
(FNR)
is
widely
used
diagnose
ozone
formation
sensitivity;
however,
its
representation
surface
conditions
remains
controversial.
In
this
study,
an
approach
construct
the
3D
spatial
distribution
FNR
in
lower
troposphere
was
proposed.
Based
on
satellite
and
multiaxes-differential
Optical
Absorption
Spectroscopy
(MAX-DOAS)
data,
horizontal
vertical
distributions
have
been
respectively
obtained.
To
further
enhance
generalizability
approach,
we
also
reproduced
profiles
using
a
machine
learning
model
(Bagged
trees)
feature
variables.
Here,
three-dimensional
during
summer
2019
as
example,
fourth-order
polynomial
relationship
found
between
reconstruction
factors
(fcol_i)
altitudes,
demonstrating
correlation
coefficient
0.98.
Utilizing
established
relationship,
significant
difference
reconstructed
FNR,
with
former
decreasing
by
56.9%.
Moreover,
for
summers
from
2018
2022
revealed
trend
over
five
years
Shanghai
control
regimes
gradually
shifting
toward
transition
NOx-limited
regimes.
Through
newly
not
only
can
accuracy
identifying
sensitivity
be
enhanced
spaced
observation,
but
it
helps
gaining
comprehensive
understanding
photochemical
mechanisms
direction.
Язык: Английский
Model-driven high-throughput zebrafish embryo assay for evaluating whole effluent toxicity variation across 100 full-scale wastewater treatment plants
Water Research,
Год журнала:
2025,
Номер
281, С. 123675 - 123675
Опубликована: Апрель 17, 2025
Язык: Английский
Exploring Aerosol Vertical Distributions and Their Influencing Factors: Insight from MAX-DOAS and Machine Learning
Environmental Science & Technology,
Год журнала:
2025,
Номер
unknown
Опубликована: Июнь 4, 2025
Understanding
aerosol
vertical
distribution
is
crucial
for
pollution
mitigation
but
hindered
by
limited
observational
data.
This
study
employed
multiaxis
differential
optical
absorption
spectroscopy
(MAX-DOAS)
technology
with
a
coupled
radiative
transfer
model-machine
learning
(RTM-ML)
framework
to
retrieve
high-resolution
properties
in
Shanghai.
Retrievals
indicated
vertically
decreasing
aerosols,
peaking
the
upper
atmosphere
summer
and
lower
winter.
Aerosol
hygroscopicity
followed
similar
seasonal
patterns
increased
altitude.
Multifactor
driving
ML
models
Shapley
additive
explanations
(SHAP)
were
used
investigate
drivers
variation.
Results
that
emissions,
east-west
transport,
atmospheric
oxidation
main
of
aerosols
below
0.5
km.
Above
km,
humidity
became
dominant,
suggesting
hygroscopic
growth
secondary
formation
more
prominent.
North-south
transport
also
significantly
influenced
within
1.6
Meteorological
normalization
emphasized
emission
reduction
can
effectively
atmosphere,
while
enhanced
promoted
formation,
particularly
atmosphere.
These
findings
advance
understanding
multiple
factors
shaping
distributions
highlight
strategies
addressing
compound
should
be
conceived
multidimensional
multifactorial
understanding.
Язык: Английский
Identifying human activities causing water pollution based on microbial community sequencing and source classifier machine learning
Environment International,
Год журнала:
2024,
Номер
195, С. 109240 - 109240
Опубликована: Дек. 25, 2024
Identifying
and
differentiating
human
activities
is
crucial
for
effectively
preventing
the
threats
posed
by
environmental
pollution
to
aquatic
ecosystems
health.
Machine
learning
(ML)
a
powerful
analytical
tool
tracking
impacts
on
river
based
high-through
datasets.
This
study
employed
an
ML
framework
16S
rRNA
sequencing
data
reveal
microbial
dynamics
trace
across
China.
The
results
revealed
that
assembly
was
mainly
dominated
deterministic
factors
(environmental
interactions
between
species),
metacommunity
partition
significantly
associated
with
in
both
water
sediment
(Chi-square
test
Язык: Английский