Environmental Science Nano,
Journal Year:
2024,
Volume and Issue:
11(6), P. 2568 - 2576
Published: Jan. 1, 2024
This
study
demonstrates
that
PBDEs
attached
to
soil
nanoparticles
can
be
highly
mobile
in
saturated
porous
media,
providing
important
insights
on
risk
assessment
of
contamination.
Research Square (Research Square),
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 5, 2024
Abstract
COD
(Chemical
Oxygen
Demand)
is
an
important
indicator
to
measure
organic
pollution
of
water
body.
To
strengthen
in-depth
analysis
and
prediction
COD,
a
new
method
was
proposed
in
this
paper.
A
frequency
division
method,
Variational
Mode
Decomposition
(VMD)
used
complete
time
domain
decomposition
data
before
model
simulation.
The
original
separated
into
five
signals
with
different
bands,
IMF1,
IMF2,
IMF3,
IMF4
IMF5,
which
the
influence
meteorological
factors
quality
on
were
explored.
long-term
content
mainly
driven
by
nutrient
phosphorus
nitrogen,
while
immediate
fluctuation
characteristics
exhibit
relatively
stability.
Random
Forest,
Long
Short-Term
Memory
(LSTM)
Gated
Recurrent
Unit
(GRU)
predict
signal
processed
VMD.
It
found
that
can
improve
simulation
stability
accuracy
GRU
LSTM
more
significantly
than
Forest.
VMD-GRU
VMD-LSTM
models
be
reliably
for
analyzation
Chengdu
area.
Toxics,
Journal Year:
2024,
Volume and Issue:
12(10), P. 737 - 737
Published: Oct. 12, 2024
To
predict
the
behavior
of
aromatic
contaminants
(ACs)
in
complex
soil-plant
systems,
this
study
developed
machine
learning
(ML)
models
to
estimate
root
concentration
factor
(RCF)
both
traditional
(e.g.,
polycyclic
hydrocarbons,
polychlorinated
biphenyls)
and
emerging
ACs
phthalate
acid
esters,
aryl
organophosphate
esters).
Four
ML
algorithms
were
employed,
trained
on
a
unified
RCF
dataset
comprising
878
data
points,
covering
6
features
cultivation
systems
98
molecular
descriptors
55
chemicals,
including
29
ACs.
The
gradient-boosted
regression
tree
(GBRT)
model
demonstrated
strong
predictive
performance,
with
coefficient
determination
(R
