Water,
Journal Year:
2025,
Volume and Issue:
17(3), P. 362 - 362
Published: Jan. 27, 2025
Groundwater
serves
as
an
indispensable
global
resource,
essential
for
agriculture,
industry,
and
the
urban
water
supply.
Predicting
groundwater
level
in
karst
regions
presents
notable
challenges
due
to
intricate
geological
structures
fluctuating
climatic
conditions.
This
study
examines
Qingzhen
City,
China,
introducing
innovative
hybrid
model,
Hodrick–Prescott
(HP)
filter–Long
Short-Term
Memory
(LSTM)
network
(HP-LSTM),
which
integrates
HP
filter
with
LSTM
enhance
precision
of
forecasting.
By
attenuating
short-term
noise,
HP-LSTM
model
improves
long-term
trend
prediction
accuracy.
Findings
reveal
that
significantly
outperformed
conventional
LSTM,
attaining
R2
values
0.99,
0.96,
0.98
on
training,
validation,
test
datasets,
respectively,
contrast
0.92,
0.76,
0.95.
The
achieved
RMSE
0.0276
a
MAPE
2.92%
set,
outperforming
(RMSE:
0.1149;
MAPE:
9.14%)
capturing
patterns
reducing
fluctuations.
While
is
effective
at
modeling
dynamics,
it
more
prone
resulting
greater
errors.
Overall,
demonstrates
superior
robustness
prediction,
whereas
may
be
better
suited
scenarios
requiring
rapid
adaptation
variations.
Selecting
appropriate
tailored
specific
predictive
needs
can
thus
optimize
management
strategies.
Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(5), P. 1438 - 1438
Published: March 3, 2023
Effects
of
landscape
patterns
or
topographic
features
on
the
river
water
environment
have
been
broadly
studied
to
control
non-point
source
(NPS)
pollution
and
cut
off
potential
pathways
for
pollutants
affect
human
health.
However,
spatio-temporal
dynamics
scale
effects
with
respect
impact
aquatic
over
successive
years
not
elucidated.
In
this
study,
quality
parameters
land
cover
data
three
consecutive
mainly
in
Tangshan
City,
located
northeast
Haihe
River
Basin,
China,
were
obtained
determine
associations
between
environment.
Results
indicated
that
seasonal
differences
dissolved
oxygen
(DO)
total
nitrogen
(TN)
significant
(p
<
0.001),
spatial
variation
was
generally
observed
each
parameter.
Redundancy
analysis
revealed
different
impacts
as
spans
scales
change.
Overall,
best
explanatory
variables
explained
an
average
58.6%
at
various
two
seasons.
Topographic
made
a
greater
contribution
changes
buffer
scale;
conversely,
catchment
scale,
stemmed
primarily
from
composition
configuration.
The
shape
index
cropland
(LSIcrop)
important
factor
influencing
scales.
These
results
suggest
considering
connectivity
distinct
could
enhance
understanding
alteration
hydrological
processes
across
multiple
features,
which
turn
has
water.
Ecological Indicators,
Journal Year:
2024,
Volume and Issue:
165, P. 112187 - 112187
Published: May 30, 2024
Microorganisms
in
sediment
can
timely
reflect
the
impact
of
anthropogenic
disturbance.
So
far,
microorganism
studies
have
primarily
focused
on
assessing
a
specific
type
disturbance,
such
as
mining,
domestic
sewage
and
damming.
However,
there
has
been
limited
attention
given
to
systematically
investigating
responses
microbial
communities
various
typical
disturbances
within
singular
watershed.
In
light
this,
this
study
involved
collection
33
superficial
samples
from
Xinzhai
River.
Physicochemical
properties
sediments
were
analyzed,
studied
by
using
Illumina
high-throughput
sequencing
technology.
The
results
informed
that
moderate
level
disturbance
contributing
enhanced
community
diversity.
Under
different
types
disturbances,
significant
differences
existed
genera,
which
significantly
affected
pH,
total
nitrogen
(TN)
heavy
metals
(HMs).
addition,
pronounced
low-abundance
biomarkers
occured
at
genus
level,
indicating
key
same
watershed
could
serve
indicators
disturbances.
Functional
microorganisms
River
mainly
associated
with
iron,
sulfur
cycling.
Furthermore,
functional
taxa
sulfate-reducing
bacteria
(SRB)
more
constrained
nutrients
displayed
positive
response
sewage.
While
related
nitrification
methane
oxidation
dominant
areas
disturbed
acid
mine
drainage
(AMD).
Damming
exerted
most
influence
composition
versatile
taxa.
This
provides
precious
comprehensive
insights
into
how
differential
respond
intensities
Simultaneously,
substantive
evidence
is
furnished
corroborate
hypothesis
activities
might
alter
structure
influencing
small
portion
