Deep learning model based on coupled SWAT and interpretable methods for water quality prediction under the influence of non-point source pollution
Computers and Electronics in Agriculture,
Год журнала:
2025,
Номер
231, С. 109985 - 109985
Опубликована: Янв. 23, 2025
Язык: Английский
Integrated Modeling and Management of Non-Point Source Pollution in the Bailin River Basin: Best Practices for Reducing Nutrient Loads
Research Square (Research Square),
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 10, 2025
Abstract
The
Bailin
River,
a
key
tributary
of
the
Yangtze
faces
significant
water
quality
challenges
due
to
agricultural
non-point
source
(NPS)
pollution
exacerbated
by
industrial
discharge
and
urban
runoff.
This
study
employs
Soil
Water
Assessment
Tool
(SWAT)
analyze
temporal
spatial
dynamics
runoff
as
well
total
nitrogen
(TN)
phosphorus
(TP)
loads
in
River
basin
from
2020
2023.
A
critical
area
analysis
was
performed
identify
regions
disproportionately
contributing
pollutant
loads.
Through
various
simulations,
including
different
Best
Management
Practices
(BMPs)
scenarios,
explores
their
effectiveness
reducing
nutrient
findings
reveal
that
losses
are
significantly
concentrated
during
flood
season,
with
TN
TP
accounting
for
58.61%
58.92%
annual
totals,
respectively.
Specific
BMP
combining
optimized
fertilization,
vegetation
buffer
strips,
grass
ditches,
demonstrated
substantial
reduction,
best
combinations
exceeding
58%
reductions
both
TP.
emphasizes
necessity
targeted
interventions
areas
optimize
management
strategies
achieve
better
outcomes.
Continuous
monitoring
adaptive
practices
will
be
crucial
addressing
ongoing
this
basin.
Ultimately,
research
contributes
deeper
understanding
NPS
mountainous
watersheds
highlights
effective
pathways
improved
ecological
health
quality.
Язык: Английский
Hydrological modeling of nutrient transport and mitigation strategies for non-point source pollution in the Bailin River basin
Journal of Contaminant Hydrology,
Год журнала:
2025,
Номер
273, С. 104617 - 104617
Опубликована: Май 20, 2025
Язык: Английский
Runoff and Drought Responses to Land Use Change and CMIP6 Climate Projections
Water,
Год журнала:
2025,
Номер
17(11), С. 1696 - 1696
Опубликована: Июнь 3, 2025
Climate
and
land
use
changes
significantly
affect
runoff
hydrological
drought,
presenting
challenges
for
water
resource
management.
This
study
focuses
on
the
Naoli
River
Basin,
utilizing
SWAT
model
integrated
with
PLUS
projections
under
CMIP6
SSP245
SSP585
scenarios
to
assess
trends
in
drought
characteristics
from
2025
2100.
The
Standardized
Runoff
Index
(SRI)
run
theory
are
applied
analyze
frequency
duration.
Key
findings
include
following:
(1)
Under
scenario
(2061–2100),
changes—specifically,
a
reduction
cropland
an
increase
forest
cover—resulted
12.59%
decrease
compared
baseline
period
(1970–2014),
notable
differences
when
considering
climate-only
scenarios.
(2)
exhibits
significant
rise
duration,
particularly
during
summer,
whereas
shows
milder
trends.
(3)
Based
Taylor
plot
evaluation,
ensemble
average
MMM-Best
(r
=
0.80,
RMSE
26.15)
has
been
identified
as
optimal
prediction
2025–2100
period.
Deviation
analysis
revealed
that
NorESM2-MM
IPSL-CM6A-LR
demonstrated
greatest
stability,
while
EC-Earth3
exhibited
largest
deviation
highest
uncertainty.
(4)
Land
help
mitigate
by
enhancing
retention,
although
their
effectiveness
diminishes
due
dominant
influence
of
climate
factors,
including
increased
temperature
precipitation
variability.
And
(5)
SRI-3
mutation
indicated
point
occurred
July
2074
April
2060
(p
<
0.05).
trend
fluctuations,
number
crossover
points
rising
40
following
changes;
conversely,
remained
stable
only
seven
points,
high-emission
predominantly
influenced
early
mutations.
These
illuminate
interactive
effects
change,
providing
scientific
foundation
optimizing
management
developing
effective
mitigation
strategies.
Язык: Английский
Assessing the Hydrological Response to Land Use Changes Linking SWAT and CA‐Markov Models
Hydrological Processes,
Год журнала:
2024,
Номер
38(11)
Опубликована: Ноя. 1, 2024
ABSTRACT
Land
use
change,
as
a
major
driving
factor
of
watershed
hydrological
process,
has
significant
influence
on
change.
In
addition,
series
models,
important
tools
for
simulating
impacts,
are
widely
employed
in
studying
land
However,
when
employing
model
to
analyse
the
impacts
changes,
most
previous
studies
focused
evolution
historical
change
and
lacked
reasonable
predictions
future
use.
Therefore,
it
is
necessary
extend
such
scenarios
cope
with
possible
variations
basin.
Given
this,
this
paper
making
Wuwei
section
Shiyang
River
Basin
study
area,
coupled
SWAT
(Soil
Water
Assessment
Tool)
simulation
CA‐Markov
(cellular
automata‐Markov
chain)
prediction
regional
effects
caused
by
changes.
general
directly
uses
system‐generated
suitability
atlas.
contrast,
applied
logistic
regression
Multi‐criteria
evaluation
(MCE)
methods
construct
atlas,
thereby
establishing
Logistic‐CA‐Markov
MCE‐CA‐Markov
models.
Based
results,
main
results
follows:
(1)
The
area
mainly
grassland
barren,
accounting
more
than
80%.
Additionally,
forest
changing
at
highest
rate
among
all
types.
(2)
terms
percentage
forest,
predicted
(Multi‐criteria
evaluation‐cellular
largest
coverage
(57.78%),
whereas
Logistic
lowest
(54.69%),
indicating
that
former
pays
attention
sustainable
development
ecological
environment.
(3)
area's
R
2
=
0.83,
NSE
0.79,
PBIAS
−18.6%,
validation
0.81,
0.76,
−17.8%
demonstrate
favourable
application
model.
(4)
simulated
runoff
under
scenarios,
amount
increasing
would
eventually
rise
water
yield
(WYLD)
lateral
(LATQ),
subsurface
(GWQ),
reducing
surface
(SURQ).
contributes
better
understanding
impact
resources
balance,
thus
guiding
management
development.
Язык: Английский