Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(9), P. 2247 - 2247
Published: April 24, 2023
Monitoring
and
managing
groundwater
resources
is
critical
for
sustaining
livelihoods
supporting
various
human
activities,
including
irrigation
drinking
water
supply.
The
most
common
method
of
monitoring
well
level
measurements.
These
records
can
be
difficult
to
collect
maintain,
especially
in
countries
with
limited
infrastructure
resources.
However,
long-term
data
collection
required
characterize
evaluate
trends.
To
address
these
challenges,
we
propose
a
framework
that
uses
from
the
Gravity
Recovery
Climate
Experiment
(GRACE)
mission
downscaling
models
generate
higher-resolution
(1
km)
predictions.
designed
flexible,
allowing
users
implement
any
machine
learning
model
interest.
We
selected
four
models:
deep
model,
gradient
tree
boosting,
multi-layer
perceptron,
k-nearest
neighbors
regressor.
effectiveness
framework,
offer
case
study
Sunflower
County,
Mississippi,
using
validate
Overall,
this
paper
provides
valuable
contribution
field
resource
management
by
demonstrating
remote
sensing
techniques
improve
resource,
those
who
seek
faster
way
begin
use
datasets
applications.
Geomatics Natural Hazards and Risk,
Journal Year:
2023,
Volume and Issue:
14(1)
Published: June 1, 2023
Groundwater
is
a
crucial
natural
resource
that
varies
in
quality
and
quantity
across
Khyber
Pakhtunkhwa
(KPK),
Pakistan.
Increased
population
urbanization
place
enormous
demands
on
groundwater
supplies,
reducing
both
their
quantity.
This
research
aimed
to
delineate
the
potential
zone
Kohat
region,
Pakistan
by
integrating
twelve
thematic
layers.
In
current
research,
Potential
Zone
(GWPZ)
were
created
implementing
Weight
of
Evidence
(WOE),
Frequency
Ratio
(FR),
Information
Value
(IV)
models
region.
this
study,
we
used
Sentinel-2
satellite
data
utilized
generate
an
inventory
map
using
machine
learning
algorithms
Google
Earth
Engine
(GEE).
Furthermore,
validation
was
done
with
field
survey
ground
data.
The
divided
into
training
(80%)
testing
(20%)
datasets.
WOE,
FR,
IV
are
applied
assess
relationship
between
factors
GWPZ
Finally,
results
Area
Under
Curve
(AUC)
technique
for
88%,
91%,
89%.
final
can
aid
better
future
planning
exploration,
management,
supply
water
Heliyon,
Journal Year:
2023,
Volume and Issue:
9(3), P. e14690 - e14690
Published: March 1, 2023
Land
subsidence
is
considered
a
threat
to
developing
cities
and
triggered
by
several
natural
(geological
seismic)
human
(mining,
groundwater
withdrawal,
oil
gas
extraction,
constructions)
factors.
This
research
has
gathered
datasets
consisting
of
80
Sentinel-1A
ascending
descending
SLC
images
from
July
2017
2019.
dataset,
concerning
InSAR
PS-InSAR,
processed
with
SARPROZ
software
determine
the
land
in
Gwadar
City,
Balochistan,
Pakistan.
Later,
maps
were
created
ArcGIS
10.8.
Due
InSAR’s
limitations
measuring
millimeter-scale
surface
deformation,
Multi-Temporal
techniques,
like
are
introduced
provide
better
accuracy,
consistency,
fewer
errors
deformation
analysis.
remote-based
SAR
technique
helpful
area;
for
researchers,
city
mobility
constrained
become
more
restricted
post-Covid-19.
requires
multiple
acquired
same
place
at
different
times
estimating
per
year,
along
uplifting
subsidence.
The
results
showed
maximum
Koh-i-Mehdi
Mountain
PS-InSAR
up
−92
mm/year
track
−66
area
Mountain,
−48
−32
deep
seaport.
From
our
experimental
results,
high
rate
been
found
newly
evolving
City.
very
beneficial
country’s
economic
development
because
its
deep-sea
port,
developed
China-Pakistan
Economic
Corridor
(CPEC).
associated
detailed
analysis
identifying
areas
significant
subsidence,
enlisting
possible
causes
that
needed
be
resolved
before
further
developments.
Our
findings
urban
disaster
monitoring
as
being
promoted
next
seaport
start
CPEC.
Water Resources Research,
Journal Year:
2024,
Volume and Issue:
60(7)
Published: July 1, 2024
Abstract
GRACE
(Gravity
Recovery
and
Climate
Experiment)
has
been
widely
used
to
evaluate
terrestrial
water
storage
(TWS)
groundwater
(GWS).
However,
the
coarse‐resolution
of
data
limited
ability
identify
local
vulnerabilities
in
changes
associated
with
climatic
anthropogenic
stressors.
This
study
employs
high‐resolution
(1
km
2
)
generated
through
machine
learning
(ML)
based
statistical
downscaling
illuminate
TWS
GWS
dynamics
across
twenty
sub‐regions
Indus
Basin.
Monthly
anomalies
obtained
from
a
geographically
weighted
random
forest
(RF
gw
model
maintained
good
consistency
original
at
25
grid
scale.
The
downscaled
1
resolution
illustrate
spatial
heterogeneity
depletion
within
each
sub‐region.
Comparison
in‐situ
2,200
monitoring
wells
shows
that
significantly
improves
agreement
data,
evidenced
by
higher
Kling‐Gupta
Efficiency
(0.50–0.85)
correlation
coefficients
(0.60–0.95).
Hotspots
highest
decline
rate
between
2002
2023
were
Dehli
Doab
(−442,
−585
mm/year),
BIST
(−367,
−556
Rajasthan
(−242,
−381
BARI
(−188,
−333
mm/year).
Based
on
general
additive
model,
47%–83%
was
stressors
mainly
due
increasing
trends
crop
sown
area,
consumption,
human
settlements.
lower
(i.e.,
−25
−75
mm/year)
upstream
(e.g.,
Yogo,
Gilgit,
Khurmong,
Kabul)
where
factors
(downward
shortwave
radiations,
air
temperature,
sea
surface
temperature)
explained
72%–91%
TWS/GWS
changes.
relative
influences
varied
sub‐regions,
underscoring
complex
interplay
natural‐human
activities
basin.
These
findings
inform
place‐based
resource
management
Basin
advancing
understanding
vulnerabilities.
