Assessing Machine Learning and Statistical Methods for Rock Glacier‐Based Permafrost Distribution in Northern Kargil Region
Permafrost and Periglacial Processes,
Journal Year:
2024,
Volume and Issue:
35(3), P. 262 - 277
Published: June 18, 2024
ABSTRACT
Estimating
permafrost
distribution
in
high‐mountain
areas
is
challenging.
In
these
situations,
rock
glaciers,
provide
valuable
insights
into
and
are
often
used
as
proxies
for
identifying
occurrence.
Integrating
various
climatological
topographical
conditioning
factors
with
glaciers
enables
inferring
the
of
environments.
This
study
utilized
three
machine
learning
models
such
random
forest
(RF),
support
vector
(SVM),
artificial
neural
network
(ANN),
one
statistical
model,
namely,
frequency
ratio
(FR),
to
assess
probability
over
northern
Kargil
region
Indian
Himalayas.
Among
198
identified
through
high‐resolution
images
from
Google
Earth,
70%
training
dataset,
rest
30%
testing
dataset.
The
considered
eight
factors:
slope,
aspect,
elevation,
curvature,
mean
annual
land
surface
temperature
(MA‐LST),
normalized
difference
snow
index
(MA‐NDSI),
water
(MA‐NDWI),
lithology
mapping.
Furthermore,
SHapley
Additive
exPlanations
(SHAP)
test
assessed
variable
importance
model
performance.
results
revealed
that
RF
performs
best
mapping,
followed
by
SVM,
FR,
ANN
models.
also
found
11%
total
geographic
area
has
a
high
very
Language: Английский
Machine learning based high-resolution air temperature modelling from landsat-8, MODIS, and In-Situ measurements with ERA-5 inter-comparison in the data sparse regions of Himachal Pradesh
Bulletin of Atmospheric Science and Technology,
Journal Year:
2024,
Volume and Issue:
5(1)
Published: Dec. 1, 2024
Language: Английский