Advancing early-stage plant phosphorus assessment for winter rye via hyperspectral data: A model-based approach harnessing feedforward neural networks
European Journal of Agronomy,
Journal Year:
2025,
Volume and Issue:
169, P. 127667 - 127667
Published: May 9, 2025
Language: Английский
In situ measurement techniques in remote sensing research over grasslands
Miscellanea Geographica,
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 17, 2025
Abstract
Remote
satellite
observations
have
played
a
crucial
role
in
monitoring
vegetation
since
the
1970s,
starting
with
development
of
Normalized
Difference
Vegetation
Index
(NDVI)
by
Rouse
(1974)
and
Tucker
(1979).
Despite
advances
technology,
validation
situ
measurements,
which
are
often
locally
sparse,
remains
essential.
Areas
such
as
grasslands
wetlands,
vital
for
CO
2
balance
water
quality,
require
special
attention.
Within
GrasSAT
project,
measurements
were
conducted
Poland
Norway,
included
LAI,
soil
moisture,
biomass.
This
article
focuses
exclusively
on
studies
carried
out
Poland,
presents
results
related
to
models
operating
under
Polish
environmental
conditions,
highlighting
importance
local
factors
context
comparing
ground
data.
Different
sampling
methods,
linear
transect
quadrat
considered.
The
research
aimed
understand
improve
consistency
between
data,
is
accurate
models.
Language: Английский
Research on the Inversion of Key Growth Parameters of Rice Based on Multisource Remote Sensing Data and Deep Learning
Jian Li,
No information about this author
Jian Lü,
No information about this author
Hongkun Fu
No information about this author
et al.
Agriculture,
Journal Year:
2024,
Volume and Issue:
14(12), P. 2326 - 2326
Published: Dec. 19, 2024
This
study
accurately
inverts
key
growth
parameters
of
rice,
including
Leaf
Area
Index
(LAI),
chlorophyll
content
(SPAD)
value,
and
height,
by
integrating
multisource
remote
sensing
data
(including
MODIS
ERA5
imagery)
deep
learning
models.
Dehui
City
in
Jilin
Province,
China,
was
selected
as
the
case
area,
where
multidimensional
vegetation
indices,
ecological
function
parameters,
environmental
variables
were
collected,
covering
seven
stages
rice.
Data
analysis
parameter
prediction
conducted
using
a
variety
machine
models
Partial
Least
Squares
(PLSs),
Support
Vector
Machine
(SVM),
Random
Forest
(RF),
Long
Short-Term
Memory
Networks
(LSTM),
among
which
LSTM
model
demonstrated
superior
performance,
particularly
at
multiple
critical
time
points.
The
results
show
that
performed
best
inverting
three
with
LAI
inversion
accuracy
on
21
August
reaching
coefficient
determination
(R2)
0.72,
root
mean
square
error
(RMSE)
0.34,
absolute
(MAE)
0.27.
SPAD
same
date
achieved
an
R2
0.69,
RMSE
1.45,
MAE
1.16.
height
25
July
reached
0.74,
2.30,
2.08.
not
only
verifies
effectiveness
combining
advanced
algorithms
but
also
provides
scientific
basis
for
precision
management
decision-making
rice
cultivation.
Language: Английский