I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
2
,
A
p
r
il 2
0
2
5
,
p
p
.
1
2
7
1
~
1
2
8
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
2
.
p
p
1
2
7
1
-
1
2
8
0
1271
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Cro
p clas
sifica
tio
n using
objec
t
-
o
ri
ented
metho
d and
G
o
o
g
le
Ea
rth
Eng
ine
G
ee
t
a
T.
Desa
i
1
,
Abha
y
N.
G
a
ik
wa
d
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
A
n
j
u
ma
n
-
I
-
I
sl
a
m's
K
a
l
s
e
k
a
r
Te
c
h
n
i
c
a
l
C
a
m
p
u
s
,
M
u
mb
a
i
U
n
i
v
e
r
si
t
y
,
P
a
n
v
e
l
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s,
B
a
b
a
s
a
h
e
b
N
a
i
k
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
sa
d
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
8
,
2
0
2
4
R
ev
is
ed
Oct
2
5
,
2
0
2
4
Acc
ep
ted
No
v
1
4
,
2
0
2
4
Ag
ricu
lt
u
re
c
ro
p
m
o
n
it
o
rin
g
in
r
e
a
l
-
ti
m
e
is
c
ru
c
ial
i
n
f
o
rm
u
lati
n
g
e
ffe
c
ti
v
e
a
g
ricu
lt
u
ra
l
p
ra
c
ti
c
e
s
a
n
d
m
a
n
a
g
e
m
e
n
t
p
o
l
icie
s.
Th
e
p
rima
ry
g
o
a
l
o
f
t
h
e
in
v
e
stig
a
t
io
n
is
to
e
x
p
l
o
re
h
o
w
th
e
u
ti
l
iza
ti
o
n
o
f
S
e
n
t
in
e
l
-
1
d
a
ta
a
n
d
it
s
fu
sio
n
wit
h
S
e
n
ti
n
e
l
-
2
imp
a
c
t
c
ro
p
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
i
n
a
fr
a
g
m
e
n
ted
a
g
ricu
lt
u
ra
l
la
n
d
sc
a
p
e
in
t
h
e
Ya
v
a
tma
l
District
o
f
M
a
h
a
ra
sh
tra,
In
d
ia.
P
i
x
e
l
b
a
se
d
c
las
sifica
ti
o
n
a
n
d
o
b
jec
t
-
o
rien
ted
c
las
sifica
ti
o
n
a
p
p
r
o
a
c
h
e
s
we
re
imp
lem
e
n
ted
o
n
G
o
o
g
le
Eart
h
En
g
i
n
e
(G
EE
)
,
a
n
d
o
b
tai
n
e
d
re
su
lt
s
we
re
c
o
m
p
a
re
d
fo
r
d
iffere
n
t
c
o
m
b
in
a
ti
o
n
s
o
f
o
p
ti
c
a
l
a
n
d
m
icro
wa
v
e
fe
a
tu
re
s.
Th
e
re
se
a
rc
h
re
v
e
a
led
th
a
t
th
e
o
b
jec
t
-
b
a
se
d
tec
h
n
iq
u
e
p
e
rfo
rm
e
d
b
e
tt
e
r
th
a
n
t
h
e
p
ix
e
l
-
b
a
se
d
a
p
p
ro
a
c
h
,
wit
h
a
3
.
5
%
i
n
c
re
a
se
in
o
v
e
ra
ll
a
c
c
u
ra
c
y
.
F
o
r
2
0
2
2
,
c
ro
p
-
ty
p
e
m
a
p
p
in
g
wa
s
g
e
n
e
ra
ted
with
o
v
e
ra
ll
a
c
c
u
ra
c
ies
v
a
ry
in
g
fro
m
8
5
.
5
%
to
6
1
%
a
n
d
a
k
a
p
p
a
c
o
e
fficie
n
t
b
e
twe
e
n
0
.
7
7
a
n
d
0
.
3
7
.
T
h
e
se
o
v
e
ra
l
l
a
c
c
u
ra
c
ies
imp
ly
th
a
t
jo
in
t
u
se
o
f
o
p
ti
c
a
l
a
n
d
ra
d
a
r
d
a
ta
h
a
s
g
i
v
e
n
a
2
4
%
imp
ro
v
e
m
e
n
t
in
o
v
e
ra
ll
a
c
c
u
ra
c
y
c
o
m
p
a
re
d
t
o
u
se
o
f
o
n
ly
o
p
ti
c
a
l
d
a
ta.
In
a
d
d
it
i
o
n
,
th
e
tem
p
o
ra
l
c
h
a
n
g
e
in
th
e
b
a
c
k
sc
a
tt
e
r
c
o
e
fficie
n
ts
a
n
d
d
iffere
n
t
v
e
g
e
tatio
n
in
d
ice
s fo
r
d
iffere
n
t
c
r
o
p
s we
re
e
x
a
m
in
e
d
o
v
e
r
c
ro
p
g
r
o
wth
c
y
c
le.
Th
is
w
o
rk
d
e
m
o
n
stra
tes
th
e
fu
s
io
n
o
f
S
e
n
ti
n
e
l
-
1
a
n
d
S
e
n
t
in
e
l
-
2
d
a
ta
t
o
c
las
sify
wh
e
a
t,
c
h
ick
p
e
a
,
o
t
h
e
r
c
ro
p
s,
wa
ter an
d
u
r
b
a
n
a
re
a
s.
K
ey
w
o
r
d
s
:
C
r
o
p
class
if
icatio
n
Go
o
g
le
E
ar
th
E
n
g
in
e
Ma
ch
in
e
lear
n
in
g
Sen
tin
el
-
1
Sen
tin
el
-
2
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Gee
ta
T.
Desai
Dep
ar
tm
en
t
of
E
lectr
o
n
ics
an
d
C
o
m
p
u
ter
Scien
ce
An
ju
m
an
-
I
-
I
s
lam
'
s
Kal
s
ek
ar
T
ec
h
n
ical
C
am
p
u
s
,
Mu
m
b
ai
U
n
iv
er
s
ity
New
Pan
v
el,
Nav
i M
u
m
b
ai,
Ma
h
ar
ash
tr
a
,
I
n
d
ia
4
1
0
2
0
6
E
m
ail:
tg
ee
tad
esai@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
r
ad
icatin
g
h
u
n
g
er
an
d
en
s
u
r
in
g
f
o
o
d
s
ec
u
r
ity
ar
e
to
p
p
r
i
o
r
ities
f
o
r
h
u
m
an
ity
.
C
r
o
p
clas
s
if
icatio
n
(
C
C
)
m
ap
s
ar
e
v
ital
f
o
r
d
es
ig
n
in
g
an
d
im
p
lem
e
n
tin
g
ag
r
icu
ltu
r
al
m
o
n
ito
r
i
n
g
p
r
ac
tices
th
at
en
s
u
r
e
f
o
o
d
s
ec
u
r
ity
an
d
d
ea
l
with
en
v
ir
o
n
m
en
tal
ch
allen
g
es
ca
u
s
ed
b
y
g
lo
b
al
war
m
in
g
[
1
]
,
[
2
]
.
W
h
ile
ex
ten
s
iv
e
f
ar
m
in
g
is
a
g
lo
b
al
tr
en
d
,
s
m
allh
o
ld
e
r
f
ar
m
in
g
is
wid
esp
r
ea
d
in
I
n
d
ia,
as
a
r
esu
lt,
th
e
p
er
f
o
r
m
an
ce
o
f
s
m
all
an
d
m
ar
g
in
al
f
ar
m
er
s
will
d
eter
m
i
n
e
th
e
f
u
tu
r
e
o
f
s
u
s
tain
ab
le
a
g
r
icu
ltu
r
al
g
r
o
wth
an
d
f
o
o
d
s
ec
u
r
ity
in
I
n
d
ia
[
3
]
.
I
n
I
n
d
ia,
cr
o
p
p
in
g
p
atter
n
s
a
r
e
h
ig
h
ly
d
iv
er
s
e
c
o
n
ce
r
n
i
n
g
th
e
ty
p
es
o
f
cr
o
p
s
an
d
th
eir
n
u
m
b
e
r
p
er
y
ea
r
,
m
ak
in
g
class
if
icatio
n
a
ch
alle
n
g
in
g
task
.
T
h
e
tr
ad
itio
n
al
m
eth
o
d
o
f
s
am
p
le
s
u
r
v
ey
s
u
s
ed
to
d
eter
m
in
e
cr
o
p
d
is
tr
ib
u
tio
n
is
lab
o
r
-
in
ten
s
iv
e
an
d
r
eq
u
ir
es
s
u
b
s
tan
tial
r
eso
u
r
ce
s
,
an
d
its
q
u
ality
an
d
tim
elin
ess
ca
n
n
o
t
alwa
y
s
b
e
g
u
ar
a
n
teed
[
4
]
.
H
o
wev
er
,
s
atellite
r
em
o
te
s
en
s
in
g
h
as
s
h
o
wn
a
h
ig
h
er
p
o
ten
tial
f
o
r
cr
e
atin
g
ac
cu
r
ate
c
r
o
p
m
ap
s
.
W
ith
th
e
in
tr
o
d
u
ctio
n
o
f
th
e
C
o
p
er
n
icu
s
p
r
o
g
r
am
,
wh
ich
o
f
f
er
s
f
r
e
q
u
en
t
an
d
co
s
t
-
ef
f
ec
tiv
e
o
b
s
er
v
atio
n
s
in
o
p
tical
Sen
tin
el
-
2
an
d
m
icr
o
wav
e
Sen
tin
el
-
1
d
o
m
ain
s
,
s
atellite
r
em
o
te
s
e
n
s
in
g
h
as
b
ec
o
m
e
a
n
attr
ac
tiv
e
alter
n
ativ
e
f
o
r
d
eter
m
in
in
g
ac
cu
r
ate
cr
o
p
m
a
p
s
[
5
]
.
Dea
lin
g
with
th
e
p
r
o
ce
s
s
in
g
o
f
m
ass
iv
e
v
o
lu
m
e
o
f
r
e
m
o
te
s
en
s
in
g
d
ata
f
o
r
lar
g
e
ar
ea
s
p
o
s
es
s
ev
er
al
ch
alle
n
g
es,
in
clu
d
in
g
tim
e
-
co
n
s
u
m
i
n
g
task
s
,
h
ig
h
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
7
1
-
1
2
8
0
1272
b
an
d
wid
th
r
eq
u
ir
em
en
ts
f
o
r
d
o
wn
lo
ad
in
g
,
an
d
th
e
n
ee
d
f
o
r
f
ast
co
m
p
u
tin
g
an
d
en
o
r
m
o
u
s
s
to
r
ag
e
ca
p
ac
ity
.
Go
o
g
le
E
ar
t
h
E
n
g
in
e
(
GE
E
)
is
a
clo
u
d
-
b
ased
p
latf
o
r
m
t
h
a
t
p
er
m
its
u
s
er
s
to
d
o
wn
lo
a
d
an
d
p
r
o
ce
s
s
r
em
o
te
s
en
s
in
g
im
ag
er
y
q
u
ick
ly
.
GE
E
h
as
b
ec
o
m
e
in
cr
ea
s
in
g
l
y
p
o
p
u
lar
am
o
n
g
r
esear
ch
e
r
s
d
u
e
t
o
its
av
ailab
ilit
y
o
f
d
if
f
er
en
t
m
ac
h
in
e
lea
r
n
in
g
alg
o
r
ith
m
s
an
d
q
u
ic
k
p
r
o
ce
s
s
in
g
tim
es
[
6
]
,
[
7
]
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t p
r
o
g
r
ess
in
b
u
ild
in
g
m
ac
h
in
e
lea
r
n
in
g
-
b
ased
CC
alg
o
r
ith
m
s
u
tili
zin
g
r
em
o
te
s
en
s
in
g
im
ag
er
y
[
8
]
,
[
9
]
.
T
h
e
r
an
d
o
m
f
o
r
est
(
R
F)
class
if
ier
is
p
ar
ticu
lar
ly
p
o
p
u
la
r
am
o
n
g
r
e
s
ea
r
ch
er
s
d
u
e
to
its
o
u
ts
tan
d
in
g
class
if
icatio
n
ac
cu
r
ac
y
an
d
h
ig
h
p
r
o
ce
s
s
in
g
s
p
ee
d
in
r
em
o
te
s
en
s
in
g
ap
p
licatio
n
s
[
1
0
]
.
C
lo
u
d
co
v
er
p
o
s
es
s
ig
n
if
ica
n
t
ch
allen
g
es
wh
en
it
c
o
m
e
s
to
u
s
in
g
o
p
tical
r
em
o
te
s
e
n
s
in
g
,
b
u
t
s
y
n
th
etic
ap
er
tu
r
e
r
a
d
ar
(
SAR
)
im
ag
es
with
clo
u
d
p
en
etr
ati
o
n
ca
p
ab
ilit
ies
ca
n
o
v
er
c
o
m
e
th
is
is
s
u
e.
Op
tical
d
ata
is
an
ex
ce
llen
t
c
h
o
ice
f
o
r
cr
ea
tin
g
c
r
o
p
m
ap
s
s
in
ce
it
allo
ws
th
e
ca
lcu
latio
n
o
f
v
eg
etatio
n
in
d
ices
an
d
p
r
o
v
id
es
v
alu
ab
le
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
b
i
o
p
h
y
s
ical
p
r
o
ce
s
s
es
o
f
v
eg
etatio
n
.
On
th
e
o
th
er
h
a
n
d
,
SAR
b
ac
k
s
ca
tter
in
g
ec
h
o
ca
n
r
ef
l
ec
t
s
tr
u
ctu
r
al
in
f
o
r
m
atio
n
a
b
o
u
t
th
e
tar
g
et,
b
ased
o
n
t
h
e
f
r
eq
u
en
cy
an
d
p
o
lar
izatio
n
[
1
1
]
.
T
h
e
co
m
b
i
n
atio
n
o
f
o
p
tical
an
d
m
icr
o
wa
v
e
im
ag
er
y
ca
n
b
e
d
ep
l
o
y
ed
t
o
g
et
ac
cu
r
ate
cr
o
p
m
ap
p
in
g
t
h
r
o
u
g
h
f
u
s
io
n
tec
h
n
iq
u
es.
Ma
n
y
r
esear
ch
er
s
h
av
e
p
r
o
p
o
s
ed
th
e
am
al
g
am
at
io
n
o
f
o
p
tical
an
d
m
icr
o
wav
e
i
n
f
o
r
m
atio
n
f
o
r
C
C
[
1
2
]
–
[
1
6
]
,
b
u
t
o
n
ly
a
f
ew
h
a
v
e
f
o
cu
s
ed
o
n
s
m
all
f
ar
m
lan
d
s
.
W
h
ile
r
esear
ch
e
r
s
h
av
e
u
s
ed
o
b
ject
-
o
r
ien
ted
(
O
O)
tech
n
iq
u
es
to
en
h
an
ce
C
C
ac
cu
r
ac
y
[
1
7
]
–
[
1
9
]
,
m
o
s
t
o
f
th
e
wo
r
k
f
o
cu
s
es
o
n
a
s
in
g
le
ty
p
e
o
f
m
icr
o
wav
e
o
r
o
p
tical
r
em
o
te
s
en
s
in
g
im
a
g
es.
Mo
r
eo
v
e
r
,
to
th
e
b
est
o
f
o
u
r
k
n
o
wled
g
e
,
n
o
r
esear
ch
h
as
y
et
ex
p
l
o
r
ed
th
e
u
tili
za
tio
n
o
f
OO
a
p
p
r
o
a
ch
co
m
b
in
e
d
with
t
h
e
am
alg
a
m
atio
n
o
f
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
im
a
g
er
y
f
o
r
s
m
all
f
ar
m
lan
d
s
.
T
h
e
m
ajo
r
o
b
je
ctiv
es o
f
r
esear
ch
ar
e
:
−
E
v
alu
ate
m
ap
p
in
g
o
f
cr
o
p
s
wi
th
Sen
tin
el
-
1
a
n
d
Sen
tin
el
-
2
d
ata
in
r
eg
i
o
n
s
h
av
i
n
g
s
m
all
-
s
ize
f
ar
m
s
u
s
in
g
OO
CC.
−
I
n
v
esti
g
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
OO
an
d
p
ix
el
-
b
ased
(
PB
)
tech
n
iq
u
e
f
o
r
C
C
.
−
Stu
d
y
n
o
r
m
alize
d
d
if
f
e
r
en
ce
v
eg
etatio
n
in
d
e
x
(
NDVI
)
,
g
r
ee
n
n
o
r
m
alize
d
d
if
f
e
r
en
ce
v
eg
etatio
n
in
d
ex
(
GNDV
I
)
,
n
o
r
m
alize
d
d
i
f
f
er
e
n
ce
y
ello
w
i
n
d
ex
(
NDYI
)
,
m
o
d
if
ied
n
o
r
m
alize
d
d
if
f
er
en
ce
wate
r
in
d
e
x
(
MN
DW
I
)
,
an
d
b
ac
k
s
ca
tter
te
m
p
o
r
al
p
r
o
f
iles
o
f
v
ar
io
u
s
cr
o
p
s
.
T
h
e
r
em
ai
n
in
g
p
ap
e
r
is
o
r
g
an
i
ze
d
as
f
o
llo
ws:
i
n
s
ec
tio
n
2
,
w
e
r
ev
iew
t
h
e
wo
r
k
s
r
elate
d
to
CC
,
wh
ile
s
ec
tio
n
3
p
r
o
v
id
es
in
f
o
r
m
atio
n
o
n
d
ata
ac
q
u
is
itio
n
an
d
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
o
f
th
e
C
C
alg
o
r
ith
m
.
I
n
s
ec
tio
n
4
,
we
p
r
esen
t
th
e
o
b
tain
ed
r
esu
lts
f
o
r
C
C
u
s
in
g
d
if
f
er
en
t
co
m
b
in
atio
n
s
o
f
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
d
ata.
Fin
ally
,
in
s
ec
tio
n
5
,
we
s
u
m
m
ar
ize
th
e
f
u
t
u
r
e
s
co
p
e
o
f
th
e
p
r
o
p
o
s
ed
r
esear
c
h
an
d
o
u
r
co
n
clu
s
io
n
s
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
i
s
s
e
c
t
i
o
n
c
o
v
e
r
s
p
r
e
v
i
o
u
s
s
t
u
d
i
es
d
o
n
e
b
y
r
e
s
e
a
r
c
h
e
r
s
f
o
r
C
C
.
P
r
e
v
i
o
u
s
s
t
u
d
ie
s
d
e
m
o
n
s
t
r
a
t
e
t
h
e
f
u
s
i
o
n
a
n
d
s
i
n
g
l
e
s
e
n
s
o
r
m
e
th
o
d
s
b
a
s
e
d
o
n
e
i
t
h
e
r
o
p
t
i
c
a
l
o
r
S
A
R
d
a
t
a
f
o
r
c
r
o
p
m
a
p
p
i
n
g
.
S
o
n
e
t
a
l
.
[
2
0
]
d
e
m
o
n
s
t
r
a
t
e
d
t
h
e
a
p
p
l
i
c
at
i
o
n
o
f
a
s
m
o
o
t
h
b
a
c
k
s
c
a
t
t
e
r
i
n
g
p
r
o
f
i
l
e
f
o
r
r
i
c
e
c
r
o
p
m
a
p
p
i
n
g
u
s
i
n
g
S
e
n
t
i
n
e
l
-
1
A
d
a
t
a.
N
i
h
a
r
e
t
a
l
.
[
2
1
]
i
n
v
e
s
t
i
g
a
t
e
d
t
h
e
c
a
p
a
c
i
t
y
o
f
S
e
n
t
i
n
e
l
-
1
d
a
t
a
f
o
r
m
a
i
z
e
a
n
d
c
o
r
n
c
r
o
p
a
r
e
a
m
a
p
p
i
n
g
u
s
i
n
g
v
e
r
t
i
c
a
l
-
h
o
r
i
z
o
n
t
al
(
VH
)
a
n
d
v
e
r
t
i
c
a
l
-
v
e
r
ti
c
a
l
(
VV
)
b
a
c
k
s
c
a
t
te
r
i
n
g
d
e
c
is
i
o
n
t
r
ee
cl
a
s
s
i
f
ie
r
r
ec
o
r
d
e
d
t
h
e
a
c
c
u
r
a
cy
o
f
7
5
.
0
%
f
o
r
V
H
.
I
n
[
2
2
]
–
[
2
4
]
,
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
w
e
r
e
e
v
a
l
u
a
t
e
d
f
o
r
C
C
u
s
i
n
g
S
AR
d
a
t
a
.
R
es
e
a
r
c
h
b
y
K
o
b
a
y
a
s
h
i
et
a
l
.
[
2
5
]
,
u
s
i
n
g
t
h
e
S
e
n
ti
n
e
l
-
2
d
a
t
a
a
u
t
h
o
r
s
,
c
o
m
p
u
t
e
d
a
n
d
e
v
a
l
u
a
t
e
d
9
1
p
u
b
l
is
h
e
d
s
p
e
c
t
r
al
i
n
d
i
c
es
f
o
r
C
C
a
n
d
c
o
n
c
l
u
d
e
d
t
h
a
t
C
C
b
a
s
e
d
o
n
s
p
e
c
t
r
a
l i
n
d
i
c
es
g
a
v
e
g
o
o
d
r
e
s
u
l
t
s
.
S
ai
n
i
a
n
d
G
h
o
s
h
[
2
6
]
c
o
n
c
l
u
d
e
d
t
h
a
t
t
h
e
N
I
R
b
a
n
d
i
n
S
e
n
t
i
n
e
l
-
2
d
a
t
a
p
l
a
y
e
d
t
h
e
m
o
s
t
p
r
o
m
i
n
e
n
t
r
o
l
e
i
n
C
C
r
e
s
u
l
t
s
c
o
n
c
l
u
d
i
n
g
t
h
a
t
o
v
e
r
a
l
l
C
C
a
c
c
u
r
a
c
y
o
f
S
e
n
t
i
n
e
l
-
2
i
m
a
g
e
r
y
o
b
t
a
i
n
e
d
b
y
RF
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
i
s
8
4
.
2
2
%
a
n
d
8
1
.
8
5
%
,
r
e
s
p
e
c
t
i
v
e
l
y
.
So
n
o
b
e
et
a
l.
[
2
7
]
co
n
clu
d
ed
th
at
f
o
r
d
etailed
cr
o
p
m
ap
p
in
g
,
v
eg
etatio
n
in
d
ices
ca
lcu
lated
f
r
o
m
th
e
o
r
ig
in
al
r
ef
lecta
n
ce
o
f
Sen
tin
el
-
2
co
n
tr
ib
u
ted
s
ig
n
if
ican
tly
.
Ma
zz
ia
et
a
l.
[
2
8
]
p
r
o
p
o
s
ed
th
e
ap
p
licatio
n
o
f
r
ec
u
r
r
en
t
an
d
co
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
s
f
o
r
lan
d
co
v
er
a
n
d
C
C
u
s
in
g
Sen
tin
el
-
2
d
ata.
Sen
tin
el
-
2
r
e
d
ed
g
e
b
an
d
1
an
d
s
h
o
r
twav
e
in
f
r
ar
e
d
b
an
d
1
h
a
d
s
h
o
wn
g
r
ea
ter
a
cc
u
r
ac
y
in
cr
o
p
m
a
p
p
in
g
.
T
h
e
am
alg
am
atio
n
o
f
o
p
tical
an
d
SAR
d
ata
o
f
f
er
s
a
co
m
p
r
eh
e
n
s
iv
e
r
ep
r
esen
tatio
n
o
f
s
tr
u
ctu
r
al
an
d
b
io
p
h
y
s
ica
l
in
f
o
r
m
atio
n
a
b
o
u
t
o
b
jects,
im
p
r
o
v
in
g
C
C
ac
cu
r
ac
y
.
Ma
n
y
r
esear
ch
e
r
s
h
av
e
u
s
ed
o
p
tical
an
d
SAR
d
ata
in
teg
r
atio
n
f
o
r
C
C
[
1
2
]
‒
[
1
6
]
.
T
h
e
ab
o
v
e
-
m
e
n
tio
n
ed
C
C
m
eth
o
d
s
ar
e
PB
an
d
p
er
f
o
r
m
C
C
b
y
d
er
i
v
in
g
t
h
e
t
em
p
o
r
al
o
p
tical
o
r
m
icr
o
wav
e
f
ea
tu
r
es
o
f
im
a
g
e
elem
en
ts
.
PB
C
C
tech
n
iq
u
es
n
eg
lect
th
e
s
p
atial
co
r
r
elatio
n
am
o
n
g
a
d
jace
n
t
p
ix
el
elem
en
ts
[
2
9
]
,
d
u
e
to
wh
ich
th
ese
tech
n
iq
u
es
ar
e
s
en
s
itiv
e
to
s
alt
-
an
d
-
p
ep
p
e
r
n
o
is
e
an
d
h
av
e
h
ig
h
er
r
eq
u
ir
em
e
n
ts
f
o
r
co
m
p
u
tin
g
p
o
wer
[
3
0
]
.
T
h
e
OO
C
C
tech
n
i
q
u
es
b
ased
o
n
r
em
o
te
s
en
s
in
g
im
ag
es
ca
n
lo
wer
th
e
s
alt
-
an
d
-
p
ep
p
e
r
n
o
is
e
[
1
7
]
,
[
1
8
]
.
Yan
g
et
a
l.
[
1
9
]
d
em
o
n
s
tr
ate
th
e
p
o
ten
tial
o
f
s
im
p
le
n
o
n
-
iter
ativ
e
clu
s
ter
in
g
(
SNI
C
)
s
u
p
er
p
ix
el
s
eg
m
en
tatio
n
tech
n
iq
u
e
f
o
r
h
i
g
h
-
r
eso
lu
tio
n
cr
o
p
m
a
p
p
in
g
b
ased
o
n
Sen
tin
el
-
1
d
ata.
A
1
0
%
in
cr
ea
s
e
in
ac
c
u
r
ac
y
was
o
b
tain
ed
i
n
[
3
1
]
u
ti
lizin
g
co
m
p
o
s
ite
Sen
tin
el
-
1
im
ag
es
an
d
th
e
OO
ca
teg
o
r
izatio
n
tech
n
iq
u
e.
I
n
co
n
cl
u
s
io
n
,
r
esear
ch
c
o
m
b
in
in
g
o
p
tical
an
d
SAR
ch
ar
ac
ter
is
tics
o
f
cr
o
p
ty
p
e
m
a
p
p
in
g
h
as
r
ec
eiv
ed
m
u
c
h
atten
tio
n
.
T
h
e
f
o
llo
win
g
p
o
s
s
ib
le
s
et
o
f
co
n
ce
r
n
s
h
as b
ee
n
f
o
u
n
d
in
p
r
ev
io
u
s
r
esear
ch
wo
r
k
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
r
o
p
cla
s
s
ifica
tio
n
u
s
in
g
o
b
je
ct
-
o
r
ien
ted
meth
o
d
a
n
d
Go
o
g
l
e
E
a
r
th
E
n
g
in
e
(
Gee
ta
T.
Desa
i
)
1273
−
Ma
n
y
r
esear
c
h
er
s
h
a
v
e
p
r
o
p
o
s
ed
th
e
am
al
g
am
atio
n
o
f
o
p
ti
ca
l
an
d
m
icr
o
wav
e
in
f
o
r
m
ati
o
n
f
o
r
C
C
,
b
u
t
o
n
ly
a
f
ew
h
av
e
f
o
cu
s
ed
o
n
s
m
all
f
ar
m
lan
d
s
.
−
Mo
s
t
cu
r
r
en
t
s
tu
d
ies
o
n
h
eter
o
g
en
eo
u
s
f
ar
m
lan
d
s
ar
e
b
ased
o
n
PB
C
C
m
eth
o
d
wh
ich
s
u
f
f
er
f
r
o
m
s
alt
an
d
p
ep
p
er
n
o
is
e.
−
Mo
s
t o
f
th
e
wo
r
k
f
o
c
u
s
es o
n
a
s
in
g
le
ty
p
e
o
f
m
icr
o
wav
e
o
r
o
p
tical
r
em
o
te
s
en
s
in
g
im
ag
es.
T
h
er
e
h
as b
ee
n
less
atten
tio
n
g
iv
en
to
th
e
a
d
v
an
tag
es th
at
ca
n
b
e
o
b
tain
e
d
b
y
f
u
s
in
g
d
if
f
er
e
n
t ty
p
es o
f
im
a
g
es.
T
h
e
p
r
o
p
o
s
ed
wo
r
k
ex
p
lo
its
OO
ap
p
r
o
ac
h
f
u
s
io
n
o
f
SAR
an
d
o
p
tical
d
ata
f
o
r
C
C
.
T
h
e
ex
p
er
im
en
t
is
f
o
cu
s
ed
o
n
s
m
allh
o
ld
er
ag
r
icu
ltu
r
al
lan
d
s
ca
p
es in
r
u
r
al
Ma
h
ar
ash
tr
a.
3.
M
E
T
H
O
D
T
h
e
F
ig
u
r
e
1
illu
s
tr
ates th
e
ad
ap
ted
m
eth
o
d
o
lo
g
ical
ap
p
r
o
ac
h
f
o
r
C
C
in
th
e
in
v
esti
g
atio
n
ar
ea
,
wh
ich
in
v
o
lv
es
u
s
in
g
v
ar
i
o
u
s
f
ea
tu
r
e
s
ex
tr
ac
ted
f
r
o
m
Sen
tin
el
-
1
a
n
d
Sen
tin
el
-
2
d
ata.
T
h
e
ap
p
r
o
ac
h
co
m
p
r
is
es
f
o
u
r
m
ain
s
tep
s
:
i
)
ac
q
u
is
itio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
o
f
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
d
ata,
ii
)
d
ata
p
r
ep
ar
atio
n
,
wh
e
r
e
v
eg
etatio
n
in
d
ices
ar
e
ca
lcu
lated
f
r
o
m
tim
e
s
er
ies
o
p
tical
a
n
d
SAR
im
ag
es,
iii
)
CC
,
wh
e
r
e
ex
tr
ac
ted
o
p
tica
l
an
d
SAR
f
ea
tu
r
es
a
r
e
m
e
r
g
e
d
,
an
d
CC
is
p
er
f
o
r
m
ed
u
s
in
g
OO
an
d
PB
ap
p
r
o
ac
h
in
d
i
f
f
er
en
t
s
ce
n
a
r
io
s
o
n
GE
E
p
latf
o
r
m
u
s
in
g
R
F c
lass
i
f
ier
,
an
d
iv
)
ac
cu
r
ac
y
ass
ess
m
en
t o
f
th
e
r
esu
ltin
g
class
if
ied
m
ap
s
.
Fig
u
r
e
1
.
Flo
wch
ar
t
o
f
m
et
h
o
d
o
lo
g
y
3
.
1
.
Sentinel
-
1
a
nd
Sentinel
-
2
da
t
a
a
cquis
it
io
n a
nd
pre
pr
o
ce
s
s
ing
T
h
e
s
tu
d
y
e
n
co
m
p
ass
es
an
ar
ea
o
f
ar
o
u
n
d
7
4
3
k
m
²
with
7
0
%
o
f
th
e
la
n
d
d
e
d
icate
d
to
a
g
r
icu
ltu
r
e
.
T
h
e
lan
d
s
ca
p
e
is
h
eter
o
g
en
e
o
u
s
an
d
co
m
p
le
x
,
with
ch
ick
p
ea
s
an
d
wh
ea
t
b
ein
g
th
e
d
o
m
in
an
t
cr
o
p
s
g
r
o
wn
.
T
h
e
ag
r
icu
ltu
r
al
ar
ea
is
m
o
s
tly
co
m
p
o
s
ed
o
f
s
m
all
f
a
r
m
s
th
at
ar
e
less
th
an
a
h
ec
tar
e
in
s
i
ze
.
T
h
e
s
tu
d
y
a
r
ea
is
s
itu
ated
at
latitu
d
e
1
9
.
9
1
2
6
7
6
an
d
lo
n
g
itu
d
e
7
7
.
5
6
6
9
1
0
.
T
h
e
s
o
il
in
th
e
ar
ea
h
as
a
clay
ey
lo
am
y
tex
tu
r
e
an
d
is
s
o
m
ewh
at
alk
alin
e,
co
n
tain
in
g
ca
lciu
m
ca
r
b
o
n
ate.
T
h
e
cli
m
ate
in
th
e
ar
ea
is
h
o
t
an
d
d
r
y
d
u
r
i
n
g
th
e
s
u
m
m
er
,
with
a
m
ea
n
m
ax
im
u
m
tem
p
er
atu
r
e
o
f
4
1
°C
in
Ma
y
a
n
d
a
tem
p
e
r
atu
r
e
r
an
g
e
o
f
1
2
-
22
°C
in
win
ter
.
T
h
e
an
n
u
al
r
ain
f
all
in
th
e
r
eg
io
n
is
ty
p
ically
b
etwe
en
8
5
0
an
d
1
,
150
m
m
.
T
h
e
s
tu
d
y
ar
ea
in
cl
u
d
es
th
e
v
illag
es
o
f
W
ar
u
d
an
d
B
h
u
jla
in
Pu
s
ad
,
w
h
er
e
ag
r
ic
u
ltu
r
e
is
a
p
r
im
a
r
y
s
o
u
r
ce
o
f
in
co
m
e.
3
.
1
.
1
.
Sentinel
-
1
da
t
a
a
cquis
it
io
n a
nd
prepro
ce
s
s
i
ng
T
h
e
s
tu
d
y
u
tili
ze
d
a
co
m
b
i
n
at
io
n
o
f
o
p
tical
an
d
SAR
im
ag
es
f
o
r
C
C
.
T
h
e
d
ataset
f
o
r
g
r
o
u
n
d
r
an
g
e
d
etec
ted
(
GR
D)
with
Sen
tin
el
-
1
SAR
was
ac
q
u
ir
ed
th
r
o
u
g
h
th
e
GE
E
cl
o
u
d
p
latf
o
r
m
,
co
n
t
ain
in
g
all
im
ag
es
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
7
1
-
1
2
8
0
1274
th
e
s
tu
d
y
a
r
ea
b
etwe
en
J
an
u
ar
y
to
Ap
r
il
2
0
2
2
.
T
h
e
s
tu
d
y
em
p
lo
y
ed
in
ter
f
er
e
n
ce
wid
eb
an
d
m
o
d
e
with
in
cid
en
ce
a
n
g
le
v
ar
iatio
n
o
f
3
5
°
to
4
0
°
to
ac
q
u
ir
e
th
e
Sen
tin
el
-
1
SAR
GR
D
d
ataset,
h
av
in
g
a
s
p
atial
r
eso
lu
tio
n
o
f
1
0
m
an
d
b
r
ea
d
t
h
o
f
2
5
0
k
m
.
T
h
e
im
ag
es
u
n
d
er
wen
t
p
r
ep
r
o
ce
s
s
in
g
o
n
th
e
GE
E
p
latf
o
r
m
with
in
th
e
Sen
tin
el
-
1
to
o
lb
o
x
.
T
o
m
ain
tain
im
ag
e
s
h
ar
p
n
ess
an
d
m
in
im
ize
s
p
ec
k
le,
a
r
ef
in
ed
L
ee
f
ilter
[
3
2
]
was
u
tili
ze
d
to
f
ilter
th
e
Sen
tin
el
-
1
im
ag
es o
n
th
e
GE
E
p
latf
o
r
m
.
3
.
1
.
2
.
Sentinel
-
2
da
t
a
a
cquis
it
io
n a
nd
prepro
ce
s
s
i
ng
T
o
co
n
d
u
ct
r
esear
c
h
,
we
u
til
ized
Sen
tin
el
-
2
o
r
th
o
r
ec
tifie
d
im
ag
es
f
r
o
m
th
e
GE
E
p
latf
o
r
m
.
T
h
e
im
ag
es
wer
e
ac
q
u
ir
e
d
b
etw
ee
n
J
an
u
ar
y
to
Ap
r
il
2
0
2
2
o
v
er
v
illag
es
o
f
B
h
u
jla
an
d
W
ar
u
d
in
Pu
s
ad
,
Ma
h
ar
ash
tr
a.
I
m
ag
es
wer
e
c
o
llected
as
a
p
ar
t
o
f
th
e
Sen
tin
el
-
2
m
u
lti
-
s
p
ec
tr
al
in
s
tr
u
m
en
t
(
MSI
)
l
e
v
el
-
1
C
d
ataset.
T
h
e
d
ataset
co
n
s
is
ts
o
f
1
3
to
p
-
of
-
atm
o
s
p
h
e
r
e
r
e
f
lecta
n
ce
MSI
b
an
d
s
,
wh
ich
ar
e
s
ca
led
b
y
a
f
ac
to
r
o
f
1
,
0
0
0
.
W
e
also
u
s
ed
th
e
q
u
ality
ass
ess
m
en
t b
an
d
(
QA6
0
)
t
o
ex
clu
d
e
an
y
in
v
alid
o
b
s
er
v
atio
n
s
.
3
.
1
.
3
.
F
ield da
t
a
B
etwe
en
J
an
u
ar
y
an
d
A
p
r
il
2
0
2
2
,
a
tea
m
o
f
r
esear
ch
er
s
v
is
ited
th
e
v
illag
es
o
f
B
h
u
jla
an
d
W
ar
u
d
in
Pu
s
ad
,
Ma
h
ar
ash
tr
a
to
co
llect
f
ield
d
ata
ab
o
u
t
cr
o
p
ty
p
e
an
d
lan
d
co
v
er
.
T
h
e
y
u
s
ed
a
GPS
d
ev
ice
to
r
ec
o
r
d
th
e
ce
n
tr
e
an
d
f
o
u
r
co
r
n
er
s
co
o
r
d
in
ates
o
f
ea
ch
f
a
r
m
,
in
ad
d
itio
n
to
th
e
n
am
e
o
f
th
e
cr
o
p
an
d
s
u
p
p
lem
en
ta
r
y
d
ata
ab
o
u
t
v
eg
etatio
n
an
d
s
tr
u
ctu
r
es
with
in
ea
ch
f
ar
m
.
W
h
ea
t,
ch
ick
p
ea
,
an
d
wate
r
m
el
o
n
wer
e
a
m
o
n
g
th
e
cr
o
p
s
o
b
s
er
v
e
d
an
d
r
ec
o
r
d
e
d
.
Af
ter
th
e
f
ield
s
u
r
v
ey
,
t
h
e
GPS
co
o
r
d
in
ates
o
f
f
ar
m
b
o
u
n
d
a
r
ies
wer
e
u
p
lo
ad
ed
in
to
Ar
cGI
S
as
a
p
o
in
t
s
h
ap
ef
ile
an
d
o
v
er
laid
o
n
to
th
e
GE
E
f
o
r
d
o
w
n
lo
ad
in
g
th
e
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
d
atasets
.
7
0
%
o
f
th
e
c
o
llected
g
r
o
u
n
d
t
r
u
th
d
ata
was
ap
p
lie
d
to
tr
ain
th
e
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el,
wh
ile
th
e
r
em
ain
in
g
3
0
% wa
s
u
s
ed
f
o
r
v
alid
atio
n
.
3
.
2
.
Da
t
a
p
re
pa
ra
t
i
o
n
3
.
2
.
1
.
O
ptic
a
l f
e
a
t
ures
T
h
e
g
r
o
wth
o
f
cr
o
p
s
ca
n
b
e
a
s
s
es
s
ed
th
r
o
u
g
h
s
p
ec
tr
al
i
n
d
ic
es
th
at
ar
e
s
en
s
itiv
e
to
v
eg
etatio
n
.
T
h
e
NDVI
is
h
ig
h
ly
r
esp
o
n
s
iv
e
to
leaf
ar
ea
in
d
ex
a
n
d
c
h
lo
r
o
p
h
y
l
l
p
r
esen
t
in
c
r
o
p
s
wh
ich
m
ak
e
s
it
an
id
ea
l
m
etr
i
c
to
ev
alu
ate
th
e
g
r
ee
n
n
ess
o
f
v
eg
etatio
n
[
3
3
]
,
[
3
4
]
.
A
r
e
s
ea
r
ch
s
tu
d
y
h
as
f
o
u
n
d
th
at
th
e
MN
DW
I
ca
n
ef
f
ec
tiv
ely
d
if
f
e
r
en
tiate
b
etwe
en
o
p
en
s
u
r
f
ac
e
wate
r
b
o
d
ies
an
d
v
eg
etatio
n
an
d
s
o
ils
[
3
5
]
.
GNDV
I
is
h
ig
h
ly
s
en
s
itiv
e
to
ch
lo
r
o
p
h
y
ll,
ac
co
r
d
in
g
to
r
esear
ch
[
3
6
]
,
[
3
7
]
.
I
n
r
ec
en
t
y
ea
r
s
,
th
e
NDYI
h
a
s
b
ee
n
ex
ten
s
iv
ely
u
tili
ze
d
f
o
r
ca
lc
u
latin
g
f
o
liag
e
co
v
er
[
3
8
]
.
Ap
a
r
t
f
r
o
m
th
e
o
r
ig
in
al
Sen
tin
el
-
2
b
a
n
d
s
,
f
o
u
r
p
r
o
m
i
n
en
t
v
eg
etatio
n
in
d
ices w
er
e
ca
lcu
lated
,
in
clu
d
in
g
th
e
NDVI
,
ND
YI
,
GNDV
I
,
an
d
MN
DW
I
.
NDVI
=
−
+
(
1
)
GNDV
I
=
−
+
(
2
)
NDYI
=
−
+
(
3
)
MN
DW
I
=
−
+
(
4
)
3
.
2
.
2
.
Ra
da
r
f
e
a
t
ure
On
ce
th
e
SAR
im
ag
e
was
ac
q
u
ir
ed
u
s
in
g
GE
E
p
latf
o
r
m
,
V
V
an
d
VH
b
an
d
s
wer
e
ex
tr
ac
t
ed
f
o
r
CC
.
R
ain
an
d
clo
u
d
c
o
v
er
d
o
n
'
t
af
f
ec
t
SAR
,
wh
ich
is
ca
p
a
b
le
o
f
tak
in
g
im
ag
es
d
ay
an
d
n
ig
h
t.
T
h
e
s
tu
d
y
f
u
lly
u
tili
ze
d
th
e
b
en
ef
its
o
f
SAR
p
ictu
r
es
b
y
u
tili
zin
g
all
win
te
r
wh
ea
t
o
b
s
er
v
atio
n
.
Plan
t
g
r
o
wth
cy
cle
-
r
elate
d
ch
an
g
es
in
th
e
wate
r
co
n
ten
t
o
f
th
e
ca
n
o
p
y
ar
e
r
ef
lecte
d
in
VV
an
d
VH.
b
an
d
h
en
ce
V
V
an
d
VH
p
r
o
v
id
e
m
o
r
e
in
f
o
r
m
atio
n
ab
o
u
t c
r
o
p
s
tr
u
ctu
r
e
an
d
ch
ar
ac
te
r
is
tics
,
s
i
g
n
if
ican
tly
im
p
r
o
v
i
n
g
C
C
alg
o
r
ith
m
s
'
ac
cu
r
ac
y
.
3
.
3
.
Cro
p
c
la
s
s
if
ica
t
io
n
3
.
3
.
1
.
Dif
f
er
ent
f
ea
t
ure
co
m
b
ina
t
io
ns
Sev
er
al
o
p
tical
an
d
r
ad
a
r
f
ea
t
u
r
e
co
m
b
in
atio
n
s
wer
e
e
v
alu
a
ted
f
o
r
th
e
p
u
r
p
o
s
e
o
f
c
o
m
p
ar
is
o
n
.
T
h
e
g
am
m
a
an
d
co
s
t
p
ar
am
eter
s
ar
e
s
u
itab
ly
tu
n
ed
b
y
th
e
R
F
alg
o
r
ith
m
u
s
in
g
a
g
r
id
s
ea
r
ch
an
d
8
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
b
ased
o
n
th
e
tr
ain
in
g
d
ata.
Nex
t,
we
p
er
f
o
r
m
ed
th
e
R
F
f
o
r
ev
er
y
co
m
b
in
atio
n
o
f
d
ata.
T
h
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
m
o
d
el
was
co
m
p
ar
ed
b
y
e
x
am
in
in
g
th
e
o
v
e
r
all
ac
cu
r
ac
y
(
OA
)
,
p
r
o
d
u
ce
r
'
s
ac
cu
r
ac
y
(
PA)
,
u
s
er
'
s
ac
cu
r
ac
y
(
UA
)
,
an
d
Kap
p
a
co
ef
f
icien
t
(
KC
)
,
f
o
llo
win
g
d
if
f
er
e
n
t
co
m
b
in
atio
n
s
o
f
o
p
tical
an
d
m
icr
o
wav
e
f
ea
tu
r
es
wer
e
ex
p
l
o
r
ed
to
i
d
en
tify
t
h
e
m
o
s
t
im
p
o
r
tan
t
r
ad
a
r
an
d
o
p
tical
f
ea
tu
r
es
f
o
r
ac
cu
r
ate
c
r
o
p
m
ap
p
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
r
o
p
cla
s
s
ifica
tio
n
u
s
in
g
o
b
je
ct
-
o
r
ien
ted
meth
o
d
a
n
d
Go
o
g
l
e
E
a
r
th
E
n
g
in
e
(
Gee
ta
T.
Desa
i
)
1275
C
o
m
b
in
atio
n
1
: V
H,
VV
SAR
f
ea
tu
r
es
C
o
m
b
in
atio
n
2
:
Sen
tin
el
-
2
b
a
n
d
s
C
o
m
b
in
atio
n
3
:
Sen
tin
el
-
2
b
a
n
d
s
an
d
NDVI
C
o
m
b
in
atio
n
4
:
Sen
tin
el
-
2
b
a
n
d
s
an
d
GNDV
I
C
o
m
b
in
atio
n
5
:
Sen
tin
el
-
2
an
d
NDYI
C
o
m
b
in
atio
n
6
:
Sen
tin
el
-
2
an
d
MN
DW
I
C
o
m
b
in
atio
n
7
: O
n
l
y
Sen
tin
el
-
2
b
an
d
s
an
d
NDVI
,
GNDV
I
,
NDYI
an
d
MN
DW
I
C
o
m
b
in
atio
n
8
: Wi
th
th
e
f
u
s
io
n
o
f
all
Sen
tin
el
-
1
an
d
Sen
tin
e
l
-
2
f
ea
tu
r
es.
3
.
3
.
2
.
P
ix
el
ba
s
ed
cla
s
s
if
ica
t
io
n
C
o
n
v
en
tio
n
al
PB
class
if
icatio
n
is
a
p
o
p
u
lar
m
eth
o
d
f
o
r
g
en
er
atin
g
cr
o
p
m
ap
s
.
T
h
e
PB
class
if
icatio
n
is
p
er
f
o
r
m
ed
at
th
e
p
i
x
el
lev
el,
wh
ich
s
o
lely
r
elies
o
n
th
e
s
p
ec
tr
al
d
ata
o
f
in
d
iv
id
u
al
p
ix
els.
I
n
PB
class
if
icatio
n
,
ea
ch
p
ix
el,
th
e
s
m
allest
u
n
it
in
th
e
im
ag
e,
is
ca
teg
o
r
ized
in
to
a
p
r
ed
ef
in
ed
class
u
s
in
g
a
tr
ain
ed
m
o
d
el.
Salt
an
d
p
ep
p
er
n
o
is
e
co
u
ld
b
e
p
r
o
d
u
ce
d
b
y
th
e
co
n
v
en
tio
n
al
PB
ca
teg
o
r
izatio
n
a
p
p
r
o
ac
h
,
p
ar
ticu
la
r
ly
f
o
r
Sen
tin
el
-
1
r
a
d
ar
d
ata.
T
h
i
s
is
s
u
e
is
les
s
en
ed
b
y
th
e
o
b
j
ec
t
-
b
ased
ap
p
r
o
ac
h
,
wh
ich
d
i
v
id
es
th
e
im
ag
e
in
to
d
is
tin
ct
r
eg
io
n
s
o
r
o
b
jects b
ased
o
n
p
r
ed
eter
m
in
ed
cr
iter
ia
b
y
tak
in
g
in
to
ac
co
u
n
t th
e
n
eig
h
b
o
r
in
g
in
f
o
r
m
atio
n
o
f
a
g
iv
e
n
p
ix
el.
3
.
3
.
3
.
O
bje
ct
ba
s
ed
cla
s
s
if
ica
t
io
n
State
-
of
-
th
e
-
ar
t
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
ca
n
e
x
ec
u
te
PB
an
d
OO
class
if
icatio
n
m
eth
o
d
s
o
n
GE
E
.
I
n
th
e
s
tu
d
y
p
r
esen
ted
,
an
R
F
class
if
ier
was
u
s
ed
to
i
m
p
lem
en
t
PB
an
d
OO
class
if
icatio
n
ap
p
r
o
ac
h
es,
with
th
e
n
u
m
b
er
o
f
tr
ee
s
s
et
t
o
1
0
0
.
An
in
b
u
ilt
GE
E
im
ag
e
s
eg
m
en
tatio
n
alg
o
r
ith
m
was
u
s
ed
to
im
p
lem
e
n
t
SNI
C
im
ag
e
s
eg
m
en
tatio
n
,
wh
ich
is
an
OO
im
ag
er
y
s
eg
m
en
tatio
n
m
eth
o
d
th
at
g
r
o
u
p
s
s
p
atial
o
b
jects
w
ith
h
ig
h
u
n
if
o
r
m
ity
.
First,
a
ce
n
tr
o
id
p
ix
el
i
n
itializatio
n
is
d
o
n
e
o
n
t
h
e
im
a
g
e'
s
r
eg
u
lar
g
r
i
d
.
T
h
en
,
th
e
d
ep
en
d
e
n
ce
o
f
ea
ch
p
ix
el
with
r
esp
ec
t
to
th
e
ce
n
tr
o
id
is
ascer
tain
ed
u
s
in
g
th
e
d
is
tan
ce
b
etwe
en
p
ix
els
in
th
e
f
iv
e
-
d
im
en
s
io
n
al
s
p
ac
e
o
f
co
l
o
u
r
an
d
s
p
atial
co
o
r
d
in
ates.
U
ltima
tely
,
th
e
d
is
tan
ce
cr
ea
tes
ef
f
ec
tiv
e,
co
m
p
ac
t,
an
d
alm
o
s
t u
n
i
f
o
r
m
p
o
ly
g
o
n
s
b
y
in
teg
r
atin
g
th
e
n
o
r
m
alis
ed
s
p
atial
an
d
co
lo
u
r
d
is
tan
ce
s
[
1
9
]
,
[
3
1
]
.
T
h
e
SNI
C
alg
o
r
ith
m
was
u
s
ed
to
c
o
m
p
ar
e
th
e
p
e
r
f
o
r
m
an
c
e
o
f
o
p
tical
an
d
SAR
f
ea
tu
r
e
s
f
o
r
PB
class
if
icatio
n
.
T
h
e
alg
o
r
ith
m
g
en
er
ates
a
r
eg
u
lar
g
r
i
d
o
f
s
ee
d
s
u
s
in
g
th
e
"I
m
ag
e.
Seg
m
en
tatio
n
.
s
ee
d
Gr
id
"
f
u
n
ctio
n
.
T
h
e
s
p
ac
in
g
o
f
s
u
p
e
r
p
ix
el
s
ee
d
lo
ca
tio
n
s
af
f
ec
ts
t
h
e
clu
s
ter
s
ize
an
d
ca
n
b
e
ad
j
u
s
ted
to
ac
h
iev
e
th
e
b
est
r
esu
lts
.
T
h
e
alg
o
r
ith
m
was
test
ed
f
o
r
d
if
f
e
r
en
t
v
al
u
es
o
f
s
ee
d
s
p
ac
in
g
to
d
eter
m
in
e
t
h
e
b
est
v
alu
e
b
ased
on
OA
.
T
o
p
r
o
d
u
ce
c
o
m
p
ac
t
c
lu
s
ter
s
,
th
e
"c
o
m
p
ac
tn
ess
f
ac
t
o
r
"
p
ar
a
m
eter
was
s
et
to
a
h
ig
h
er
v
alu
e,
wh
ile
th
e
"c
o
n
n
ec
tiv
ity
"
p
ar
am
eter
was
s
et
to
8
to
a
v
o
id
tile
b
o
u
n
d
ar
y
ar
tifa
cts.
Ad
d
itio
n
ally
,
a
"n
eig
h
b
o
u
r
h
o
o
d
s
"
p
ar
am
eter
was
u
s
ed
to
en
s
u
r
e
th
at
th
e
tiles
d
id
n
o
t
o
v
e
r
lap
.
I
n
th
is
s
tu
d
y
,
th
e
SNI
C
p
ar
a
m
eter
s
wer
e
s
et
to
co
m
p
ac
tn
ess
=
0
,
co
n
n
ec
tiv
ity
=
8
,
an
d
n
eig
h
b
o
u
r
h
o
o
d
s
ize
=
2
5
6
.
Fin
ally
,
t
h
e
v
is
u
aliza
tio
n
s
ca
le
was
f
o
u
n
d
to
s
ig
n
if
ican
tly
im
p
ac
t th
e
ac
c
u
r
ac
y
o
f
th
e
SNI
C
alg
o
r
ith
m
f
o
r
OO
class
if
icatio
n
.
3
.
3
.
4
.
R
a
nd
o
m
f
o
re
s
t
cla
s
s
if
ier
R
F
is
a
s
u
p
er
v
is
ed
m
ac
h
i
n
e
le
ar
n
in
g
m
o
d
el
th
at
d
o
es
n
o
t
f
o
l
lo
w
th
e
n
o
r
m
al
d
is
tr
ib
u
tio
n
o
f
p
r
ed
icto
r
v
ar
iab
les.
I
t
in
teg
r
ates
lar
g
e
d
ec
is
io
n
tr
ee
s
an
d
em
p
lo
y
s
an
ad
ju
s
tab
le
am
o
u
n
t
o
f
p
r
e
d
icto
r
v
ar
iab
les.
R
F
is
b
u
ilt
u
s
in
g
th
e
b
o
o
ts
tr
ap
p
in
g
tech
n
iq
u
e,
wh
er
e
ea
c
h
d
ec
is
io
n
tr
ee
is
f
it
ted
b
ased
o
n
in
-
b
ag
d
ata.
Fo
r
class
if
icatio
n
,
two
v
ar
iab
les
ar
e
to
b
e
s
et
f
o
r
th
e
R
F
class
if
ier
,
n
tr
ee
wh
ich
s
tan
d
s
f
o
r
th
e
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
s
g
r
o
wn
a
n
d
m
tr
y
,
wh
ich
s
tan
d
s
f
o
r
th
e
n
u
m
b
er
o
f
v
ar
iab
les
u
s
ed
at
ev
er
y
s
p
lit.
A
tr
ee
is
tr
im
m
ed
o
n
l
y
af
ter
it
is
f
u
lly
d
ev
elo
p
e
d
an
d
w
h
en
its
n
o
d
es
ar
e
p
u
r
e
a
n
d
ca
n
b
e
u
s
ed
f
o
r
p
r
ed
ictio
n
.
R
F
was
s
elec
ted
f
o
r
its
ad
v
an
tag
es,
in
clu
d
in
g
th
e
ab
ilit
y
to
h
an
d
le
la
r
g
e
d
ata
s
ets,
r
esi
s
tan
ce
to
n
o
is
e
an
d
o
u
tlier
s
,
an
d
lo
w
co
m
p
u
tatio
n
al
co
m
p
le
x
ity
co
m
p
ar
e
d
to
o
t
h
er
en
s
em
b
le
m
eth
o
d
s
[
3
9
]
.
3
.
4
.
Acc
ura
cy
a
s
s
esem
ent
T
h
e
f
o
llo
win
g
m
etr
ics
ar
e
em
p
lo
y
ed
to
ass
ess
th
e
alg
o
r
ith
m
p
r
esen
ted
in
th
is
wo
r
k
:
O
A,
KC
,
UA,
an
d
PA.
T
h
e
OA
is
d
eter
m
in
e
d
b
y
ca
lcu
latin
g
th
e
r
atio
o
f
c
o
r
r
ec
tly
class
if
ied
ce
lls
to
th
e
to
tal
n
u
m
b
er
o
f
ce
lls
[
4
0
]
.
T
h
e
KC
is
a
s
tatis
tical
m
ea
s
u
r
e
o
f
in
ter
class
ag
r
ee
m
en
t
th
at
ass
ess
es
clas
s
if
icatio
n
ac
cu
r
ac
y
u
s
in
g
al
l
d
ata
av
ailab
le
i
n
th
e
co
n
f
u
s
io
n
m
atr
ix
.
T
h
e
PA
o
f
a
m
ap
is
d
ef
in
e
d
f
r
o
m
th
e
m
a
p
p
r
o
d
u
ce
r
'
s
p
o
in
t
o
f
v
iew,
wh
er
ea
s
UA
is
d
ef
in
ed
f
r
o
m
t
h
e
u
s
er
'
s
p
o
in
t
o
f
v
iew
[
3
6
]
,
[
4
0
]
.
T
h
e
f
o
r
m
u
las
f
o
r
OA,
KC
,
PA
an
d
UA
ar
e
g
iv
en
b
y
ex
p
r
ess
io
n
(
5
)
-
(
8
)
r
e
s
p
ec
tiv
ely
.
=
∑
=
1
=
1
∑
=
1
(
5
)
=
∑
=
1
−
∑
(
+
+
)
=
1
2
−
∑
(
+
+
)
=
1
(
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
7
1
-
1
2
8
0
1276
T
h
e
PA
o
f
a
m
a
p
is
d
ef
in
e
d
f
r
o
m
th
e
m
a
p
p
r
o
d
u
ce
r
'
s
p
o
in
t
o
f
v
iew,
wh
er
ea
s
UA
is
d
ef
in
e
d
f
r
o
m
t
h
e
u
s
er
'
s
p
o
in
t o
f
v
iew
[
3
6
]
,
[
4
0
]
.
T
h
e
f
o
r
m
u
las f
o
r
PA a
n
d
UA
ar
e
g
iv
en
i
n
(
7
)
an
d
(
8
)
.
=
+
(
7
)
=
+
(
8
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Ana
ly
s
is
o
f
t
e
m
po
ra
l sig
na
t
ures o
f
o
ptic
a
l da
t
a
I
n
Fig
u
r
e
s
2
(
a)
t
o
2
(
d
)
,
th
e
te
m
p
o
r
al
v
ar
iatio
n
o
f
NDVI
,
NDYI
,
GNDV
I
,
an
d
MN
DW
I
o
f
d
if
f
er
en
t
class
es
(
ch
ick
p
ea
,
wh
ea
t,
wate
r
m
elo
n
,
g
a
r
lic
,
u
r
b
an
,
an
d
w
ater
)
wer
e
p
lo
tted
to
s
tu
d
y
th
e
tem
p
o
r
al
p
atter
n
o
f
v
eg
etatio
n
in
d
ex
es a
t d
if
f
e
r
en
t
p
h
en
o
l
o
g
ical
s
tag
es o
f
v
a
r
io
u
s
cr
o
p
s
.
−
T
h
e
NDVI
is
a
m
ea
s
u
r
e
o
f
v
eg
etatio
n
co
v
e
r
th
at
r
an
g
es
f
r
o
m
-
1
t
o
+1
.
I
n
t
h
is
s
ca
le,
p
o
s
itiv
e
v
alu
es
in
d
icate
ar
ea
s
co
v
er
ed
b
y
clo
u
d
s
an
d
wate
r
,
wh
ile
a
v
alu
e
o
f
0
r
e
p
r
esen
ts
n
o
v
eg
etatio
n
co
v
e
r
.
NDVI
v
alu
es
th
at
ar
e
clo
s
e
to
1
in
d
icate
d
en
s
e
v
e
g
etatio
n
.
T
h
is
i
n
d
ex
h
as
b
ee
n
p
r
o
v
e
n
to
b
e
a
h
elp
f
u
l
to
o
l
in
esti
m
atin
g
cr
o
p
y
ield
an
d
m
o
n
ito
r
in
g
cr
o
p
g
r
o
wth
.
D
u
r
in
g
th
e
s
o
win
g
p
er
io
d
,
cr
o
p
s
ty
p
ical
ly
h
av
e
a
s
m
all
NDVI
v
alu
e.
Ho
wev
er
,
as
th
ey
en
ter
th
e
f
ast
-
g
r
o
win
g
s
ea
s
o
n
,
th
e
NDVI
v
alu
e
in
cr
ea
s
es
r
ap
id
ly
.
W
h
ea
t,
f
o
r
in
s
tan
ce
,
b
eg
in
s
to
m
atu
r
e
f
r
o
m
t
h
e
en
d
o
f
Feb
r
u
ar
y
,
an
d
as
it
d
o
es
s
o
,
its
NDVI
v
alu
e
d
ec
r
ea
s
es,
r
ea
ch
in
g
a
m
in
im
u
m
at
h
a
r
v
e
s
tin
g
tim
e.
C
h
ick
p
ea
an
d
wh
e
at
ty
p
ically
h
av
e
NDVI
v
alu
e
s
o
f
m
o
r
e
th
an
0
.
3
,
wh
ile
th
e
NDVI
o
f
o
th
er
cr
o
p
s
,
u
r
b
an
ar
ea
s
,
an
d
wate
r
b
o
d
ies
ar
e
lo
wer
th
a
n
0
.
3
.
T
h
e
wate
r
class
u
s
u
ally
s
h
o
ws th
e
lo
west ND
VI
v
alu
es.
−
B
ased
o
n
th
e
b
lu
e
an
d
g
r
ee
n
b
an
d
s
,
th
e
NDYI
is
s
u
itab
le
f
o
r
r
ep
r
esen
tin
g
th
e
in
cr
ea
s
e
in
y
ello
wn
ess
d
u
r
in
g
b
lo
s
s
o
m
in
g
.
T
h
is
is
b
ec
au
s
e
f
lo
wer
s
ab
s
o
r
b
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
b
lu
e
lig
h
t,
an
d
th
e
h
i
g
h
r
ef
lecta
n
ce
in
th
e
g
r
ee
n
a
n
d
r
ed
b
an
d
s
is
th
en
p
er
ce
iv
e
d
as
y
ello
w.
T
h
e
s
tu
d
y
f
o
u
n
d
th
at
in
-
s
itu
d
ata
r
eg
ar
d
in
g
th
e
b
eg
in
n
i
n
g
an
d
e
n
d
o
f
f
lo
wer
in
g
was sim
ilar
to
th
at
ca
p
tu
r
ed
b
y
t
h
e
Sen
tin
el
-
1
d
ata
[
3
8
]
.
−
GNDV
I
h
as
a
tem
p
o
r
al
p
atte
r
n
s
im
ilar
to
NDVI
.
Ho
wev
er
,
it
is
a
v
ar
iatio
n
o
f
NDVI
th
at
u
s
es
g
r
ee
n
r
ef
lecta
n
ce
in
s
tead
o
f
r
ed
.
−
MN
DW
I
ca
n
d
is
tin
g
u
is
h
wate
r
an
d
u
r
b
an
a
r
ea
s
ea
s
ily
b
ec
au
s
e
wate
r
h
as
th
e
h
ig
h
est
MN
DW
I
v
alu
e
co
m
p
ar
ed
to
o
th
e
r
class
es,
wh
ile
u
r
b
an
a
r
ea
s
h
av
e
n
e
g
ativ
e
MN
DW
I
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
T
e
m
p
o
r
al
p
r
o
f
iles
o
f
(
a)
NDVI
,
(
b
)
GNDV
I
,
(
c)
N
DYI
,
an
d
(
d
)
MN
DW
I
4
.
2
.
Dy
na
m
ics o
f
SAR
po
la
r
is
a
t
io
ns
v
er
t
ica
l
–
v
er
t
ica
l
a
nd
v
er
t
ica
l
-
ho
rizo
nta
l
T
h
e
SAR
VV
an
d
VH
b
a
ck
s
ca
tter
v
ar
ies
as
th
e
cr
o
p
g
r
o
ws
f
r
o
m
s
o
win
g
to
h
ar
v
esti
n
g
.
Fig
u
r
e
s
3
(
a)
an
d
3
(
b
)
s
h
o
ws th
e
tem
p
o
r
al
v
ar
iatio
n
o
f
th
e
av
e
r
ag
e
b
ac
k
s
ca
tter
co
ef
f
icien
ts
o
f
wh
ea
t,
ch
ick
p
ea
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
r
o
p
cla
s
s
ifica
tio
n
u
s
in
g
o
b
je
ct
-
o
r
ien
ted
meth
o
d
a
n
d
Go
o
g
l
e
E
a
r
th
E
n
g
in
e
(
Gee
ta
T.
Desa
i
)
1277
wate
r
m
elo
n
,
g
ar
lic,
wate
r
,
an
d
u
r
b
a
n
ar
ea
u
n
d
er
s
tu
d
y
in
2
0
2
2
.
I
n
Fig
u
r
e
3
,
o
n
th
e
X
ax
is
,
th
e
d
ate
o
f
SAR
im
ag
e
ac
q
u
is
itio
n
is
tak
en
,
a
n
d
o
n
th
e
Y
ax
is
v
alu
e
o
f
th
e
b
a
ck
s
ca
tter
in
g
co
ef
f
icien
t is p
lac
ed
.
−
Du
r
in
g
th
e
in
itial
g
r
o
wth
s
ta
g
es,
b
ac
k
s
ca
tter
v
alu
es
ar
e
lo
w,
h
o
wev
er
,
t
h
ey
in
cr
ea
s
e
r
ap
id
ly
as
cr
o
p
s
p
r
o
g
r
ess
to
th
e
v
eg
etativ
e
s
tag
e.
−
Du
r
in
g
th
e
r
ep
r
o
d
u
ctiv
e
s
tag
e,
s
lig
h
t v
ar
iatio
n
s
in
cr
o
p
b
i
o
m
ass
an
d
s
tr
u
ctu
r
e
ca
u
s
e
m
in
u
te
v
ar
iatio
n
in
b
ac
k
s
ca
tter
.
−
Du
r
in
g
h
ar
v
esti
n
g
,
a
s
ig
n
if
ican
t
d
ec
r
ea
s
e
in
b
ac
k
s
ca
tter
was
o
b
s
er
v
ed
as
th
e
p
lan
t
d
ied
,
r
esu
ltin
g
in
a
r
ed
u
ctio
n
o
f
th
e
p
lan
t'
s
wate
r
co
n
te
n
t.
T
h
e
b
ac
k
s
ca
tter
d
r
o
p
p
ed
f
r
o
m
-
1
5
d
B
(
VH)
,
-
7
.
5
d
B
(
VV)
to
-
2
2
d
B
(
VH)
,
-
1
1
d
B
(
VV)
f
o
r
ch
ick
p
ea
;
-
1
3
d
B
(
VH)
,
-
1
0
d
B
(
VV)
to
-
1
5
d
B
(
VH)
,
-
1
3
d
B
(
VV)
f
o
r
wh
ea
t; a
n
d
-
1
5
d
B
(
VH)
,
-
1
0
d
B
(
VV)
to
-
1
8
d
B
(
VH)
,
-
1
2
d
B
(
VV)
f
o
r
wate
r
m
elo
n
.
−
T
h
e
wate
r
class
h
ad
th
e
lo
west
b
ac
k
s
ca
tter
an
d
VV
p
o
lar
iz
atio
n
s
h
o
wed
h
ig
h
er
b
ac
k
s
ca
tter
v
ar
iatio
n
as
cr
o
p
s
g
r
ew
c
o
m
p
ar
e
d
to
VH
p
o
lar
izatio
n
,
th
is
ag
r
ee
s
with
p
r
ev
io
u
s
r
esear
ch
[
4
1
]
.
(
a)
(
b
)
Fig
u
r
e
3
.
T
e
m
p
o
r
al
p
r
o
f
i
les
o
f
(
a
)
v
er
t
ic
al
v
er
tic
al
(
b
)
v
e
r
ti
ca
l
h
o
r
iz
o
n
t
al
4
.
3
.
Cla
s
s
if
ica
t
io
n
r
esu
lt
s
T
h
e
class
if
icatio
n
m
ap
s
g
en
e
r
ated
ap
p
ly
i
n
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
th
e
in
v
esti
g
atio
n
ar
ea
ar
e
d
is
p
lay
ed
in
Fig
u
r
e
4
.
Fig
u
r
e
4
(
a)
s
h
o
ws
class
if
icatio
n
m
a
p
s
g
en
er
ated
u
s
in
g
PB
m
eth
o
d
an
d
F
ig
u
r
e
4
(
b
)
s
h
o
ws
clas
s
if
icatio
n
m
ap
s
g
en
er
ated
u
s
in
g
OO
m
eth
o
d
.
T
ab
le
1
lis
ts
th
e
OAs
an
d
KC
o
f
th
e
d
if
f
er
en
t
class
if
icatio
n
s
ch
em
es
u
s
in
g
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
d
at
a.
T
h
e
OA
r
esu
lts
v
a
r
ied
f
r
o
m
6
1
%
to
8
5
.
5
%
d
ep
en
d
i
n
g
o
n
th
e
a
p
p
r
o
ac
h
(
P
B
o
r
OO)
an
d
i
n
p
u
t
f
ea
tu
r
es.
T
h
e
h
ig
h
est
OA
an
d
KC
o
f
8
5
.
5
%
an
d
0
.
7
7
4
was
o
b
tain
ed
f
o
r
OO
-
b
ased
class
if
icatio
n
ap
p
r
o
ac
h
with
th
e
f
u
s
i
o
n
o
f
Sen
tin
el
-
1
a
n
d
Sen
tin
el
-
2
d
ata.
On
t
h
e
o
th
e
r
h
an
d
,
o
n
ly
Sen
tin
el
-
2
b
an
d
s
p
r
o
d
u
ce
d
th
e
lo
west
OA
o
f
6
1
%
an
d
KC
o
f
0
.
3
7
.
Or
y
n
b
aik
y
zy
et
a
l.
[
1
5
]
o
b
s
er
v
ed
th
at
Sen
tin
el
-
1
d
ata
s
h
o
wed
m
o
r
e
p
r
o
m
is
in
g
r
esu
lt
s
th
an
Sen
tin
el
-
2
.
T
h
is
r
esu
lt
was
co
n
s
is
ten
t
with
th
e
co
n
clu
s
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
wo
r
k
.
Ver
m
a
et
a
l.
[
1
2
]
u
s
ed
jo
in
t
Sen
tin
el
-
1
a
n
d
Sen
t
in
el
-
2
d
ata
f
o
r
C
C
,
wh
ich
y
ield
ed
an
OA
o
f
8
3
.
8
7
an
d
a
KC
o
f
0
.
7
8
.
R
esear
ch
b
y
Yan
g
et
a
l.
[
1
9
]
,
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
8
3
.
3
5
%
was
o
b
tain
ed
f
o
r
C
C
b
ased
o
n
th
e
jo
in
t
u
s
e
o
f
Sen
t
in
el
-
1
an
d
Sen
tin
el
-
2
im
a
g
es.
C
h
ick
p
ea
h
ad
th
e
lo
west
UA
an
d
PA
d
u
e
to
th
e
s
m
aller
n
u
m
b
e
r
o
f
v
is
ited
p
lo
t
s
.
T
h
er
ef
o
r
e,
C
h
ick
p
ea
was
m
i
s
class
if
ied
as
o
th
er
cr
o
p
s
.
T
h
is
m
is
class
if
icatio
n
m
ay
h
av
e
r
esu
lted
f
r
o
m
th
e
c
o
in
cid
in
g
g
r
o
wth
s
tag
es o
f
t
h
ese
cr
o
p
s
.
(
a)
(
b
)
Fig
u
r
e
4
.
Usi
n
g
f
u
s
io
n
o
f
o
p
tical
an
d
SAR
im
ag
es (
a)
PB
class
if
icatio
n
(
b
)
OO
class
if
icati
o
n
ap
p
r
o
ac
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
7
1
-
1
2
8
0
1278
T
ab
le
1
.
OA
an
d
KP
o
f
ea
ch
c
o
m
b
in
atio
n
C
o
m
b
i
n
a
t
i
o
n
PB
OO
OA
KC
OA
KC
V
V
+
V
H
0
.
8
0
.
6
9
0
.
8
3
0
.
7
6
S
e
n
t
i
n
e
l
-
2
b
a
n
d
s
0
.
6
1
0
.
3
7
0
.
6
6
0
.
4
8
S
e
n
t
i
n
e
l
-
2
+
N
D
V
I
0
.
6
7
0
.
4
7
0
.
6
6
3
0
.
4
8
S
e
n
t
i
n
e
l
-
2
+
G
N
D
V
I
0
.
6
7
9
0
.
4
7
0
.
6
6
4
0
.
4
8
1
S
e
n
t
i
n
e
l
-
2
+
M
N
D
V
I
0
.
6
6
0
.
4
9
0
.
6
6
1
0
.
4
8
7
9
S
e
n
t
i
n
e
l
-
2
+
N
D
Y
I
0
.
6
8
1
8
0
.
4
7
8
0
.
6
6
0
.
4
8
S
e
n
t
i
n
e
l
-
1
+
S
e
n
t
i
n
e
l
-
2
0
.
8
1
3
6
0
.
7
0
0
.
8
5
5
0
.
7
7
4
I
n
th
e
s
tu
d
y
,
Fig
u
r
e
s
5
(
a)
an
d
5
(
b
)
d
is
p
lay
s
th
e
UA
an
d
P
A
o
b
tain
ed
f
o
r
d
if
f
er
e
n
t
ca
teg
o
r
ies
u
s
in
g
PB
an
d
OO
class
if
icatio
n
tech
n
iq
u
es.
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
OO
class
if
icatio
n
ap
p
r
o
ac
h
h
ad
a
h
ig
h
er
UA
th
an
th
e
PB
clas
s
if
icatio
n
.
T
h
e
r
esear
ch
er
s
co
n
cl
u
d
ed
t
h
at
th
e
f
u
s
io
n
o
f
Sen
tin
el
-
1
r
ad
ar
an
d
Sen
tin
el
-
2
o
p
tical
d
ata
h
as
r
esu
lted
in
an
en
h
an
ce
m
e
n
t
in
ac
cu
r
ac
y
o
f
C
C
S
im
ilar
o
u
tco
m
es
wer
e
al
s
o
ac
h
iev
ed
in
t
h
e
s
tu
d
ies
[
1
3
]
,
[
1
4
]
.
T
h
e
OA
o
b
tain
ed
in
t
h
is
s
tu
d
y
was
h
ig
h
er
th
an
[
1
2
]
,
p
r
im
ar
ily
d
u
e
t
o
th
e
in
teg
r
atio
n
o
f
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
u
s
in
g
th
e
OO
class
if
icatio
n
ap
p
r
o
ac
h
.
Ob
ject
-
b
ased
C
C
elim
in
ates
o
b
ject
s
p
ec
tr
al
v
ar
iab
ilit
y
b
y
av
e
r
ag
in
g
m
an
y
p
ix
el
v
alu
es
lead
in
g
to
an
i
n
c
r
ea
s
e
in
ac
cu
r
ac
y
.
An
im
p
o
r
ta
n
t
f
ac
to
r
af
f
ec
tin
g
th
e
class
if
icatio
n
ac
cu
r
ac
y
o
f
h
ig
h
-
r
eso
lu
tio
n
im
a
g
es
class
if
ied
u
s
in
g
SNI
C
tech
n
iq
u
e
is
th
e
s
ize
o
f
th
e
s
u
p
er
p
ix
els.
T
o
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
an
d
ef
f
icie
n
cy
o
f
class
if
icatio
n
,
th
e
au
to
m
atic
o
p
tim
al
s
u
p
er
p
ix
el
s
eg
m
en
tatio
n
s
ize
s
elec
tio
n
m
eth
o
d
s
till
h
as to
b
e
cr
ea
te
d
.
(
a)
(
b
)
Fig
u
r
e
5
.
PB
an
d
OO
class
if
icatio
n
of
(
a)
u
s
er
ac
c
u
r
ac
y
a
n
d
(
b
)
p
r
o
d
u
ce
r
ac
cu
r
ac
y
5.
CO
NCLU
SI
O
N
T
h
e
r
ea
s
o
n
b
eh
in
d
th
e
in
v
es
tig
atio
n
was
to
ex
am
i
n
e
th
e
p
o
ten
tial
o
f
co
m
b
in
in
g
m
u
l
ti
-
tem
p
o
r
al
Sen
tin
el
-
1
an
d
o
p
tical
Sen
tin
el
-
2
im
ag
es
to
m
ap
cr
o
p
s
u
s
in
g
th
e
PB
an
d
OO
class
if
icat
io
n
ap
p
r
o
ac
h
with
a
R
F
cla
s
s
if
ier
.
Dif
f
er
en
t
co
m
b
i
n
atio
n
s
o
f
o
p
tical
an
d
m
icr
o
wav
e
f
ea
tu
r
es
wer
e
ex
p
lo
r
ed
to
id
en
tify
th
e
m
o
s
t
im
p
o
r
tan
t
r
ad
ar
an
d
o
p
tical
f
ea
tu
r
es
f
o
r
ac
cu
r
ate
cr
o
p
m
ap
p
in
g
.
T
h
e
o
u
tco
m
e
d
e
m
o
n
s
tr
ated
th
at
th
e
in
teg
r
atio
n
o
f
Sen
tin
el
-
1
an
d
Sen
tin
el
-
2
u
s
in
g
th
e
OO
class
if
icatio
n
ap
p
r
o
ac
h
p
r
o
v
id
e
d
th
e
b
est
r
esu
lts
.
T
h
e
R
F
m
o
d
el
tr
ain
ed
u
s
in
g
t
h
e
f
u
s
io
n
o
f
Sen
tin
el
-
1
an
d
Se
n
tin
el
-
2
d
ata
h
a
d
a
m
ax
im
u
m
OA
o
f
8
5
.
5
3
%
an
d
a
KC
o
f
0
.
7
7
,
wh
ich
was
h
i
g
h
er
th
an
th
e
OA
o
b
tain
ed
u
s
i
n
g
eith
er
Sen
tin
el
-
1
o
r
Sen
ti
n
el
-
2
d
ata
al
o
n
e.
T
h
is
s
u
g
g
ests
th
at
m
er
g
in
g
r
em
o
te
s
en
s
in
g
d
ata
h
as
ex
ce
llen
t
p
r
o
s
p
ec
ts
f
o
r
im
ag
e
s
eg
m
en
tatio
n
an
d
class
if
icatio
n
alg
o
r
ith
m
s
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
u
s
ed
G
EE
,
wh
ic
h
m
ad
e
t
h
e
g
en
er
atio
n
o
f
cr
o
p
m
ap
s
c
o
n
v
en
ie
n
t,
f
ast
an
d
ac
cu
r
ate.
T
h
is
ap
p
r
o
ac
h
is
s
u
itab
le
f
o
r
f
i
n
ely
class
if
y
in
g
cr
o
p
s
in
q
u
ite
c
o
m
p
lex
a
n
d
h
eter
o
g
en
e
o
u
s
r
eg
io
n
s
.
I
n
th
e
f
u
tu
r
e,
au
to
m
atic
s
ele
ctio
n
o
f
a
n
id
ea
l
s
u
p
er
p
ix
el
f
o
r
SNI
C
ca
n
b
e
ex
p
lo
r
ed
t
o
f
u
r
t
h
er
b
o
o
s
t
th
e
ac
cu
r
ac
y
o
f
th
e
C
C
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
S
c
h
m
e
d
t
m
a
n
n
a
n
d
M
.
C
a
m
p
a
g
n
o
l
o
,
“
R
e
l
i
a
b
l
e
c
r
o
p
i
d
e
n
t
i
f
i
c
a
t
i
o
n
w
i
t
h
sat
e
l
l
i
t
e
i
m
a
g
e
r
y
i
n
t
h
e
c
o
n
t
e
x
t
o
f
c
o
mm
o
n
a
g
r
i
c
u
l
t
u
r
e
p
o
l
i
c
y
su
b
s
i
d
y
c
o
n
t
r
o
l
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
7
,
n
o
.
7
,
p
p
.
9
3
2
5
–
9
3
4
6
,
2
0
1
5
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
7
0
7
0
9
3
2
5
.
[
2
]
K
.
V
a
n
Tr
i
c
h
t
,
A
.
G
o
b
i
n
,
S
.
G
i
l
l
i
a
ms
,
a
n
d
I
.
P
i
c
c
a
r
d
,
“
S
y
n
e
r
g
i
st
i
c
u
se
o
f
r
a
d
a
r
s
e
n
t
i
n
e
l
-
1
a
n
d
o
p
t
i
c
a
l
se
n
t
i
n
e
l
-
2
i
ma
g
e
r
y
f
o
r
c
r
o
p
map
p
i
n
g
:
A
c
a
se
s
t
u
d
y
f
o
r
B
e
l
g
i
u
m,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
0
,
n
o
.
1
0
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
0
1
0
1
6
4
2
.
[
3
]
M
.
A
.
A
l
t
i
e
r
i
,
F
.
R
.
F
u
n
e
s
-
M
o
n
z
o
t
e
,
a
n
d
P
.
P
e
t
e
r
se
n
,
“
A
g
r
o
e
c
o
l
o
g
i
c
a
l
l
y
e
f
f
i
c
i
e
n
t
a
g
r
i
c
u
l
t
u
r
a
l
s
y
s
t
e
ms
f
o
r
sm
a
l
l
h
o
l
d
e
r
f
a
r
mers
:
c
o
n
t
r
i
b
u
t
i
o
n
s
t
o
f
o
o
d
s
o
v
e
r
e
i
g
n
t
y
,
”
A
g
ro
n
o
m
y
f
o
r
S
u
st
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
3
2
,
n
o
.
1
,
p
p
.
1
–
1
3
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
5
9
3
-
0
1
1
-
0
0
6
5
-
6.
0
0
.
2
0
.
4
0
.
6
0
.
8
1
1
.
2
Ch
a
n
n
a
o
t
h
erc
r
o
p
s
w
h
ea
t
u
r
b
a
n
w
a
t
er
U
s
er
a
c
c
u
r
a
c
y
Cl
a
s
s
i
f
i
c
a
t
i
o
n
c
l
a
s
s
es
PB
OO
0
0
.
2
0
.
4
0
.
6
0
.
8
1
1
.
2
Ch
a
n
n
a
o
t
h
erc
r
o
p
s
w
h
ea
t
u
r
b
a
n
w
a
t
er
Pr
o
d
u
c
er
a
c
c
u
r
a
c
y
Cl
a
s
s
i
f
i
c
a
t
i
o
n
c
l
a
s
s
es
PB
OO
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
r
o
p
cla
s
s
ifica
tio
n
u
s
in
g
o
b
je
ct
-
o
r
ien
ted
meth
o
d
a
n
d
Go
o
g
l
e
E
a
r
th
E
n
g
in
e
(
Gee
ta
T.
Desa
i
)
1279
[
4
]
C
.
Lu
o
,
H
.
L
i
u
,
L.
Lu
,
Z.
L
i
u
,
F
.
K
o
n
g
,
a
n
d
X
.
Z
h
a
n
g
,
“
M
o
n
t
h
l
y
c
o
m
p
o
s
i
t
e
s
f
r
o
m
se
n
t
i
n
e
l
-
1
a
n
d
se
n
t
i
n
e
l
-
2
i
m
a
g
e
s
f
o
r
r
e
g
i
o
n
a
l
maj
o
r
c
r
o
p
ma
p
p
i
n
g
w
i
t
h
G
o
o
g
l
e
E
a
r
t
h
E
n
g
i
n
e
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
g
r
a
t
i
v
e
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
2
0
,
n
o
.
7
,
p
p
.
1
9
4
4
–
1
9
5
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
0
9
5
-
3
1
1
9
(
2
0
)
6
3
3
2
9
-
9.
[
5
]
M
.
B
e
r
g
e
r
,
J.
M
o
r
e
n
o
,
J
.
A
.
Jo
h
a
n
n
e
ssen
,
P
.
F
.
Le
v
e
l
t
,
a
n
d
R
.
F
.
H
a
n
sse
n
,
“
ESA
’
s
se
n
t
i
n
e
l
mi
ss
i
o
n
s
i
n
s
u
p
p
o
r
t
o
f
Ea
r
t
h
s
y
s
t
e
m
sci
e
n
c
e
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
o
f
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
1
2
0
,
p
p
.
8
4
–
9
0
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se.
2
0
1
1
.
0
7
.
0
2
3
.
[
6
]
N
.
G
o
r
e
l
i
c
k
,
M
.
H
a
n
c
h
e
r
,
M
.
D
i
x
o
n
,
S
.
I
l
y
u
s
h
c
h
e
n
k
o
,
D
.
T
h
a
u
,
a
n
d
R
.
M
o
o
r
e
,
“
G
o
o
g
l
e
Ea
r
t
h
En
g
i
n
e
:
P
l
a
n
e
t
a
r
y
-
sca
l
e
g
e
o
sp
a
t
i
a
l
a
n
a
l
y
si
s
f
o
r
e
v
e
r
y
o
n
e
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
o
f
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
0
2
,
p
p
.
1
8
–
2
7
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se.
2
0
1
7
.
0
6
.
0
3
1
.
[
7
]
G
.
T
.
D
e
sa
i
a
n
d
A
.
N
.
G
a
i
k
w
a
d
,
“
A
u
t
o
ma
t
i
c
l
a
n
d
c
o
v
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
S
A
R
i
ma
g
e
r
y
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
u
si
n
g
G
o
o
g
l
e
Ea
r
t
h
E
n
g
i
n
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
j
o
u
rn
a
l
o
f
e
l
e
c
t
ri
c
a
l
a
n
d
c
o
m
p
u
t
e
r
e
n
g
i
n
e
e
r
i
n
g
sys
t
e
m
s
,
v
o
l
.
1
3
,
n
o
.
1
0
,
p
p
.
9
0
9
–
9
1
6
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
9
8
5
/
i
j
e
c
e
s.
1
3
.
1
0
.
6
.
[
8
]
A
.
E
.
M
a
x
w
e
l
l
,
T.
A
.
W
a
r
n
e
r
,
a
n
d
F
.
F
a
n
g
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
r
e
mo
t
e
se
n
si
n
g
:
a
n
a
p
p
l
i
e
d
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
3
9
,
n
o
.
9
,
p
p
.
2
7
8
4
–
2
8
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
4
3
1
1
6
1
.
2
0
1
8
.
1
4
3
3
3
4
3
.
[
9
]
D
.
J.
La
r
y
,
A
.
H
.
A
l
a
v
i
,
A
.
H
.
G
a
n
d
o
mi
,
a
n
d
A
.
L.
W
a
l
k
e
r
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
g
e
o
sci
e
n
c
e
s
a
n
d
r
e
mo
t
e
se
n
s
i
n
g
,
”
G
e
o
sc
i
e
n
c
e
Fro
n
t
i
e
rs
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
3
–
1
0
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
sf
.
2
0
1
5
.
0
7
.
0
0
3
.
[
1
0
]
M
.
B
e
l
g
i
u
a
n
d
L
.
D
r
ă
g
u
ţ
,
“
R
a
n
d
o
m
f
o
r
e
st
i
n
r
e
mo
t
e
se
n
si
n
g
:
A
r
e
v
i
e
w
o
f
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,”
I
S
PR
S
J
o
u
r
n
a
l
o
f
Ph
o
t
o
g
r
a
m
m
e
t
ry
a
n
d
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
1
4
,
p
p
.
2
4
–
3
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
p
r
sj
p
r
s.
2
0
1
6
.
0
1
.
0
1
1
.
[
1
1
]
A
.
V
e
l
o
s
o
e
t
a
l
.
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
t
h
e
t
e
m
p
o
r
a
l
b
e
h
a
v
i
o
r
o
f
c
r
o
p
s
u
s
i
n
g
se
n
t
i
n
e
l
-
1
a
n
d
se
n
t
i
n
e
l
-
2
-
l
i
k
e
d
a
t
a
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
a
p
p
l
i
c
a
t
i
o
n
s,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
o
f
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
1
9
9
,
p
p
.
4
1
5
–
4
2
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se.
2
0
1
7
.
0
7
.
0
1
5
.
[
1
2
]
A
.
V
e
r
ma,
A
.
K
u
m
a
r
,
a
n
d
K
.
L
a
l
,
“
K
h
a
r
i
f
c
r
o
p
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
u
si
n
g
c
o
mb
i
n
a
t
i
o
n
o
f
S
A
R
a
n
d
M
S
I
o
p
t
i
c
a
l
sen
t
i
n
e
l
sa
t
e
l
l
i
t
e
d
a
t
a
se
t
s,
”
J
o
u
rn
a
l
o
f
Ea
r
t
h
S
y
st
e
m
S
c
i
e
n
c
e
,
v
o
l
.
1
2
8
,
n
o
.
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
0
4
0
-
0
1
9
-
1
2
6
0
-
0.
[
1
3
]
A
.
C
h
a
k
h
a
r
,
D
.
H
e
r
n
á
n
d
e
z
-
L
ó
p
e
z
,
R
.
B
a
l
l
e
s
t
e
r
o
s,
a
n
d
M
.
A
.
M
o
r
e
n
o
,
“
I
mp
r
o
v
i
n
g
t
h
e
a
c
c
u
r
a
c
y
o
f
m
u
l
t
i
p
l
e
a
l
g
o
r
i
t
h
ms
f
o
r
c
r
o
p
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
I
n
t
e
g
r
a
t
i
n
g
s
e
n
t
i
n
e
l
-
1
o
b
s
e
r
v
a
t
i
o
n
s
w
i
t
h
s
e
n
t
i
n
e
l
-
2
d
a
t
a
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
3
,
n
o
.
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
0
2
0
2
4
3
.
[
1
4
]
Y
.
C
h
e
n
,
J.
H
o
u
,
C
.
H
u
a
n
g
,
Y
.
Z
h
a
n
g
,
a
n
d
X
.
Li
,
“
M
a
p
p
i
n
g
ma
i
z
e
a
r
e
a
i
n
h
e
t
e
r
o
g
e
n
e
o
u
s
a
g
r
i
c
u
l
t
u
r
a
l
l
a
n
d
sc
a
p
e
w
i
t
h
m
u
l
t
i
-
t
e
m
p
o
r
a
l
se
n
t
i
n
e
l
-
1
a
n
d
s
e
n
t
i
n
e
l
-
2
i
m
a
g
e
s
b
a
se
d
o
n
r
a
n
d
o
m
f
o
r
e
st
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
1
5
2
9
8
8
.
[
1
5
]
A
.
O
r
y
n
b
a
i
k
y
z
y
,
U
.
G
e
s
sn
e
r
,
B
.
M
a
c
k
,
a
n
d
C
.
C
o
n
r
a
d
,
“
C
r
o
p
t
y
p
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
f
u
si
o
n
o
f
se
n
t
i
n
e
l
-
1
a
n
d
sen
t
i
n
e
l
-
2
d
a
t
a
:
A
ssessi
n
g
t
h
e
i
m
p
a
c
t
o
f
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
o
p
t
i
c
a
l
d
a
t
a
a
v
a
i
l
a
b
i
l
i
t
y
,
a
n
d
p
a
r
c
e
l
s
i
z
e
s
o
n
t
h
e
a
c
c
u
r
a
c
i
e
s
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
2
,
n
o
.
1
7
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
2
1
7
2
7
7
9
.
[
1
6
]
R
.
S
o
n
o
b
e
,
Y
.
Y
a
ma
y
a
,
H
.
Ta
n
i
,
X
.
W
a
n
g
,
N
.
K
o
b
a
y
a
sh
i
,
a
n
d
K
.
M
o
c
h
i
z
u
k
i
,
“
A
ssess
i
n
g
t
h
e
s
u
i
t
a
b
i
l
i
t
y
o
f
d
a
t
a
f
r
o
m
s
e
n
t
i
n
e
l
-
1
A
a
n
d
2
A
f
o
r
c
r
o
p
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
G
I
S
c
i
e
n
c
e
&
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
5
4
,
n
o
.
6
,
p
p
.
9
1
8
–
9
3
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
4
8
1
6
0
3
.
2
0
1
7
.
1
3
5
1
1
4
9
.
[
1
7
]
V
.
W
a
l
t
e
r
,
“
O
b
j
e
c
t
-
b
a
se
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
r
e
m
o
t
e
se
n
s
i
n
g
d
a
t
a
f
o
r
c
h
a
n
g
e
d
e
t
e
c
t
i
o
n
,
”
I
S
P
RS
J
o
u
rn
a
l
o
f
Ph
o
t
o
g
r
a
m
m
e
t
ry
a
n
d
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
5
8
,
n
o
.
3
–
4
,
p
p
.
2
2
5
–
2
3
8
,
2
0
0
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
p
r
sj
p
r
s.2
0
0
3
.
0
9
.
0
0
7
.
[
1
8
]
M
.
B
a
a
t
z
,
C
.
H
o
f
f
m
a
n
n
,
a
n
d
G
.
W
i
l
l
h
a
u
c
k
,
“
P
r
o
g
r
e
ss
i
n
g
f
r
o
m
o
b
j
e
c
t
-
b
a
se
d
t
o
o
b
j
e
c
t
-
o
r
i
e
n
t
e
d
i
m
a
g
e
a
n
a
l
y
si
s,
”
i
n
O
b
j
e
c
t
-
Ba
s
e
d
I
m
a
g
e
A
n
a
l
y
s
i
s
,
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
0
8
,
p
p
.
2
9
–
4
2
.
[
1
9
]
L.
Y
a
n
g
,
L
.
W
a
n
g
,
G
.
A
.
A
b
u
b
a
k
a
r
,
a
n
d
J.
H
u
a
n
g
,
“
H
i
g
h
-
r
e
s
o
l
u
t
i
o
n
r
i
c
e
map
p
i
n
g
b
a
se
d
o
n
S
N
I
C
se
g
me
n
t
a
t
i
o
n
a
n
d
m
u
l
t
i
-
s
o
u
r
c
e
r
e
mo
t
e
s
e
n
s
i
n
g
i
m
a
g
e
s,”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
3
,
n
o
.
6
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
0
6
1
1
4
8
.
[
2
0
]
N.
-
T.
S
o
n
,
C
.
-
F
.
C
h
e
n
,
C
.
-
R
.
C
h
e
n
,
a
n
d
V
.
-
Q
.
M
i
n
h
,
“
A
ssessm
e
n
t
o
f
se
n
t
i
n
e
l
-
1
A
d
a
t
a
f
o
r
r
i
c
e
c
r
o
p
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
st
s
a
n
d
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
”
G
e
o
c
a
r
t
o
I
n
t
e
r
n
a
t
i
o
n
a
l
,
p
p
.
1
–
1
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
1
0
6
0
4
9
.
2
0
1
7
.
1
2
8
9
5
5
5
.
[
2
1
]
M
.
A
.
N
i
h
a
r
,
J.
M
.
A
h
a
me
d
,
S
.
P
a
z
h
a
n
i
v
e
l
a
n
,
R
.
K
u
mara
p
e
r
u
ma
l
,
a
n
d
K
.
G
.
R
a
j
,
“
Es
t
i
m
a
t
i
o
n
o
f
c
o
t
t
o
n
a
n
d
m
a
i
z
e
c
r
o
p
a
r
e
a
i
n
P
e
r
a
mb
a
l
u
r
D
i
s
t
r
i
c
t
O
f
Ta
m
i
l
N
a
d
u
u
si
n
g
m
u
l
t
i
-
d
a
t
e
se
n
t
i
n
e
l
-
1
A
S
A
R
d
a
t
a
,
”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
Ar
c
h
i
v
e
s
o
f
t
h
e
Ph
o
t
o
g
r
a
m
m
e
t
ry
,
Re
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
p
p
.
6
7
–
7
1
,
2
0
1
9
,
d
o
i
:
1
0
.
5
1
9
4
/
i
sp
r
s
-
a
r
c
h
i
v
e
s
-
X
LI
I
-
3
-
W6
-
67
-
2
0
1
9
.
[
2
2
]
P
.
P
.
D.
B
e
m
,
O
.
A
.
D.
C.
J
ú
n
i
o
r
,
O
.
L.
F
.
D.
C
a
r
v
a
l
h
o
,
R
.
A
.
T.
G
o
m
e
s,
R
.
F
.
G
u
i
marā
e
s,
a
n
d
C
.
M
.
M
.
P
i
m
e
n
t
e
l
,
“
I
r
r
i
g
a
t
e
d
r
i
c
e
c
r
o
p
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
S
o
u
t
h
e
r
n
B
r
a
z
i
l
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
s
e
n
t
i
n
e
l
-
1
t
i
m
e
s
e
r
i
e
s
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s:
S
o
c
i
e
t
y
a
n
d
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
sas
e
.
2
0
2
1
.
1
0
0
6
2
7
.
[
2
3
]
L.
E.
C
.
L
.
R
o
sa,
R
.
Q
.
F
e
i
t
o
s
a
,
P
.
N
.
H
a
p
p
,
I
.
D
.
S
a
n
c
h
e
s,
a
n
d
G
.
A
.
O
.
P
.
D.
C
o
s
t
a
,
“
C
o
mb
i
n
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
p
r
i
o
r
k
n
o
w
l
e
d
g
e
f
o
r
c
r
o
p
ma
p
p
i
n
g
i
n
t
r
o
p
i
c
a
l
r
e
g
i
o
n
s
f
r
o
m
mu
l
t
i
t
e
m
p
o
r
a
l
S
A
R
i
ma
g
e
se
q
u
e
n
c
e
s,”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
1
,
n
o
.
1
7
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
1
1
7
2
0
2
9
.
[
2
4
]
E.
N
d
i
k
u
ma
n
a
,
D
.
H
.
T.
M
i
n
h
,
N
.
B
a
g
h
d
a
d
i
,
D
.
C
o
u
r
a
u
l
t
,
a
n
d
L
.
H
o
ss
a
r
d
,
“
D
e
e
p
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
mu
l
t
i
t
e
mp
o
r
a
l
S
A
R
se
n
t
i
n
e
l
-
1
f
o
r
C
a
marg
u
e
,
F
r
a
n
c
e
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
0
,
n
o
.
8
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
0
0
8
1
2
1
7
.
[
2
5
]
N
.
K
o
b
a
y
a
s
h
i
,
H
.
Ta
n
i
,
X
.
W
a
n
g
,
a
n
d
R
.
S
o
n
o
b
e
,
“
C
r
o
p
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
s
p
e
c
t
r
a
l
i
n
d
i
c
e
s
d
e
r
i
v
e
d
f
r
o
m
se
n
t
i
n
e
l
-
2
A
i
ma
g
e
r
y
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
6
7
–
9
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
2
4
7
5
1
8
3
9
.
2
0
1
9
.
1
6
9
4
7
6
5
.
[
2
6
]
R
.
S
a
i
n
i
a
n
d
S
.
K
.
G
h
o
sh
,
“
C
r
o
p
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
n
si
n
g
l
e
d
a
t
e
s
e
n
t
i
n
e
l
-
2
i
ma
g
e
r
y
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
Arc
h
i
v
e
s
o
f
t
h
e
P
h
o
t
o
g
ra
m
m
e
t
ry
,
R
e
m
o
t
e
S
e
n
s
i
n
g
a
n
d
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
X
LI
I
–
5
,
p
p
.
6
8
3
–
6
8
8
,
2
0
1
8
,
d
o
i
:
1
0
.
5
1
9
4
/
i
sp
r
s
-
a
r
c
h
i
v
e
s
-
X
LI
I
-
5
-
683
-
2
0
1
8
.
[
2
7
]
R
.
S
o
n
o
b
e
,
Y
.
Y
a
ma
y
a
,
H
.
Ta
n
i
,
X
.
W
a
n
g
,
N
.
K
o
b
a
y
a
s
h
i
,
a
n
d
K
.
M
o
c
h
i
z
u
k
i
,
“
C
r
o
p
c
l
a
s
si
f
i
c
a
t
i
o
n
f
r
o
m
s
e
n
t
i
n
e
l
-
2
-
d
e
r
i
v
e
d
v
e
g
e
t
a
t
i
o
n
i
n
d
i
c
e
s
u
s
i
n
g
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
2
,
n
o
.
0
2
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
1
7
/
1
.
JR
S
.
1
2
.
0
2
6
0
1
9
.
[
2
8
]
V
.
M
a
z
z
i
a
,
A
.
K
h
a
l
i
q
,
a
n
d
M
.
C
h
i
a
b
e
r
g
e
,
“
I
mp
r
o
v
e
me
n
t
i
n
l
a
n
d
c
o
v
e
r
a
n
d
c
r
o
p
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
t
e
m
p
o
r
a
l
f
e
a
t
u
r
e
s
l
e
a
r
n
i
n
g
f
r
o
m
s
e
n
t
i
n
e
l
-
2
d
a
t
a
u
si
n
g
r
e
c
u
r
r
e
n
t
-
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
R
-
C
N
N
)
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
1
0
2
3
8
.
[
2
9
]
M
.
F
a
u
v
e
l
,
Y
.
Ta
r
a
b
a
l
k
a
,
J.
A
.
B
e
n
e
d
i
k
t
sso
n
,
J.
C
h
a
n
u
ss
o
t
,
a
n
d
J.
C
.
Ti
l
t
o
n
,
“
A
d
v
a
n
c
e
s
i
n
sp
e
c
t
r
a
l
-
s
p
a
t
i
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
s
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
,
v
o
l
.
1
0
1
,
n
o
.
3
,
p
p
.
6
5
2
–
6
7
5
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JP
R
O
C
.
2
0
1
2
.
2
1
9
7
5
8
9
.
[
3
0
]
Q
.
Y
u
,
P
.
G
o
n
g
,
N
.
C
l
i
n
t
o
n
,
G
.
B
i
g
i
n
g
,
M
.
K
e
l
l
y
,
a
n
d
D
.
S
c
h
i
r
o
k
a
u
e
r
,
“
O
b
j
e
c
t
-
b
a
se
d
d
e
t
a
i
l
e
d
v
e
g
e
t
a
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
a
i
r
b
o
r
n
e
h
i
g
h
s
p
a
t
i
a
l
r
e
so
l
u
t
i
o
n
r
e
m
o
t
e
se
n
s
i
n
g
i
ma
g
e
r
y
,
”
P
h
o
t
o
g
ra
m
m
e
t
ri
c
E
n
g
i
n
e
e
r
i
n
g
&
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
7
2
,
n
o
.
7
,
p
p
.
7
9
9
–
8
1
1
,
2
0
0
6
,
d
o
i
:
1
0
.
1
4
3
5
8
/
P
E
R
S
.
7
2
.
7
.
7
9
9
.
[
3
1
]
C
.
L
u
o
e
t
a
l
.
,
“
U
si
n
g
t
i
m
e
ser
i
e
s
s
e
n
t
i
n
e
l
-
1
i
m
a
g
e
s
f
o
r
o
b
j
e
c
t
-
o
r
i
e
n
t
e
d
c
r
o
p
c
l
a
s
si
f
i
c
a
t
i
o
n
i
n
G
o
o
g
l
e
Ea
r
t
h
E
n
g
i
n
e
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
3
,
n
o
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
3
0
4
0
5
6
1
.
[
3
2
]
J.
-
S
.
L
e
e
,
J
.
-
H
.
W
e
n
,
T.
L.
A
i
n
sw
o
r
t
h
,
K
.
-
S
.
C
h
e
n
,
a
n
d
A
.
J
.
C
h
e
n
,
“
I
mp
r
o
v
e
d
s
i
g
ma
f
i
l
t
e
r
f
o
r
s
p
e
c
k
l
e
f
i
l
t
e
r
i
n
g
o
f
S
A
R
i
ma
g
e
r
y
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
G
e
o
sc
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
4
7
,
n
o
.
1
,
p
p
.
2
0
2
–
2
1
3
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TG
R
S
.
2
0
0
8
.
2
0
0
2
8
8
1
.
[
3
3
]
C
.
A
.
D
.
V
i
t
t
o
r
i
o
a
n
d
A
.
P
.
G
e
o
r
g
a
k
a
k
o
s,
“
L
a
n
d
c
o
v
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
w
e
t
l
a
n
d
i
n
u
n
d
a
t
i
o
n
ma
p
p
i
n
g
u
s
i
n
g
M
O
D
I
S
,
”
Re
m
o
t
e
S
e
n
si
n
g
o
f
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
2
0
4
,
p
p
.
1
–
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
se.
2
0
1
7
.
1
1
.
0
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
2
,
Ap
r
il 2
0
2
5
:
1
2
7
1
-
1
2
8
0
1280
[
3
4
]
C
.
J.
T
u
c
k
e
r
,
“
R
e
d
a
n
d
p
h
o
t
o
g
r
a
p
h
i
c
i
n
f
r
a
r
e
d
l
i
n
e
a
r
c
o
m
b
i
n
a
t
i
o
n
s
f
o
r
mo
n
i
t
o
r
i
n
g
v
e
g
e
t
a
t
i
o
n
,
”
Re
m
o
t
e
S
e
n
si
n
g
o
f
En
v
i
r
o
n
m
e
n
t
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
1
2
7
–
1
5
0
,
1
9
7
9
,
d
o
i
:
1
0
.
1
0
1
6
/
0
0
3
4
-
4
2
5
7
(
7
9
)
9
0
0
1
3
-
0.
[
3
5
]
H
.
X
u
,
“
M
o
d
i
f
i
c
a
t
i
o
n
o
f
n
o
r
m
a
l
i
se
d
d
i
f
f
e
r
e
n
c
e
w
a
t
e
r
i
n
d
e
x
(
N
D
W
I
)
t
o
e
n
h
a
n
c
e
o
p
e
n
w
a
t
e
r
f
e
a
t
u
r
e
s
i
n
r
e
mo
t
e
l
y
sen
s
e
d
i
ma
g
e
r
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
2
7
,
n
o
.
1
4
,
p
p
.
3
0
2
5
–
3
0
3
3
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
4
3
1
1
6
0
6
0
0
5
8
9
1
7
9
.
[
3
6
]
M
.
F
.
I
si
p
,
R
.
T.
A
l
b
e
r
t
o
,
a
n
d
A
.
R
.
B
i
a
g
t
a
n
,
“
E
x
p
l
o
r
i
n
g
v
e
g
e
t
a
t
i
o
n
i
n
d
i
c
e
s
a
d
e
q
u
a
t
e
i
n
d
e
t
e
c
t
i
n
g
t
w
i
st
e
r
d
i
s
e
a
se
o
f
o
n
i
o
n
u
s
i
n
g
sen
t
i
n
e
l
-
2
i
ma
g
e
r
y
,
”
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
Re
s
e
a
rc
h
,
v
o
l
.
2
8
,
n
o
.
3
,
p
p
.
3
6
9
–
3
7
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
3
2
4
-
0
1
9
-
0
0
2
9
7
-
7.
[
3
7
]
W
.
W
u
,
“
T
h
e
g
e
n
e
r
a
l
i
z
e
d
d
i
f
f
e
r
e
n
c
e
v
e
g
e
t
a
t
i
o
n
i
n
d
e
x
(
G
D
V
I
)
f
o
r
d
r
y
l
a
n
d
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
,
”
Re
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
1
2
1
1
–
1
2
3
3
,
2
0
1
4
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
6
0
2
1
2
1
1
.
[
3
8
]
G
.
M
i
sr
a
,
F
.
C
a
w
k
w
e
l
l
,
a
n
d
A
.
W
i
n
g
l
e
r
,
“
S
t
a
t
u
s
o
f
p
h
e
n
o
l
o
g
i
c
a
l
r
e
se
a
r
c
h
u
s
i
n
g
se
n
t
i
n
e
l
-
2
d
a
t
a
:
a
r
e
v
i
e
w
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
2
,
n
o
.
1
7
,
p
.
2
7
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
2
1
7
2
7
6
0
.
[
3
9
]
V
.
F
.
R
o
d
r
i
g
u
e
z
-
G
a
l
i
a
n
o
,
B
.
G
h
i
mi
r
e
,
J.
R
o
g
a
n
,
M
.
C
h
i
c
a
-
O
l
m
o
,
a
n
d
J
.
P
.
R
i
g
o
l
-
S
a
n
c
h
e
z
,
“
A
n
a
ss
e
ssm
e
n
t
o
f
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
a
r
a
n
d
o
m
f
o
r
e
st
c
l
a
ssi
f
i
e
r
f
o
r
l
a
n
d
-
c
o
v
e
r
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
I
S
PR
S
J
o
u
r
n
a
l
o
f
P
h
o
t
o
g
r
a
m
m
e
t
ry
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
6
7
,
p
p
.
9
3
–
1
0
4
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sp
r
s
j
p
r
s.
2
0
1
1
.
1
1
.
0
0
2
.
[
4
0
]
Z.
W
a
n
g
,
L.
X
u
,
Q
.
Ji
,
W
.
S
o
n
g
,
a
n
d
L.
W
a
n
g
,
“
A
m
u
l
t
i
-
l
e
v
e
l
n
o
n
-
u
n
i
f
o
r
m
sp
a
t
i
a
l
sam
p
l
i
n
g
met
h
o
d
f
o
r
a
c
c
u
r
a
c
y
a
ss
e
ssm
e
n
t
o
f
r
e
mo
t
e
s
e
n
s
i
n
g
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
r
e
su
l
t
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
1
6
5
5
6
8
.
[
4
1
]
A
.
Ta
s
si
,
D
.
G
i
g
a
n
t
e
,
G
.
M
o
d
i
c
a
,
L.
D
i
M
a
r
t
i
n
o
,
a
n
d
M
.
V
i
z
z
a
r
i
,
“
P
i
x
e
l
-
v
s.
o
b
j
e
c
t
-
b
a
se
d
l
a
n
d
s
a
t
8
d
a
t
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
G
o
o
g
l
e
Ea
r
t
h
E
n
g
i
n
e
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
:
t
h
e
c
a
se
s
t
u
d
y
o
f
M
a
i
e
l
l
a
N
a
t
i
o
n
a
l
P
a
r
k
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
3
,
n
o
.
1
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
3
1
2
2
2
9
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
G
e
e
ta
T.
De
sa
i
re
c
e
iv
e
d
h
e
r
B
.
E
.
d
e
g
re
e
fro
m
P
a
d
re
Co
n
c
e
ica
o
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Ve
rn
a
,
G
o
a
Un
iv
e
rsity
,
M
.
E
.
in
e
lec
tro
n
ics
a
n
d
tel
e
c
o
m
m
n
ica
ti
o
n
e
n
g
i
n
e
e
rin
g
fro
m
th
e
M
u
m
b
a
i
Un
i
v
e
rsity
in
2
0
1
4
,
a
n
d
c
o
m
p
lete
d
h
e
r
P
h
.
D.
d
e
g
re
e
in
e
lec
tro
n
ics
fro
m
Ba
b
a
sa
h
e
b
Na
ik
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
P
u
sa
d
fro
m
Am
ra
v
a
ti
u
n
i
v
e
rsity
.
S
h
e
is w
o
rk
i
n
g
a
s a
n
As
sista
n
ti
P
ro
fe
ss
o
r
in
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter,
in
An
j
u
m
a
n
-
I
-
Isla
m
’s
Ka
lse
k
a
r
Tec
h
n
ica
l
Ca
m
p
u
s.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
d
i
g
it
a
l
ima
g
e
p
ro
c
e
ss
in
g
,
re
m
o
te se
n
sin
g
,
a
n
d
m
a
c
h
i
n
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tg
e
e
tad
e
sa
i@g
m
a
il
.
c
o
m
.
Abh
a
y
N.
G
a
i
k
wa
d
re
c
e
iv
e
d
h
is
B
.
E
.
d
e
g
re
e
fro
m
Ba
b
a
sa
h
e
b
Na
ik
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
P
u
sa
d
,
Am
ra
v
a
ti
Un
iv
e
rsit
y
,
Am
ra
v
a
ti
in
1
9
9
3
,
M
.
Tec
h
.
fro
m
VN
IT
(fo
rm
e
rly
VRCE)
Na
g
p
u
r
in
2
0
0
1
a
n
d
P
h
.
D
.
fro
m
I
n
d
ian
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
,
R
o
o
r
k
e
e
,
Uttara
k
h
a
n
d
,
In
d
ia
i
n
2
0
1
2
.
He
is
p
re
se
n
tl
y
w
o
rk
i
n
g
a
s
He
a
d
o
f
De
p
a
rtme
n
t
o
f
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
Da
ta
S
c
ien
c
e
En
g
in
e
e
ri
n
g
,
Ba
b
a
sa
h
e
b
Na
ik
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
P
u
sa
d
.
He
h
a
s
2
9
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
.
His
re
se
a
rc
h
in
tere
st
i
n
c
lu
d
e
s
wire
les
s
c
o
m
m
u
n
ica
ti
o
n
,
r
a
d
a
r
sig
n
a
l
p
ro
c
e
ss
in
g
,
t
h
ro
u
g
h
wa
ll
ima
g
in
g
ra
d
a
r,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
b
h
a
y
.
n
.
g
a
i
k
wa
d
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.