I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
,
p
p
.
6
4
8
~
6
5
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
1
.
pp
648
-
6
5
9
648
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
O
DIS
-
NDVI a
n
d
whea
t
yield pa
t
t
erns a
nd pr
edicti
o
ns
in
Ta
o
una
te,
M
o
ro
cco
Sa
ra
B
o
us
k
o
ur
1
,
M
o
ha
m
ed
H
icha
m
Z
a
g
g
a
f
1
,
L
ho
us
s
a
in
B
a
ha
t
t
i
1
,
So
um
a
y
a
Z
a
y
rit
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
Ec
o
l
e
N
o
r
mal
e
S
u
p
é
r
i
e
u
r
e
d
e
l
’
En
s
e
i
g
n
e
m
e
n
t
Te
c
h
n
i
q
u
e
(
EN
S
E
T)
,
H
a
ss
a
n
I
I
U
n
i
v
e
r
si
t
y
,
M
o
h
a
mm
e
d
i
a
,
M
o
r
o
c
c
o
2
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
A
i
n
C
h
o
c
k
,
U
n
i
v
e
r
si
t
y
H
a
ss
a
n
II
-
C
a
sab
l
a
n
c
a
,
C
a
sa
b
l
a
n
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
11
,
2
0
2
4
R
ev
is
ed
Sep
12
,
2
0
2
4
Acc
ep
ted
Sep
29
,
2
0
2
4
Th
is
st
u
d
y
is
d
e
v
o
ted
to
th
e
u
se
o
f
v
a
ried
a
n
a
ly
ti
c
a
l
m
e
th
o
d
s
to
e
lu
c
id
a
te
th
e
c
o
m
p
lex
re
latio
n
sh
i
p
b
e
twe
e
n
n
o
rm
a
li
z
e
d
d
iffere
n
c
e
v
e
g
e
ta
ti
o
n
in
d
e
x
(ND
VI)
a
n
d
wh
e
a
t
p
ro
d
u
c
ti
o
n
in
Tao
u
n
a
te
,
M
o
r
o
c
c
o
b
a
se
d
o
n
M
OD
IS
S
a
telli
te
d
a
ta.
Li
n
e
a
r
re
g
re
ss
io
n
(LR)
,
wit
h
a
c
o
e
fficie
n
t
o
f
d
e
term
in
a
ti
o
n
(R²
)
o
f
0
.
9
3
,
p
ro
v
id
e
d
a
so
l
id
b
a
sis,
wh
il
e
th
e
d
e
c
isio
n
tree
(D
T)
sh
o
we
d
sig
n
ifi
c
a
n
t
p
e
rfo
rm
a
n
c
e
with
a
n
R²
o
f
0
.
8
1
.
S
u
p
p
o
r
t
v
e
c
to
r
re
g
re
ss
io
n
(S
VR)
p
e
rfo
rm
e
d
we
ll
with
a
n
R²
o
f
0
.
9
6
,
h
i
g
h
l
ig
h
ti
n
g
it
s a
b
il
i
ty
t
o
c
a
p
tu
re
th
e
n
o
n
-
li
n
e
a
r
n
u
a
n
c
e
s
o
f
th
e
d
a
ta.
G
iv
e
n
th
e
c
o
m
p
lex
it
y
i
n
h
e
re
n
t
in
t
h
e
o
b
se
rv
e
d
re
latio
n
sh
i
p
s,
c
h
a
ra
c
teriz
e
d
b
y
n
o
n
-
l
in
e
a
r
v
a
riatio
n
s,
we
o
p
ted
f
o
r
a
c
o
m
b
in
e
d
a
p
p
ro
a
c
h
.
K
-
m
e
a
n
s,
c
lo
se
ly
li
n
k
e
d
t
o
S
VR,
wa
s
in
teg
ra
ted
fo
r
it
s
a
b
il
it
y
to
id
e
n
ti
fy
h
o
m
o
g
e
n
e
o
u
s
su
b
g
ro
u
p
s
i
n
t
h
e
d
a
ta
(R
2
u
p
to
0
.
9
8
).
Th
is
c
o
m
b
in
a
ti
o
n
m
a
d
e
it
p
o
ss
i
b
l
e
to
c
ircu
m
v
e
n
t
th
e
l
imits
o
f
stri
c
tl
y
li
n
e
a
r
m
e
th
o
d
s,
t
h
u
s
re
in
f
o
rc
in
g
t
h
e
r
o
b
u
st
n
e
ss
o
f
o
u
r
a
n
a
ly
sis.
Th
e
se
re
su
lt
s
u
n
d
e
rl
in
e
th
e
c
a
p
a
c
it
y
o
f
t
h
e
c
h
o
se
n
m
e
th
o
d
o
lo
g
y
t
o
d
e
c
o
d
e
th
e
i
n
tera
c
ti
o
n
s
b
e
twe
e
n
ND
VI
a
n
d
wh
e
a
t
p
ro
d
u
c
ti
o
n
i
n
t
h
e
c
o
m
p
lex
c
o
n
tex
t
o
f
Tao
u
n
a
te.
By
p
r
o
v
i
d
i
n
g
c
lea
r
a
n
d
n
u
a
n
c
e
d
p
e
rsp
e
c
ti
v
e
s,
th
is
st
u
d
y
h
e
l
p
s
in
f
o
rm
a
g
ricu
lt
u
ra
l
d
e
c
isio
n
s
a
n
d
b
u
il
d
re
sili
e
n
c
e
to
c
li
m
a
te
c
h
a
ll
e
n
g
e
s
in
th
e
re
g
io
n
.
K
ey
w
o
r
d
s
:
E
s
tim
ate
wh
ea
t y
ield
K
-
m
ea
n
s
MO
DI
S
NDVI
SVR
T
im
e
s
er
ies
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
:
Sar
a
B
o
u
s
k
o
u
r
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
E
co
le
No
r
m
ale
Su
p
ér
ieu
r
e
d
e
l’
E
n
s
eig
n
em
en
t T
ec
h
n
iq
u
e
(
E
NSET
)
Hass
an
I
I
Un
iv
er
s
ity
Mo
h
am
m
ed
ia,
M
o
r
o
cc
o
E
m
ail: sar
a.
b
o
u
s
k
o
u
r
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Sm
ar
t
ag
r
icu
ltu
r
e
is
em
er
g
in
g
as
an
ess
en
tial
r
esp
o
n
s
e
to
f
o
o
d
s
ec
u
r
ity
an
d
clim
ate
ch
a
n
g
e
is
s
u
es.
At
th
e
h
ea
r
t
o
f
t
h
is
in
n
o
v
ativ
e
ap
p
r
o
ac
h
is
th
e
f
u
s
io
n
o
f
c
u
ttin
g
-
ed
g
e
tech
n
o
lo
g
ies
an
d
in
f
o
r
m
ed
ag
r
ic
u
ltu
r
al
p
r
ac
tices
[
1
]
,
aim
ed
at
o
p
tim
izin
g
p
r
o
d
u
ctiv
it
y
wh
ile
m
itig
atin
g
en
v
ir
o
n
m
e
n
tal
im
p
ac
ts
.
Ou
r
s
tu
d
y
f
o
llo
w
s
th
e
m
o
m
e
n
tu
m
o
f
s
m
ar
t
ag
r
icu
ltu
r
e
s
p
ec
if
ically
in
M
o
r
o
cc
o
,
w
h
er
e
wh
ea
t
cu
ltiv
ati
o
n
is
o
f
p
ar
ticu
lar
im
p
o
r
tan
ce
.
Face
d
with
co
n
s
t
an
tly
ev
o
l
v
in
g
clim
ate
ch
allen
g
es,
th
e
n
e
ed
f
o
r
ad
ap
tiv
e
s
tr
ateg
ies
em
er
g
es
as
a
p
r
io
r
ity
,
a
n
d
it is
in
th
is
p
er
s
p
e
ctiv
e
th
at
o
u
r
w
o
r
k
is
d
e
p
lo
y
e
d
[
2
]
.
T
r
ad
itio
n
al
m
eth
o
d
s
o
f
f
o
r
ec
a
s
tin
g
cr
o
p
y
ield
s
d
u
r
in
g
th
e
g
r
o
win
g
s
ea
s
o
n
ca
n
esti
m
ate
y
ie
ld
s
b
ef
o
r
e
h
ar
v
est
an
d
h
elp
m
a
k
e
m
o
r
e
in
f
o
r
m
e
d
m
an
a
g
em
en
t
d
ec
is
io
n
s
.
Alth
o
u
g
h
b
ased
o
n
s
o
u
n
d
p
h
y
s
io
lo
g
ical
an
d
p
h
y
s
ical
co
n
ce
p
ts
,
th
ese
m
et
h
o
d
s
p
r
o
v
e
in
ef
f
ec
tiv
e
in
ca
s
es
o
f
s
p
atial
s
o
il
v
ar
ia
b
ilit
y
,
s
tr
ess
,
o
r
d
if
f
er
e
n
t
m
an
ag
em
en
t
p
r
ac
tices.
I
n
co
n
tr
ast,
p
lan
t
co
v
er
r
e
m
o
te
s
en
s
in
g
is
h
ig
h
lig
h
ted
as
a
p
o
ten
tiall
y
v
alu
a
b
le
to
o
l f
o
r
ag
r
icu
ltu
r
al
m
o
n
ito
r
in
g
,
o
wi
n
g
to
its
s
y
n
o
p
tic
co
v
er
ag
e
an
d
its
ab
ilit
y
to
o
b
s
er
v
e
in
m
a
n
y
s
p
ec
tr
al
wav
elen
g
th
s
.
Ma
n
y
s
tu
d
ies
h
av
e
r
ec
o
g
n
ize
d
th
at
p
lan
t
d
ev
elo
p
m
e
n
t,
s
tr
ess
,
an
d
y
ie
ld
ca
p
ab
ilit
ies
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
MODI
S
-
N
DV
I
a
n
d
w
h
ea
t y
iel
d
p
a
tter
n
s
a
n
d
p
r
ed
ictio
n
s
in
Ta
o
u
n
a
te,
Mo
r
o
cc
o
(
S
a
r
a
B
o
u
s
ko
u
r
)
649
m
an
if
ested
in
th
e
s
p
ec
tr
al
r
e
f
lecta
n
ce
o
f
p
la
n
t
ca
n
o
p
ies
a
n
d
ca
n
b
e
q
u
an
tifie
d
u
s
in
g
v
eg
etatio
n
s
p
ec
tr
al
in
d
ices (
NDVI
,
E
VI
,
SAVI
,
A
R
VI
,
GC
L
,
R
e
C
I
)
.
A
s
tu
d
y
co
n
d
u
cted
b
y
Sh
a
f
iee
et
a
l.
[
3
]
ex
am
i
n
es
th
e
ap
p
licatio
n
o
f
two
m
ac
h
in
e
lear
n
in
g
-
b
ased
r
eg
r
ess
io
n
m
eth
o
d
s
to
p
r
ed
i
ct
wh
ea
t
g
r
ain
y
ield
f
r
o
m
v
eg
etatio
n
in
d
ices
e
x
tr
ac
ted
f
r
o
m
UAV
im
ag
es.
T
h
e
o
b
jectiv
e
o
f
th
is
r
esear
c
h
was
to
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
s
u
p
p
o
r
t
v
ec
to
r
r
e
g
r
ess
io
n
(
SVR
)
in
co
m
b
in
atio
n
with
s
eq
u
en
tial
f
o
r
war
d
s
elec
tio
n
(
SF
S)
f
o
r
g
r
ain
y
ield
p
r
ed
ictio
n
.
An
o
th
er
s
tu
d
y
,
b
y
Ash
o
u
r
lo
o
et
a
l.
[
4
]
,
e
x
p
lo
r
e
d
v
ar
io
u
s
r
e
m
o
te
s
en
s
in
g
m
eth
o
d
s
to
im
p
r
o
v
e
c
r
o
p
y
ield
f
o
r
ec
asti
n
g
.
T
h
e
m
ain
o
b
jectiv
e
o
f
t
h
is
s
tu
d
y
is
to
d
et
er
m
in
e
th
e
b
est r
em
o
te
s
en
s
in
g
ch
ar
ac
ter
is
tics
an
d
th
e
m
o
s
t e
f
f
icien
t r
eg
r
ess
io
n
m
o
d
el
f
o
r
wh
ea
t y
ield
p
r
ed
icti
o
n
in
th
e
Ham
e
d
an
r
e
g
io
n
,
I
r
a
n
.
T
o
th
is
en
d
,
we
u
s
ed
s
ev
er
a
l v
eg
etatio
n
in
d
ices
(
VI
)
an
d
r
e
f
lecta
n
ce
v
alu
es
o
b
tain
ed
f
r
o
m
Sen
tin
el
-
2
im
ag
es,
an
aly
ze
d
in
d
if
f
er
e
n
t
tim
e
win
d
o
ws,
as
in
p
u
t
d
ata
f
o
r
th
e
r
eg
r
ess
io
n
m
o
d
els
.
Am
o
n
g
th
e
m
o
d
els
test
ed
,
t
h
e
g
au
s
s
ian
r
eg
r
ess
io
n
m
o
d
el
(
GPR
)
g
av
e
th
e
b
est
r
esu
lts
,
with
a
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
o
f
0
.
2
2
8
t/
h
a
an
d
a
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
R
²
o
f
0
.
7
3
.
A
r
ec
en
t
s
tu
d
y
b
y
Ash
f
aq
et
a
l
.
[
5
]
d
em
o
n
s
tr
ated
th
at
c
o
m
b
in
in
g
m
u
ltip
le
d
atasets
u
s
in
g
th
r
ee
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
s
ig
n
if
ican
tly
im
p
r
o
v
ed
y
ield
p
r
e
d
ictio
n
p
er
f
o
r
m
an
ce
,
with
a
co
ef
f
icie
n
t
o
f
d
eter
m
in
atio
n
r
an
g
in
g
f
r
o
m
0
.
7
4
to
0
.
8
8
.
I
n
co
r
p
o
r
atin
g
s
p
atial
in
f
o
r
m
atio
n
an
d
o
th
er
p
r
o
p
er
ties
in
to
th
e
r
ef
er
en
ce
m
o
d
els
im
p
r
o
v
e
d
p
r
e
d
ictio
n
ac
cu
r
ac
y
f
r
o
m
0
.
0
8
t
o
0
.
1
2
.
Ou
r
an
al
y
s
is
ap
p
r
o
ac
h
is
b
ased
o
n
th
e
n
o
r
m
alize
d
d
if
f
e
r
e
n
ce
v
e
g
etatio
n
i
n
d
ex
(
NDVI
)
wh
ich
is
co
n
s
id
er
ed
th
e
in
d
icato
r
p
a
r
ex
ce
llen
ce
.
T
h
is
p
ar
am
eter
,
d
er
iv
ed
f
r
o
m
s
atellite
d
ata,
p
r
o
v
id
es
an
o
b
jectiv
e
m
ea
s
u
r
e
o
f
cr
o
p
h
ea
lth
an
d
v
i
g
o
r
,
b
ased
o
n
th
e
n
o
r
m
alize
d
d
if
f
er
en
ce
b
etwe
en
r
ef
lecte
d
l
ig
h
t
in
th
e
r
ed
an
d
n
ea
r
-
in
f
r
ar
ed
r
a
n
g
e
[
6
]
.
I
ts
r
elev
an
ce
lies
in
its
ab
ilit
y
to
q
u
a
n
tify
th
e
v
e
g
etatio
n
p
r
esen
ce
a
n
d
d
en
s
ity
,
th
e
r
eb
y
p
r
o
v
id
i
n
g
d
etailed
i
n
s
ig
h
t in
to
cr
o
p
p
er
f
o
r
m
an
ce
[
7
]
.
I
n
an
ag
r
ic
u
ltu
r
al
c
o
n
tex
t,
th
e
NDVI
allo
ws
th
e
cr
o
p
ev
o
lu
ti
o
n
to
b
e
o
b
s
er
v
e
d
in
a
n
o
n
-
in
t
r
u
s
iv
e
an
d
co
n
tin
u
o
u
s
m
an
n
er
[
8
]
.
I
ts
s
en
s
itiv
ity
to
c
h
an
g
es
i
n
p
lan
t
co
v
er
m
a
k
es
it
a
p
r
e
f
er
r
ed
to
o
l
f
o
r
ass
ess
in
g
s
ea
s
o
n
al
v
ar
iatio
n
s
,
wate
r
s
tr
e
s
s
,
an
d
th
e
im
p
ac
ts
o
f
clim
atic
co
n
d
itio
n
s
o
n
cr
o
p
h
ea
lth
[
9
]
,
[
1
0
]
.
B
y
c
h
o
o
s
in
g
NDVI
as
th
e
p
iv
o
t
o
f
o
u
r
s
tu
d
y
,
we
r
ely
o
n
a
p
r
o
v
e
n
s
cien
tific
m
eth
o
d
to
d
is
s
ec
t
th
e
co
m
p
lex
r
elatio
n
s
h
ip
b
etwe
en
v
eg
etatio
n
an
d
wh
ea
t
p
r
o
d
u
ctio
n
,
p
r
o
v
id
in
g
r
ic
h
an
d
n
u
a
n
ce
d
i
n
s
ig
h
ts
in
to
th
e
ag
r
icu
ltu
r
al
lan
d
s
ca
p
e
o
f
T
ao
u
n
ate.
I
n
th
is
q
u
est
f
o
r
in
-
d
ep
th
u
n
d
er
s
tan
d
in
g
,
we
h
av
e
m
o
b
ili
ze
d
a
r
an
g
e
o
f
an
aly
tical
to
o
ls
.
L
in
ea
r
r
eg
r
ess
io
n
(
L
R
)
o
u
tlin
ed
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
NDVI
a
n
d
wh
ea
t
p
r
o
d
u
ctio
n
,
wh
ile
SVR
d
elv
ed
in
to
th
e
in
tr
icac
ies
o
f
th
ese
lin
k
s
,
ca
p
tu
r
in
g
c
r
u
cial
n
o
n
-
lin
ea
r
n
u
a
n
ce
s
.
T
h
e
d
ec
is
io
n
tr
ee
(
DT
)
with
its
ab
ilit
y
to
u
n
r
av
el
co
m
p
le
x
p
atter
n
s
en
r
i
ch
ed
o
u
r
an
aly
s
is
b
y
r
ev
ea
lin
g
d
elica
te
r
elatio
n
s
h
ip
s
th
at
a
r
e
o
f
te
n
d
if
f
icu
lt
t
o
id
en
tify
.
K
-
m
ea
n
s
,
clo
s
ely
in
teg
r
ated
with
th
e
SVR
,
p
ar
titi
o
n
ed
th
e
d
ata,
r
ev
ea
lin
g
h
o
m
o
g
en
eo
u
s
g
r
o
u
p
s
an
d
th
u
s
co
n
s
o
lid
atin
g
o
u
r
p
er
ce
p
tio
n
o
f
d
if
f
e
r
en
t
b
eh
a
v
io
r
s
with
in
th
e
NDVI
-
wh
ea
t
p
r
o
d
u
ctio
n
co
n
tin
u
u
m
.
T
h
is
ap
p
r
o
ac
h
co
m
b
i
n
atio
n
h
as
s
h
ap
ed
a
h
o
lis
tic
p
er
s
p
e
ctiv
e,
tr
an
s
ce
n
d
i
n
g
th
e
b
o
u
n
d
ar
ies
o
f
tr
ad
itio
n
al
m
eth
o
d
s
to
ad
d
r
ess
co
m
p
lex
it
y
in
an
i
n
teg
r
ated
way
.
At
th
e
h
ea
r
t
o
f
th
is
wo
r
k
lies
o
u
r
s
cien
tific
ap
p
r
o
ac
h
wh
ich
e
n
s
u
r
es
o
u
r
co
m
m
itm
en
t
ef
f
ec
ti
v
en
ess
to
u
n
v
eilin
g
e
x
p
lo
itab
le
k
n
o
wl
ed
g
e
f
o
r
m
a
k
in
g
i
n
f
o
r
m
ed
ag
r
icu
ltu
r
al
d
ec
is
io
n
s
,
s
u
c
h
as
ir
r
ig
atio
n
an
d
f
er
tili
za
tio
n
[
1
1
]
.
B
y
p
r
o
b
in
g
t
h
e
d
y
n
am
ic
r
elatio
n
s
h
ip
b
etwe
en
NDVI
an
d
wh
ea
t
p
r
o
d
u
cti
o
n
,
we
aim
to
o
f
f
e
r
n
u
an
ce
d
p
er
s
p
ec
tiv
es,
th
er
eb
y
co
n
tr
ib
u
tin
g
to
s
tr
en
g
th
en
i
n
g
th
e
r
esil
ien
ce
o
f
ag
r
icu
ltu
r
al
p
r
ac
tices
in
th
e
f
ac
e
o
f
cu
r
r
en
t c
lim
ate
ch
allen
g
es a
n
d
en
s
u
r
in
g
f
o
o
d
s
ec
u
r
ity
in
th
e
T
ao
u
n
ate
r
eg
io
n
,
Mo
r
o
cc
o
.
T
h
is
ar
ticle
is
c
o
m
p
o
s
ed
o
f
d
if
f
er
en
t
s
ec
tio
n
s
aim
ed
at
a
n
ex
am
i
n
atio
n
o
f
wh
ea
t
p
r
o
d
u
ctio
n
in
T
ao
u
n
ate.
T
h
e
f
ir
s
t
s
ec
tio
n
is
d
ev
o
ted
to
th
e
p
r
ec
is
e
d
elim
itatio
n
o
f
o
u
r
s
tu
d
ied
r
eg
i
o
n
.
T
h
e
m
eth
o
d
o
l
o
g
y
s
ets
o
u
t
th
e
mo
d
u
s
o
p
era
n
d
i
,
f
r
o
m
th
e
c
o
llectio
n
o
f
NDVI
d
ata
t
o
th
e
s
tu
d
y
o
f
co
r
r
elatio
n
with
wh
ea
t
p
r
o
d
u
ctio
n
.
T
h
e
r
esu
lts
ar
e
p
r
esen
ted
g
r
ap
h
ically
,
f
o
llo
wed
b
y
a
d
is
cu
s
s
io
n
.
T
h
e
co
n
clu
s
io
n
s
u
m
m
ar
iz
es
k
ey
f
in
d
in
g
s
an
d
id
en
tifie
s
p
o
ten
tial d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
2.
ST
UDY
Z
O
N
E
Ou
r
s
tu
d
y
is
ca
r
r
ied
o
u
t
in
t
h
e
T
ao
u
n
ate
r
eg
io
n
,
lo
ca
ted
in
th
e
n
o
r
t
h
o
f
Mo
r
o
cc
o
,
8
0
k
m
f
r
o
m
Fez,
th
e
ca
p
ital
o
f
th
e
Fez
-
Me
k
n
es
r
eg
io
n
.
T
h
is
p
r
o
v
in
ce
as
h
ig
h
lig
h
ted
b
y
th
e
r
e
d
h
ex
ag
o
n
i
n
Fig
u
r
e
1
ex
ten
d
s
o
v
er
an
ar
ea
o
f
5
6
1
,
6
0
0
h
a
=
5
,
6
1
6
km
2
,
b
etwe
en
th
e
co
o
r
d
in
ates
3
4
°
3
2
′
0
9
″
n
o
r
th
an
d
4
°
3
8
′
2
4
″
west.
W
h
en
it
co
m
es
to
clim
ate,
T
ao
u
n
ate
tak
es
ad
v
a
n
tag
e
o
f
th
e
Me
d
iter
r
a
n
ea
n
wea
th
er
.
T
h
e
latter
is
ch
ar
ac
ter
ized
b
y
h
o
t,
d
r
y
s
u
m
m
er
s
an
d
r
ain
y
win
ter
s
,
wh
ic
h
cr
ea
tes
id
ea
l
c
o
n
d
itio
n
s
f
o
r
v
ar
y
in
g
ag
r
ic
u
ltu
r
al
a
ctiv
ities
.
At
th
e
s
am
e
t
im
e,
th
is
r
eg
io
n
p
r
esen
ts
wid
e
-
r
an
g
in
g
s
o
il
ty
p
es
an
d
f
av
o
r
ab
le
co
n
d
itio
n
s
f
o
r
d
iv
er
s
if
y
in
g
cr
o
p
s
.
W
e
f
in
d
c
lay
s
o
ils
p
r
o
v
id
in
g
m
o
is
tu
r
e
r
eser
v
es
u
s
ed
d
u
r
in
g
d
r
y
p
er
i
o
d
s
.
T
h
er
e
is
also
a
ty
p
e
ca
lled
l
o
am
y
with
an
in
ter
m
ed
iate
tex
tu
r
e
b
etwe
e
n
clay
an
d
s
an
d
,
th
u
s
p
r
o
m
o
tin
g
d
r
ain
ag
e
a
n
d
m
ain
tain
in
g
ce
r
tain
wate
r
r
eten
tio
n
.
Fin
ally
,
th
er
e
is
also
a
s
an
d
y
s
o
il
cr
ea
tin
g
r
ap
id
d
r
ai
n
a
g
e
co
n
d
itio
n
s
id
ea
l
f
o
r
s
p
ec
if
ic
cr
o
p
s
s
u
ch
as r
o
o
t
v
eg
etab
les,
asp
ar
ag
u
s
,
a
n
d
ar
o
m
atic
h
er
b
s
.
A
s
tu
d
y
was
c
o
n
d
u
cted
b
y
B
elm
ah
i
et
a
l.
[
1
2
]
in
th
e
Fez
-
Me
k
n
es
r
eg
io
n
to
s
tu
d
y
th
e
r
elatio
n
s
h
ip
b
etwe
en
ce
r
ea
l
y
ield
an
d
NDVI
d
ata
b
ased
o
n
t
h
e
Pear
s
o
n
co
ef
f
icien
t
a
n
d
LR
.
T
h
is
s
tu
d
y
r
ev
e
als
o
u
r
ch
o
ice
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
648
-
6
5
9
650
o
f
T
a
o
u
n
ate
as
a
s
tu
d
y
ar
ea
.
T
h
e
g
r
ap
h
lin
k
e
d
to
th
is
s
tu
d
y
p
r
o
v
es
t
h
at
T
a
o
u
n
ate
is
th
e
m
ain
p
r
o
d
u
ce
r
o
f
ce
r
ea
ls
(
3
0
%)
in
th
e
Fez
-
Me
k
n
es R
eg
io
n
.
Fig
u
r
e
1
.
L
o
ca
tio
n
o
f
th
e
s
tu
d
y
ar
ea
3.
M
E
T
H
O
D
3
.
1
.
Re
m
o
t
e
s
ens
ing
da
t
a
s
et
Ou
r
an
aly
s
is
o
f
w
h
ea
t
cr
o
p
s
in
T
ao
u
n
ate
r
elies
o
n
th
e
GI
MM
S
g
lo
b
al
ag
r
ic
u
ltu
r
al
m
o
n
ito
r
in
g
(
GL
AM
)
in
ter
f
ac
e,
a
p
latf
o
r
m
th
at
p
r
o
v
id
es
ac
ce
s
s
to
NDVI
im
ag
es
f
r
o
m
MO
DI
S
an
d
VI
I
R
S
s
atellite
s
,
as
well
as
th
e
r
etr
ie
v
al
o
f
N
DVI
d
ata
tim
e
s
er
ies
[
1
3
]
.
T
h
e
g
lo
b
al
in
v
e
n
to
r
y
m
o
d
elin
g
an
d
m
a
p
p
in
g
s
tu
d
ies/
g
lo
b
al
ag
r
icu
ltu
r
al
m
o
n
ito
r
i
n
g
(
GI
MM
S/GLAM
)
s
y
s
tem
p
r
o
v
id
es
8
-
d
ay
g
lo
b
al
d
atasets
in
n
ea
r
r
ea
l
-
tim
e.
T
h
is
d
ata
is
d
er
iv
ed
f
r
o
m
s
atellite
im
ag
es
ca
p
tu
r
ed
b
y
s
en
s
o
r
s
o
n
NASA’
s
T
er
r
a
s
p
ac
ec
r
af
t,
at
an
av
er
ag
e
s
p
atial
r
eso
lu
tio
n
o
f
5
0
0
m
eter
s
.
B
ef
o
r
e
b
ein
g
o
p
er
atio
n
al,
th
is
d
ata
u
n
d
e
r
g
o
es
atm
o
s
p
h
er
ic
co
r
r
ec
tio
n
a
n
d
clo
u
d
f
ilter
in
g
,
ca
r
r
ied
o
u
t p
ix
el
b
y
p
ix
el,
th
an
k
s
to
th
e
ef
f
o
r
ts
o
f
th
e
MO
DI
S scien
tific
team
.
T
h
e
d
ev
elo
p
m
e
n
t
an
d
p
r
o
v
is
io
n
o
f
th
is
in
ter
f
ac
e
ar
e
en
s
u
r
e
d
b
y
th
e
Natio
n
al
Aer
o
n
au
tics
an
d
Sp
ac
e
Ad
m
in
is
tr
atio
n
/Go
d
d
ar
d
Sp
a
ce
Fli
g
h
t
C
en
ter
/Th
e
Glo
b
al
I
n
v
en
t
o
r
y
Mo
d
elin
g
an
d
Ma
p
p
in
g
Stu
d
ies
(
NASA/GS
FC
/
GI
MM
S)
g
r
o
u
p
f
o
r
t
h
e
Un
ited
States
Dep
ar
tm
en
t
o
f
Ag
r
icu
ltu
r
e/
Fo
r
eig
n
Ag
r
icu
ltu
r
al
Ser
v
ice/I
n
ter
n
atio
n
al
Pr
o
d
u
cti
o
n
Ass
ess
m
en
t
Div
is
io
n
(
USDA/FAS
/I
PAD)
g
lo
b
al
ag
r
ic
u
ltu
r
al
m
o
n
ito
r
in
g
p
r
o
ject.
T
h
e
m
is
s
io
n
o
f
th
is
p
r
o
ject
is
t
o
p
r
o
v
i
d
e
a
n
o
b
je
ctiv
e,
tim
ely
,
an
d
r
e
g
u
lar
ass
ess
m
en
t
o
f
g
lo
b
al
ag
r
icu
ltu
r
al
p
r
o
d
u
ctio
n
p
r
o
s
p
e
cts an
d
co
n
d
itio
n
s
af
f
ec
tin
g
g
l
o
b
al
f
o
o
d
s
ec
u
r
ity
.
T
h
e
ch
o
ice
o
f
th
is
d
ata
f
o
r
o
u
r
s
tu
d
y
s
tem
s
f
r
o
m
t
h
e
n
e
ed
to
ac
c
ess
p
r
ec
is
e
an
d
n
ea
r
r
ea
l
-
tim
e
in
f
o
r
m
atio
n
o
n
cr
o
p
h
ea
lth
.
T
h
e
d
ata’
s
s
cien
tific
q
u
ality
,
co
u
p
le
d
with
atm
o
s
p
h
er
ic
c
o
r
r
ec
tio
n
an
d
clo
u
d
f
ilter
in
g
,
o
f
f
er
s
u
s
a
th
o
r
o
u
g
h
v
iew
o
f
th
e
e
v
o
lu
tio
n
o
f
wh
e
a
t
cr
o
p
s
i
n
T
a
o
u
n
ate
o
v
e
r
tim
e.
Du
r
in
g
o
u
r
NDVI
d
ata
ex
p
lo
r
a
tio
n
in
T
ao
u
n
at
e,
a
cr
itically
im
p
o
r
tan
t
o
b
s
er
v
atio
n
em
er
g
e
d
:
o
n
Feb
r
u
ar
y
1
8
,
2
0
1
6
,
an
in
ter
r
u
p
tio
n
was
n
o
ted
in
t
h
e
d
ata.
T
o
en
s
u
r
e
co
n
tin
u
ity
i
n
o
u
r
a
n
aly
s
is
,
we
to
o
k
co
r
r
ec
tiv
e
m
ea
s
u
r
es
b
y
r
ep
lacin
g
t
h
e
m
is
s
in
g
v
alu
e
w
ith
th
e
d
ata
av
er
a
g
e
ju
s
t
b
ef
o
r
e
an
d
af
ter
t
h
is
s
p
ec
if
ic
d
ate.
T
h
is
ap
p
r
o
ac
h
was
ad
o
p
ted
to
m
in
im
ize
th
e
im
p
ac
t
o
f
th
e
in
ter
r
u
p
tio
n
o
n
th
e
tim
e
s
er
ies
co
n
s
is
ten
cy
,
th
er
eb
y
en
ab
lin
g
a
m
o
r
e
r
eliab
le
an
aly
s
is
o
f
ag
r
icu
ltu
r
al
tr
en
d
s
.
T
em
p
o
r
ar
y
d
ata
b
r
e
ak
s
ar
e
a
co
m
m
o
n
ch
allen
g
e
i
n
tim
e
s
er
ies
-
b
ase
d
s
tu
d
ies,
an
d
th
is
c
o
r
r
ec
tio
n
h
elp
s
m
ain
tain
th
e
in
teg
r
ity
o
f
o
u
r
wh
ea
t
c
r
o
p
h
ea
lth
ass
es
s
m
en
t
in
T
ao
u
n
at
e
d
u
r
in
g
th
e
s
tu
d
y
p
er
io
d
.
3
.
2
.
P
r
o
du
ct
io
n
d
a
t
a
s
et
T
h
e
p
r
o
d
u
ctio
n
d
ata
u
s
ed
in
o
u
r
s
tu
d
y
r
ep
r
esen
ted
in
Fig
u
r
e
2
b
y
th
e
b
ar
g
r
ap
h
,
em
a
n
ate
f
r
o
m
t
h
e
h
ig
h
c
o
m
m
is
s
io
n
f
o
r
p
lan
n
in
g
(
HC
P),
th
e
m
ai
n
p
r
o
v
id
e
r
o
f
Mo
r
o
cc
o
’
s
o
f
f
icial
s
tatis
tics
.
R
eliab
le
an
d
o
f
f
icial
s
o
u
r
ce
r
ein
f
o
r
ce
s
th
e
cr
ed
ib
ili
ty
o
f
o
u
r
an
aly
s
is
,
r
ely
in
g
o
n
in
f
o
r
m
atio
n
ca
r
ef
u
lly
co
llecte
d
b
y
an
i
n
s
titu
tio
n
h
av
in
g
in
s
titu
tio
n
al
an
d
p
r
o
f
e
s
s
io
n
al
in
d
ep
en
d
e
n
ce
.
W
h
ea
t
p
r
o
d
u
ctio
n
in
T
ao
u
n
ate,
e
x
p
r
e
s
s
ed
in
m
illi
o
n
s
o
f
q
u
in
tals
,
ex
p
er
ien
ce
d
n
o
tab
le
f
lu
ctu
atio
n
s
f
r
o
m
2
0
0
0
t
o
2
0
2
0
.
I
n
2
0
0
0
,
p
r
o
d
u
ctio
n
r
ea
ch
ed
1
4
2
3
.
1
m
illi
o
n
q
u
in
tals
,
f
o
llo
wed
b
y
a
s
ig
n
if
ican
t
d
ec
lin
e
to
6
5
2
.
7
m
illi
o
n
q
u
in
tals
in
2
0
0
1
.
I
n
2
0
0
2
,
an
in
c
r
ea
s
e
was
r
ec
o
r
d
e
d
with
p
r
o
d
u
ctio
n
o
f
1
7
2
3
.
5
m
illi
o
n
q
u
in
tals
,
b
u
t
in
2
0
0
3
,
p
r
o
d
u
ctio
n
r
o
s
e
to
1
7
5
7
.
2
m
illi
o
n
q
u
in
tals
,
m
ar
k
in
g
a
y
ea
r
o
f
g
r
o
wth
.
I
n
2
0
0
4
,
p
r
o
d
u
ctio
n
d
ec
r
ea
s
ed
to
9
7
8
.
5
m
illi
o
n
q
u
in
tals
,
b
u
t
in
2
0
0
5
,
a
s
h
ar
p
in
cr
ea
s
e
was
o
b
s
er
v
ed
with
a
p
r
o
d
u
ctio
n
o
f
2
3
2
1
.
6
m
illi
o
n
q
u
in
tals
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
MODI
S
-
N
DV
I
a
n
d
w
h
ea
t y
iel
d
p
a
tter
n
s
a
n
d
p
r
ed
ictio
n
s
in
Ta
o
u
n
a
te,
Mo
r
o
cc
o
(
S
a
r
a
B
o
u
s
ko
u
r
)
651
Fig
u
r
e
2
.
An
n
u
al
wh
ea
t
y
ield
(
2
0
0
0
–
2
0
2
0
)
I
n
2
0
0
6
,
p
r
o
d
u
ctio
n
f
ell
to
5
5
3
.
3
m
illi
o
n
q
u
in
tals
,
o
n
ly
to
e
x
p
er
ien
ce
a
s
ig
n
if
ica
n
t
in
cr
ea
s
e
in
2
0
0
7
,
r
ea
ch
in
g
1
6
5
8
m
illi
o
n
q
u
in
tal
s
.
T
h
e
f
o
llo
win
g
y
ea
r
s
wer
e
m
ar
k
ed
b
y
v
a
r
iatio
n
s
,
with
h
i
g
h
p
o
in
ts
in
2
0
0
9
(
1
0
6
3
.
3
m
illi
o
n
q
u
in
tals
)
an
d
2
0
1
6
(
2
1
4
6
.
5
m
illi
o
n
q
u
in
tals
)
.
T
h
e
y
ea
r
2
0
1
5
wa
s
ch
ar
ac
ter
ized
b
y
ex
ce
p
tio
n
ally
l
o
w
p
r
o
d
u
ctio
n
,
r
ec
o
r
d
in
g
o
n
ly
2
5
1
.
8
m
il
lio
n
q
u
i
n
tals
.
I
n
2
0
1
7
,
p
r
o
d
u
ctio
n
r
e
b
o
u
n
d
ed
,
r
ea
ch
in
g
1
,
7
7
6
m
illi
o
n
q
u
in
t
als.
T
h
e
y
ea
r
s
2
0
1
8
an
d
2
0
1
9
s
aw
a
d
ec
r
ea
s
e
in
p
r
o
d
u
cti
o
n
,
with
r
esp
ec
tiv
e
f
ig
u
r
es
o
f
9
6
9
.
5
an
d
4
7
0
.
2
m
illi
o
n
q
u
in
tals
.
I
n
2
0
2
0
,
p
r
o
d
u
ctio
n
i
n
cr
ea
s
ed
to
1
9
0
4
.
4
m
illi
o
n
q
u
in
tals
.
T
h
is
d
ata
s
h
o
ws
th
e
in
f
l
u
en
ce
o
f
f
ac
t
o
r
s
s
u
ch
as
wea
th
er
co
n
d
itio
n
s
,
ag
r
ic
u
ltu
r
al
p
r
ac
tices,
an
d
o
th
er
en
v
ir
o
n
m
en
tal
v
ar
ia
b
les.
3
.
3
.
Da
t
a
s
et
co
rr
el
a
t
io
n study
T
h
e
s
tu
d
y
o
f
th
e
c
o
r
r
elatio
n
b
etwe
en
NDVI
v
alu
es
d
e
r
iv
ed
f
r
o
m
MO
DI
S
im
a
g
es
(
ev
e
r
y
8
d
ay
s
)
a
n
d
an
n
u
al
wh
ea
t
p
r
o
d
u
ctio
n
p
r
o
v
id
es
a
d
ec
is
iv
e
p
e
r
s
p
ec
tiv
e
to
s
h
ed
lig
h
t
o
n
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
v
eg
etatio
n
an
d
wh
ea
t
g
r
ain
y
ield
.
B
y
ch
e
ck
in
g
th
e
c
o
r
r
elatio
n
b
etwe
en
th
ese
m
ea
s
u
r
em
en
ts
an
d
wh
ea
t
y
ield
,
we
s
ee
k
to
d
eter
m
in
e
t
h
e
d
e
g
r
ee
to
wh
ic
h
p
lan
t
v
ig
o
r
,
as
ca
p
tu
r
ed
b
y
N
DVI
,
i
m
p
ac
ts
p
r
o
d
u
ctiv
it
y
.
T
h
is
m
eth
o
d
m
ak
es
it
p
o
s
s
ib
le
to
d
eter
m
in
e
cr
itical
p
h
ases
o
f
th
e
wh
ea
t
g
r
o
wth
cy
cle
wh
er
e
th
e
co
r
r
elatio
n
p
r
o
v
id
es
v
er
y
h
ig
h
v
alu
es,
h
en
c
e
p
r
o
v
id
i
n
g
in
f
o
r
m
atio
n
o
n
th
e
c
r
itical
m
o
m
en
ts
.
A
p
o
s
itiv
e
co
r
r
elatio
n
v
alu
e
in
d
icate
s
th
at
o
p
ti
m
al
p
lan
t
co
n
d
itio
n
s
ar
e
lin
k
ed
to
v
er
y
h
i
g
h
p
r
o
d
u
cti
o
n
,
wh
ile
a
n
e
g
ativ
e
co
r
r
elat
io
n
v
alu
e
s
u
g
g
ests
ad
v
er
s
e
f
ac
to
r
s
f
o
r
g
r
o
wth
.
B
y
v
is
u
alizin
g
th
e
co
r
r
elatio
n
g
r
ap
h
p
r
esen
ted
in
Fig
u
r
e
3
,
we
n
o
tice
a
s
ig
n
if
ican
tly
h
ig
h
co
r
r
elatio
n
b
etwe
en
th
e
NDVI
-
MO
DI
S
v
alu
es
an
d
th
e
an
n
u
al
wh
ea
t
p
r
o
d
u
ctio
n
d
u
r
in
g
th
e
p
e
r
io
d
(
T
1
3
-
T
2
5
)
wh
ich
co
r
r
esp
o
n
d
s
to
th
e
p
e
r
io
d
f
r
o
m
J
an
u
ar
y
1
7
to
A
p
r
il 3
0
.
Du
r
in
g
th
is
tim
e
-
lap
s
e,
a
s
u
s
tain
ed
p
o
s
itiv
e
co
r
r
elatio
n
b
etwe
en
NDVI
an
d
wh
ea
t
y
i
eld
h
en
ce
s
u
g
g
ests
th
at
cr
o
p
h
ea
lth
d
eter
m
in
ed
b
y
th
e
v
eg
etatio
n
in
d
ex
h
as
a
n
o
tab
le
ef
f
ec
t
o
n
wh
ea
t
p
r
o
d
u
ctio
n
.
Fig
u
r
e
3
.
Hig
h
lig
h
t o
f
th
e
co
r
r
elatio
n
p
er
io
d
b
etwe
en
NDVI
an
d
wh
ea
t y
ield
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
648
-
6
5
9
652
T
h
e
d
ata
ch
o
ice
f
o
r
th
e
r
e
g
r
e
s
s
io
n
is
ju
s
tifie
d
b
y
th
e
f
ac
t
th
at
th
is
p
er
io
d
(
J
an
1
7
-
Ap
r
3
0
)
s
ee
m
s
p
ar
ticu
lar
l
y
s
en
s
itiv
e
to
v
a
r
iatio
n
s
in
NDVI
,
u
n
lik
e
th
e
o
th
e
r
m
o
m
e
n
ts
.
T
h
u
s
,
it
s
ee
m
s
r
ea
s
o
n
ab
le
to
s
u
g
g
est
th
at
th
e
wh
ea
t
h
a
r
v
est
is
s
ig
n
if
ican
tly
im
p
ac
ted
b
y
e
n
v
ir
o
n
m
en
tal
an
d
a
g
r
icu
ltu
r
al
co
n
d
itio
n
s
d
u
r
in
g
th
ese
wee
k
s
.
B
y
f
o
cu
s
in
g
o
n
th
is
p
h
ase,
th
e
r
elatio
n
s
h
ip
b
etwe
en
t
h
e
v
eg
etatio
n
in
d
ex
an
d
wh
ea
t
p
r
o
d
u
ctio
n
ca
n
b
e
ca
p
tu
r
ed
in
a
m
o
r
e
p
r
ec
is
e
way
,
th
er
ef
o
r
e
lead
in
g
to
v
e
r
y
r
eliab
le
an
d
s
p
ec
if
ic
p
r
ed
ictio
n
s
at
th
is
s
o
-
ca
lled
cr
itical
tem
p
o
r
al
r
an
g
e
o
f
th
e
cr
o
p
wh
ea
t
g
r
o
wth
c
y
cle.
3
.
4
.
K
-
m
e
a
ns
c
lus
t
er
ing
wit
h SV
R
m
o
delin
g
I
n
o
u
r
s
tu
d
y
,
we
s
ee
k
to
im
p
l
em
en
t
a
clu
s
ter
in
g
(
K
-
m
ea
n
s
)
an
d
SVR
ap
p
r
o
ac
h
to
ag
r
icu
l
tu
r
al
d
ata.
T
h
e
o
b
jectiv
e
is
to
m
o
d
el
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
av
e
r
ag
e
NDVI
f
o
r
ea
ch
y
ea
r
(
2
0
0
0
to
2
0
2
0
)
a
n
d
th
e
co
r
r
esp
o
n
d
in
g
wh
ea
t
p
r
o
d
u
cti
o
n
.
T
h
e
p
r
o
ce
s
s
s
tar
t
s
b
y
ap
p
ly
in
g
th
e
K
-
m
ea
n
s
alg
o
r
ith
m
to
g
r
o
u
p
th
e
y
ea
r
s
in
to
k
clu
s
ter
s
,
th
en
o
b
tain
in
g
th
e
clu
s
ter
ce
n
ter
s
μ
(
m
ea
n
N
DVI
)
f
o
r
ea
ch
clu
s
ter
j,
an
d
f
in
ally
o
b
tain
in
g
th
e
clu
s
ter
ass
ig
n
m
en
t in
d
ices c
(i)
f
o
r
ea
ch
y
ea
r
i
.
Ma
th
em
atica
lly
,
th
is
co
u
ld
b
e
ex
p
r
ess
ed
as f
o
llo
ws:
(
,
)
=
∑
=
1
∑
=
1
∥
∥
(
)
−
∥
∥
2
⋅
(
(
)
=
)
(
1
)
s
u
ch
th
at:
x
(
i
):
th
e
av
er
a
g
e
o
f
th
e
NDVI
f
o
r
y
ea
r
i
μ
: th
e
ce
n
ter
o
f
clu
s
ter
j
c
(
i
)
: th
e
in
d
ex
o
f
th
e
cl
u
s
ter
to
wh
ich
y
ea
r
i is ass
ig
n
ed
I
(
⋅
)
: th
e
in
d
icato
r
f
u
n
ctio
n
T
h
en
,
f
o
r
ea
ch
clu
s
ter
id
en
tifi
ed
b
y
K
-
m
ea
n
s
,
an
SVR
m
o
d
el
is
tr
ain
ed
.
Fo
r
ea
ch
clu
s
ter
j,
we
m
u
s
t
ex
tr
ac
t
th
e
y
ea
r
s
i
b
elo
n
g
i
n
g
t
o
clu
s
ter
j,
th
en
ap
p
ly
th
e
SV
R
o
n
th
is
s
u
b
s
et
o
f
d
ata
(
X
j
,
Y
j
)
,
an
d
f
in
ally
o
b
tain
th
e
weig
h
ts
w
j
,
th
e
b
ias b
j
,
a
n
d
th
e
p
r
ed
ictio
n
s
Y
’
j
f
o
r
t
h
is
clu
s
ter
.
Ma
th
em
atica
lly
,
th
is
co
u
l
d
b
e
ex
p
r
ess
ed
as
:
min
,
,
⋅
∗
1
2
⋅
+
∑
=
1
(
,
+
,
∗
)
(
2
)
f
o
r
a
s
p
ec
if
ic
clu
s
ter
j [
1
4
]
:
Un
d
er
th
e
c
o
n
s
tr
ain
ts
:
,
−
⋅
,
−
≤
+
,
⋅
,
+
−
,
≤
+
,
∗
(
3
)
w
h
er
e:
x
j,
i
: th
e
av
er
ag
e
o
f
NDVI
f
o
r
y
ea
r
i in
clu
s
ter
j
y
j,
i:
th
e
wh
ea
t p
r
o
d
u
ctio
n
f
o
r
y
ea
r
i in
clu
s
ter
j
ξ
j,
i
an
d
ξ*
j,
i
: th
e
d
ev
iatio
n
v
ar
i
ab
les
“C”: th
e
r
eg
u
lar
izatio
n
p
ar
am
eter
,
an
d
ε
is
a
to
ler
a
b
le
er
r
o
r
p
ar
am
eter
.
T
h
is
r
ep
r
esen
ts
a
m
o
d
elin
g
ap
p
r
o
ac
h
wh
er
e
K
-
m
ea
n
s
is
u
s
e
d
to
id
en
tify
clu
s
ter
s
o
f
s
im
ila
r
b
eh
av
io
r
in
ter
m
s
o
f
m
ea
n
NDVI
,
an
d
th
en
SVR
is
ap
p
lied
to
ea
c
h
clu
s
ter
to
m
o
d
el
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
NDVI
an
d
wh
ea
t p
r
o
d
u
ctio
n
with
in
e
ac
h
g
r
o
u
p
.
Ou
r
s
o
lu
tio
n
o
p
tim
izes
d
ata
m
an
ag
e
m
en
t
b
y
u
s
in
g
clu
s
ter
in
g
to
d
i
v
id
e
d
ata
ac
co
r
d
in
g
to
its
d
is
p
er
s
io
n
,
f
o
llo
wed
b
y
p
r
ec
i
s
e
ap
p
licatio
n
o
f
SVR
.
W
e
h
av
e
in
teg
r
ated
two
k
ey
m
eth
o
d
s
:
c
lu
s
ter
in
g
an
d
n
o
r
m
aliza
tio
n
:
w
e
s
tar
t
b
y
g
r
o
u
p
in
g
d
ata
in
to
h
o
m
o
g
e
n
eo
u
s
clu
s
ter
s
v
ia
K
-
m
ea
n
s
an
d
th
en
n
o
r
m
alize
th
e
d
at
a
to
en
s
u
r
e
a
f
air
an
d
b
alan
ce
d
co
m
p
ar
is
o
n
.
Hy
p
er
p
ar
a
m
eter
s
ea
r
ch
an
d
cr
o
s
s
-
v
alid
atio
n
:
f
o
r
ea
ch
clu
s
ter
,
we
em
p
lo
y
R
an
d
o
m
ized
Sear
ch
C
V
to
ex
p
lo
r
e
th
e
SVR
h
y
p
er
p
ar
am
eter
s
p
ac
e
ef
f
icien
tly
,
ad
j
u
s
tin
g
th
e
v
al
u
es
o
f
C
,
g
am
m
a,
ep
s
ilo
n
,
an
d
k
er
n
el
.
W
e
u
s
e
L
ea
v
eOn
eOu
t
f
o
r
s
m
all
clu
s
ter
s
to
ad
ju
s
t
th
e
n
u
m
b
er
o
f
f
o
l
d
s
f
o
r
lar
g
er
clu
s
ter
s
,
en
s
u
r
in
g
p
r
o
p
er
cr
o
s
s
-
v
alid
atio
n
an
d
av
o
id
i
n
g
o
v
e
r
f
itti
n
g
.
T
h
is
ap
p
r
o
ac
h
g
u
ar
an
tees
r
o
b
u
s
t
p
r
ed
ictio
n
s
ad
a
p
ted
to
th
e
s
p
ec
if
i
c
ch
ar
ac
ter
is
tics
o
f
ea
ch
cl
u
s
ter
.
4.
RE
SU
L
T
S
T
h
e
d
ata
was
s
p
lit
in
to
two
tr
ain
in
g
a
n
d
test
in
g
s
ets,
with
r
atio
s
o
f
8
0
%
an
d
2
0
%,
r
e
s
p
ec
tiv
ely
.
T
h
e
d
is
tr
ib
u
tio
n
b
etwe
en
tr
ai
n
in
g
an
d
test
in
g
p
ar
ts
s
ig
n
if
i
ca
n
tly
in
f
lu
en
c
es
th
e
r
esu
lt
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
o
en
s
u
r
e
co
n
s
is
ten
cy
b
etwe
en
d
atasets
o
f
d
if
f
er
en
t
s
izes,
w
e
m
ain
tain
ed
th
e
s
am
e
r
atio
.
Alth
o
u
g
h
th
e
ch
o
ice
o
f
th
is
r
atio
d
e
p
en
d
s
o
n
p
er
s
o
n
al
p
r
e
f
e
r
en
ce
,
o
p
tin
g
f
o
r
a
h
ig
h
e
r
p
r
o
p
o
r
tio
n
in
th
e
tr
ain
in
g
s
et
ten
d
s
to
im
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
o
f
th
e
r
e
s
u
lts
.
T
h
e
r
atio
we
o
p
ted
f
o
r
is
th
e
m
o
s
t r
ec
o
m
m
en
d
e
d
o
n
e
[
1
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
MODI
S
-
N
DV
I
a
n
d
w
h
ea
t y
iel
d
p
a
tter
n
s
a
n
d
p
r
ed
ictio
n
s
in
Ta
o
u
n
a
te,
Mo
r
o
cc
o
(
S
a
r
a
B
o
u
s
ko
u
r
)
653
As
p
ar
t
o
f
o
u
r
s
tu
d
y
o
n
wh
ea
t
p
r
o
d
u
ctio
n
in
T
ao
u
n
ate,
we
ad
o
p
ted
a
v
ar
ie
d
ap
p
r
o
ac
h
to
a
n
aly
ze
th
e
d
ata
[
1
6
]
,
tak
in
g
in
to
ac
co
u
n
t
in
p
ar
ticu
lar
th
e
NDVI
.
First,
we
ex
p
lo
r
ed
lin
ea
r
tr
e
n
d
s
u
s
in
g
LR
b
y
ass
ess
in
g
th
e
co
r
r
elatio
n
b
etwe
en
NDVI
an
d
wh
ea
t
p
r
o
d
u
ctio
n
.
Nex
t
,
we
ap
p
lied
SVR
to
ac
co
u
n
t
f
o
r
p
o
ten
tial
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
an
d
also
in
co
r
p
o
r
at
ed
NDVI
in
to
o
u
r
m
o
d
el.
Fo
r
in
-
d
ep
th
u
n
d
er
s
tan
d
in
g
,
we
also
u
s
ed
th
e
DT
alg
o
r
ith
m
to
ca
p
tu
r
e
co
m
p
lex
s
tr
u
ctu
r
es
in
th
e
d
ata,
in
t
eg
r
atin
g
NDVI
as
a
k
ey
v
ar
ia
b
le
in
th
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
.
Su
b
s
eq
u
en
tly
,
we
r
ef
in
ed
o
u
r
an
aly
s
is
b
y
in
teg
r
atin
g
th
e
K
-
m
ea
n
s
alg
o
r
i
th
m
in
co
n
ju
n
ctio
n
with
th
e
SVR
,
wh
ile
co
n
tin
u
in
g
to
co
n
s
id
er
th
e
NDVI
as a
d
eter
m
in
in
g
f
ac
t
o
r
in
t
h
e
clu
s
ter
f
o
r
m
atio
n
.
No
w,
we
ar
e
r
ea
d
y
to
p
r
esen
t
th
e
r
esu
lts
v
is
u
ally
in
g
r
ap
h
f
o
r
m
.
T
h
ese
g
r
ap
h
ical
r
e
p
r
esen
tatio
n
s
in
clu
d
in
g
NDVI
will
allo
w
u
s
to
clea
r
ly
illu
s
tr
ate
tr
en
d
s
,
clu
s
ter
in
g
p
atter
n
s
,
a
n
d
r
el
atio
n
s
h
ip
s
b
etwe
en
v
ar
iab
les,
p
r
o
v
id
in
g
an
in
-
d
e
p
th
v
is
u
al
u
n
d
er
s
tan
d
in
g
o
f
th
e
d
y
n
am
ics
o
f
wh
ea
t
p
r
o
d
u
ctio
n
in
T
a
o
u
n
ate
o
v
er
tim
e.
T
h
is
m
u
ltid
im
en
s
io
n
al
a
p
p
r
o
ac
h
will a
llo
w
u
s
to
ex
p
lo
r
e
th
e
s
p
ec
if
ic
co
n
tr
i
b
u
tio
n
o
f
NDVI
to
v
ar
iatio
n
s
in
wh
ea
t p
r
o
d
u
ctio
n
.
4
.
1
.
L
inea
r
r
eg
re
s
s
io
n
LR
allo
ws
y
o
u
to
b
u
ild
a
m
o
d
el
attem
p
tin
g
to
f
i
n
d
a
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
t
h
e
in
d
ep
en
d
e
n
t
v
ar
iab
les
(
X)
an
d
th
e
p
r
ed
icte
d
d
ep
en
d
en
t
v
ar
ia
b
le
(
Y)
.
Fro
m
a
v
is
u
al
o
b
s
er
v
atio
n
,
we
tr
y
to
cr
ea
te
a
lin
e
s
o
th
at
th
e
p
o
in
ts
ar
e
as
clo
s
e
a
s
p
o
s
s
ib
le,
co
m
p
ar
ed
to
o
th
er
p
o
s
s
ib
le
lin
es
[
4
]
,
[1
7
].
T
h
e
LR
alg
o
r
ith
m
was
ap
p
lied
to
d
ates
with
a
b
etter
co
r
r
elatio
n
b
etwe
en
MO
DI
S
-
NDVI
an
d
wh
ea
t
g
r
ain
y
ield
t
o
b
e
ab
le
to
p
r
e
d
ict
p
r
o
d
u
ctiv
ity
b
ased
o
n
th
e
d
er
i
v
ed
NDVI
.
T
h
e
r
eg
r
ess
io
n
lin
e
s
lo
p
e
s
h
o
wn
in
Fig
u
r
e
4
in
d
icate
s
a
p
o
s
itiv
e
r
elatio
n
s
h
ip
b
etwe
en
NDVI
v
alu
es
an
d
wh
ea
t
y
ield
.
I
n
o
th
er
wo
r
d
s
,
as
th
e
NDVI
v
alu
e
in
c
r
ea
s
es,
wh
ea
t
g
r
ain
p
r
o
d
u
ctio
n
ten
d
s
to
in
cr
ea
s
e,
th
is
s
u
g
g
ests
a
s
t
r
o
n
g
co
r
r
elatio
n
b
etwe
en
p
lan
t
h
ea
lth
,
r
e
p
r
esen
ted
b
y
NDVI
,
an
d
ag
r
icu
ltu
r
al
p
r
o
d
u
ctio
n
[
1
8
]
.
Ho
wev
er
,
it
is
im
p
o
r
tan
t
to
n
o
te
th
at
th
is
co
r
r
elatio
n
d
o
es
n
o
t
n
ec
ess
ar
ily
ju
s
tify
d
ir
ec
t
ca
u
s
atio
n
,
s
in
ce
o
th
er
f
ac
to
r
s
ca
n
g
r
ea
tly
in
f
lu
e
n
ce
p
r
o
d
u
ctio
n
s
u
ch
as
ex
tr
em
e
wea
th
er
f
ac
to
r
s
.
T
h
is
is
s
ee
n
o
n
th
e
g
r
ap
h
an
d
is
r
ef
lecte
d
b
y
p
o
in
ts
a
litt
le
away
f
r
o
m
th
e
lin
e.
T
h
e
d
eter
m
in
atio
n
co
ef
f
icien
t
o
f
0
.
9
3
is
a
s
tr
o
n
g
in
d
icatio
n
t
h
at
9
3
%
o
f
th
e
v
ar
iab
ilit
y
in
p
r
o
d
u
ctio
n
is
m
ain
ly
lin
k
e
d
t
o
c
h
an
g
es
i
n
th
e
NDVI
v
alu
e
.
T
h
is
s
h
o
w
s
th
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
p
r
ed
ict
wh
ea
t
g
r
ai
n
y
ield
b
ased
o
n
th
e
NDVI
v
al
u
e
d
er
iv
e
d
f
r
o
m
th
e
s
tu
d
y
ar
ea
s
atellite
im
ag
es.
T
h
e
R
MSE
o
f
0
.
1
5
5
f
o
r
tifie
s
th
e
r
eg
r
ess
io
n
r
esu
lts
co
n
f
ir
m
i
n
g
t
h
e
lin
k
b
etwe
en
NDI
V
an
d
wh
ea
t p
r
o
d
u
ctio
n
.
4
.
2
.
T
he
decisi
o
n
t
rees
DT
h
av
e
s
h
o
wn
th
eir
s
u
p
er
i
o
r
ity
in
m
o
d
elin
g
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
.
T
h
ey
p
er
f
o
r
m
s
u
cc
ess
iv
e
d
iv
is
io
n
s
o
f
th
e
d
ata
b
ased
o
n
th
e
p
r
ed
icto
r
s
,
wh
ich
allo
ws
th
em
to
cr
ea
te
n
o
n
-
lin
ea
r
s
ep
ar
atio
n
zo
n
es.
T
h
u
s
,
if
th
e
d
ep
en
d
en
t
an
d
th
e
in
d
ep
en
d
en
t
v
ar
iab
le
ch
a
n
g
e
in
a
n
o
n
-
lin
ea
r
m
an
n
e
r
,
th
e
tr
ee
ca
n
ca
p
tu
r
e
th
es
e
ch
an
g
es,
h
en
ce
th
e
u
s
e
o
f
t
h
is
alg
o
r
ith
m
to
m
o
d
el
t
h
e
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
b
etwe
en
t
h
e
av
er
ag
e
NDVI
an
d
wh
ea
t p
r
o
d
u
ctio
n
[
19
]
.
W
e
o
b
s
er
v
e
t
h
at
th
e
p
r
e
d
icted
an
d
o
b
s
er
v
ed
v
alu
e
p
o
i
n
ts
ar
e
clo
s
ely
s
u
p
e
r
im
p
o
s
ed
,
th
is
m
ea
n
s
th
at
o
u
r
m
o
d
el
is
p
er
tin
en
t.
T
h
is
i
s
also
co
n
f
ir
m
ed
b
y
th
e
R
2
o
f
0
.
8
0
w
h
ich
is
g
en
er
ally
co
n
s
id
er
ed
a
g
o
o
d
f
i
t
(
Fig
u
r
e
5
)
.
Plo
ttin
g
th
e
g
r
a
p
h
(
Fig
u
r
e
6
)
allo
wed
u
s
to
o
p
ti
m
ally
v
is
u
alize
th
e
s
tr
o
n
g
co
r
r
elatio
n
b
etwe
en
th
e
p
r
ed
icted
v
alu
es
an
d
th
e
co
l
lecte
d
v
alu
es.
W
e
b
ased
o
u
r
s
elv
es
o
n
th
e
p
ea
k
s
o
f
th
e
p
lo
t
s
u
p
er
p
o
s
itio
n
.
W
e
co
u
n
t 1
4
p
ea
k
s
th
at
o
v
er
la
p
p
er
f
ec
tly
.
Fig
u
r
e
4
.
NDVI
-
wh
ea
t
p
r
o
d
u
c
tio
n
LR
(
2
0
0
0
–
2
0
2
0
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
648
-
6
5
9
654
Fig
u
r
e
5
.
W
h
ea
t
p
r
o
d
u
ctio
n
DT
r
ep
r
es
en
tatio
n
Fig
u
r
e
6
.
Pre
d
icte
d
an
d
o
b
s
er
v
ed
wh
ea
t
p
r
o
d
u
ctio
n
4
.
3
.
Vec
t
o
r
re
g
re
s
s
io
n su
pp
o
rt
S
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
(
S
V
M
)
a
r
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
w
i
d
e
l
y
u
s
e
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
[
2
0
]
,
[2
1
]
an
d
r
eg
r
ess
io
n
task
s
[
2
2
]
-
[2
4
]
.
T
h
eir
p
o
p
u
lar
ity
s
tem
s
f
r
o
m
th
eir
ab
ilit
y
to
f
in
d
o
p
tim
al
d
ec
is
io
n
b
o
u
n
d
a
r
ies
i
n
m
u
l
t
i
d
i
m
e
n
s
i
o
n
a
l
s
p
a
c
e
s
,
m
a
k
i
n
g
t
h
e
m
p
a
r
t
i
c
u
l
a
r
l
y
s
u
i
t
e
d
t
o
c
o
m
p
l
e
x
p
r
o
b
l
e
m
s
i
n
s
e
v
e
r
a
l
f
i
e
l
d
s
:
m
e
d
i
c
a
l
[
2
5
],
an
d
ed
u
ca
tio
n
[
2
6
]
.
SVR
b
ec
o
m
es
a
r
eliab
le
ch
o
ice
wh
en
d
ea
lin
g
with
s
p
ar
s
e
d
ataset
s
[
2
7
]
.
I
ts
ab
ilit
y
to
m
o
d
el
c
o
m
p
lex
n
o
n
-
lin
ea
r
r
el
atio
n
s
h
ip
s
,
p
ar
ticu
la
r
ly
t
h
r
o
u
g
h
th
e
u
s
e
o
f
k
er
n
els
s
u
ch
as
r
ad
ial
b
asis
f
u
n
ctio
n
(
RBF
)
,
m
ak
es
it
p
o
s
s
ib
le
to
ca
p
tu
r
e
s
u
b
tle
p
atter
n
s
p
r
ese
n
t
in
s
ca
tter
ed
d
ata.
Un
lik
e
s
o
m
e
lin
ea
r
m
o
d
el
s
,
wh
ich
ca
n
p
er
f
o
r
m
p
o
o
r
l
y
in
th
is
s
itu
atio
n
,
SVR
is
p
o
wer
f
u
l
to
i
d
en
tify
t
r
en
d
s
.
Stra
te
g
ically
p
o
s
itio
n
ed
s
u
p
p
o
r
t
v
ec
to
r
s
co
n
tr
ib
u
te
to
th
e
r
o
b
u
s
tn
ess
o
f
th
e
m
o
d
el,
p
r
o
v
id
i
n
g
g
r
ea
ter
f
lex
ib
ilit
y
to
ad
ap
t
to
ch
an
g
es
in
h
er
en
t
i
n
s
p
ar
s
e
d
ata.
T
h
e
r
e
f
o
r
e,
t
h
e
ch
o
ice
o
f
SVR
is
ju
s
tifie
d
d
u
e
to
its
in
tr
in
s
ic
ab
ilit
y
to
c
o
p
e
with
th
e
ch
allen
g
es
o
f
d
ata
d
is
p
er
s
io
n
b
y
p
r
o
v
id
in
g
r
eliab
le
an
d
ac
cu
r
ate
r
esu
lts
ev
en
in
s
itu
atio
n
s
wh
er
e
o
th
er
m
o
d
els
m
ay
s
tr
u
g
g
le.
L
o
o
k
in
g
at
th
e
g
r
a
p
h
in
Fig
u
r
e
7
,
we
p
er
ce
iv
e
th
e
e
x
ac
t
s
u
p
er
p
o
s
itio
n
o
f
th
e
s
u
p
p
o
r
t
v
e
cto
r
p
o
in
ts
with
th
e
o
b
s
er
v
ed
d
ata
p
o
i
n
ts
.
T
h
is
p
h
e
n
o
m
en
o
n
d
em
o
n
s
tr
ates
th
e
ab
ilit
y
o
f
th
e
m
o
d
el
t
o
ef
f
ec
tiv
ely
id
e
n
tify
an
d
ex
p
lo
it
th
e
m
o
s
t
cr
itical
p
o
in
ts
in
th
e
co
n
s
tr
u
ctio
n
o
f
t
h
e
m
o
d
el.
Mo
r
e
r
em
a
r
k
ab
l
y
,
th
e
p
o
in
ts
p
r
ed
ic
ted
b
y
SVR
s
h
o
w
p
er
f
ec
t
p
r
o
x
im
i
ty
to
th
e
r
ea
l
d
ata,
e
v
en
in
t
h
e
p
r
esen
ce
o
f
s
ig
n
if
ica
n
t
d
is
p
er
s
io
n
.
T
h
is
b
eh
a
v
io
r
h
ig
h
lig
h
ts
th
e
m
o
d
el’
s
a
b
ilit
y
to
g
en
er
alize
a
n
d
s
tr
o
n
g
ly
ca
p
tu
r
e
u
n
d
er
l
y
in
g
p
atter
n
s
d
esp
ite
th
e
in
h
er
e
n
t
v
ar
iab
ilit
y
in
th
e
d
ata.
T
h
e
h
i
g
h
R
2
o
f
0
.
9
6
in
d
icate
s
th
at
th
e
m
o
d
el
in
ter
p
r
ets
th
e
v
ar
ian
ce
in
th
e
d
ata
well,
th
u
s
s
tr
en
g
th
en
in
g
o
u
r
ex
p
la
n
atio
n
.
Fig
u
r
e
7
.
SVR
g
r
ap
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
MODI
S
-
N
DV
I
a
n
d
w
h
ea
t y
iel
d
p
a
tter
n
s
a
n
d
p
r
ed
ictio
n
s
in
Ta
o
u
n
a
te,
Mo
r
o
cc
o
(
S
a
r
a
B
o
u
s
ko
u
r
)
655
4
.
4
.
I
m
ple
m
ent
a
t
io
n o
f
K
-
mea
ns
clus
t
er
ing
T
h
e
tr
an
s
itio
n
f
r
o
m
a
m
o
d
el
s
o
lely
b
ased
o
n
SVR
to
a
m
o
d
el
b
ased
jo
in
tly
o
n
K
-
m
ea
n
s
an
d
SVR
r
ep
r
esen
ts
a
s
tr
ateg
ic
ev
o
lu
tio
n
in
th
e
m
o
d
elin
g
ap
p
r
o
ac
h
.
I
n
itially
,
SVR
s
tan
d
s
o
u
t
f
o
r
its
ab
ili
ty
to
s
eiz
e
in
tr
icate
r
elatio
n
s
h
ip
s
in
d
ata,
p
r
o
v
id
in
g
ac
cu
r
ate
p
r
e
d
ictio
n
s
ev
en
in
co
n
tex
ts
o
f
d
is
p
er
s
io
n
.
Ho
wev
er
,
b
y
in
tr
o
d
u
ci
n
g
K
-
m
ea
n
s
,
we
aim
to
b
etter
u
n
d
er
s
tan
d
th
e
u
n
d
er
ly
in
g
s
tr
u
ctu
r
e
o
f
th
e
d
ata
b
y
id
en
tif
y
in
g
h
o
m
o
g
en
eo
u
s
clu
s
ter
s
.
E
ac
h
th
en
b
ec
o
m
es
th
e
s
u
b
s
tr
at
e
f
o
r
a
d
ed
icate
d
SVR
m
o
d
el,
allo
win
g
f
in
er
ad
ap
tatio
n
.
T
h
is
ca
s
ca
d
e
ap
p
r
o
ac
h
f
o
cu
s
es
o
n
o
p
tim
izin
g
t
h
e
ac
cu
r
ac
y
an
d
in
ter
p
r
etab
ili
ty
o
f
th
e
m
o
d
el
b
y
r
ec
o
g
n
izin
g
an
d
p
r
o
ce
s
s
in
g
l
o
ca
l
v
ar
iatio
n
s
.
I
n
itially
,
we
m
u
s
t
v
is
u
alize
th
e
d
ata
to
d
ef
in
e
th
e
n
ee
d
f
o
r
clu
s
ter
in
g
;
h
er
e
we
u
s
e
th
e
s
am
e
d
ataset,
n
am
ely
th
e
an
n
u
a
l
av
er
ag
e
NDVI
as
th
e
in
d
ep
en
d
en
t
v
ar
iab
le
(
X
)
an
d
th
e
wh
ea
t
g
r
ain
p
r
o
d
u
ctio
n
as th
e
v
ar
iab
le
tar
g
et
o
n
wh
i
ch
we
in
ten
d
t
o
p
r
e
d
ict
(
Fig
u
r
e
8
)
.
T
h
e
d
ata
p
o
in
ts
d
o
n
o
t
f
o
llo
w
a
d
is
tr
ib
u
tio
n
th
at
ca
n
b
e
e
n
ca
p
s
u
lated
in
th
e
h
y
p
er
p
la
n
e.
So
,
u
s
in
g
t
h
e
K
-
m
ea
n
s
clu
s
ter
in
g
alg
o
r
ith
m
is
in
o
r
d
e
r
,
b
u
t
o
n
e
m
u
s
t
f
ir
s
t
d
ete
r
m
in
e
th
e
o
p
tim
al
clu
s
ter
n
u
m
b
er
to
ac
cu
r
ately
r
etain
th
e
d
ata
p
o
in
ts
with
in
th
e
id
en
tifie
d
clu
s
ter
n
u
m
b
er
.
T
o
th
at
en
d
,
we
co
u
ld
u
s
e
th
e
Sil
h
o
u
ette
co
ef
f
icien
t
(
Fig
u
r
e
9
)
.
I
f
th
e
latter
is
h
ig
h
,
th
is
im
p
lies
a
g
r
o
u
p
in
g
o
f
b
etter
q
u
ality
;
a
s
co
r
e
th
at
r
ea
c
h
es
th
e
v
alu
e
1
r
e
v
ea
ls
s
p
ac
ed
an
d
d
is
tin
g
u
is
h
ed
clu
s
ter
s
wh
ile
a
s
co
r
e
o
f
0
s
u
g
g
ests
an
in
s
ig
n
if
ican
t
d
is
tan
ce
b
etwe
en
clu
s
ter
s
.
W
h
en
th
e
s
co
r
e
is
-
1
,
it in
d
icate
s
an
in
co
r
r
ec
t c
lu
s
ter
ass
ig
n
m
en
t.
Fig
u
r
e
8
.
NDVI
an
d
wh
ea
t p
r
o
d
u
ctio
n
r
elatio
n
s
h
ip
(
2
0
0
0
–
2
0
2
0
)
Fig
u
r
e
9
.
Sil
h
o
u
ette
co
ef
f
icien
t sco
r
es o
f
d
if
f
er
en
t c
lu
s
ter
n
u
m
b
e
r
s
T
h
e
Sil
h
o
u
ette
co
ef
f
icien
t
h
a
s
a
cr
u
cial
im
p
ac
t
o
n
d
ec
is
io
n
-
m
ak
in
g
r
eg
ar
d
in
g
t
h
e
clu
s
ter
n
u
m
b
e
r
.
Af
ter
its
ev
alu
ati
on
,
we
f
o
u
n
d
two
p
r
o
m
is
in
g
o
p
tio
n
s
:
eith
er
th
r
ee
o
r
f
iv
e
clu
s
ter
s
.
T
o
d
is
p
el
th
is
u
n
ce
r
tain
ty
b
etwe
en
th
e
two
alter
n
ativ
es,
it
is
ess
en
tial
to
g
o
th
r
o
u
g
h
a
s
ilh
o
u
ette
an
aly
s
is
;
th
i
s
is
t
h
e
v
is
u
al
in
d
icato
r
allo
win
g
th
e
co
h
er
en
ce
e
v
alu
a
tio
n
an
d
t
h
e
s
eg
m
en
tatio
n
s
tab
ilit
y
b
ased
o
n
th
e
s
ilh
o
u
ette
o
u
tlin
e
th
ick
n
ess
.
I
n
Fig
u
r
e
1
0
,
we
co
u
ld
s
ee
s
ig
n
if
ican
t
s
tab
ilit
y
an
d
clea
r
s
ep
ar
atio
n
b
etwe
en
th
e
clu
s
ter
s
.
As
f
o
r
Sil
h
o
u
ette
v
alu
es,
t
h
ey
ar
e
u
n
if
o
r
m
an
d
h
i
g
h
,
s
ig
n
if
y
i
n
g
b
etter
in
tr
ac
lu
s
ter
c
o
h
esio
n
an
d
in
ter
cl
u
s
ter
d
is
tin
ctio
n
.
No
twith
s
tan
d
in
g
,
in
th
e
f
iv
e
cl
u
s
ter
s
ca
s
e
(
Fig
u
r
e
11)
,
th
e
p
l
o
t
th
ick
n
e
s
s
d
is
p
lay
s
a
clea
r
r
esem
b
lan
ce
wh
ich
co
u
ld
lea
d
to
o
v
er
-
s
eg
m
en
tatio
n
a
n
d
e
x
ce
s
s
iv
e
co
m
p
lex
ity
,
s
in
ce
ce
r
tain
clu
s
ter
s
co
u
ld
h
av
e
a
s
tr
o
n
g
s
im
ilar
ity
with
th
eir
p
ee
r
s
.
4
.
5
.
SVR
cr
ea
t
i
o
n f
o
r
clus
t
er
s
T
h
e
s
ec
o
n
d
s
tep
c
o
n
s
is
ts
o
f
d
ev
elo
p
in
g
SVM
f
o
r
r
eg
r
ess
io
n
(
SVR
)
f
o
r
ea
ch
o
f
th
e
es
tab
lis
h
ed
clu
s
ter
s
as
s
ee
n
in
F
ig
u
r
e
1
2
.
T
h
is
m
ak
es
it
p
o
s
s
ib
le
to
im
p
lem
en
t
an
in
d
i
v
id
u
alize
d
ap
p
r
o
ac
h
th
at
aim
s
t
o
co
n
s
tr
u
ct
r
e
g
r
ess
io
n
m
o
d
els
s
p
ec
if
ic
to
e
ac
h
s
u
b
g
r
o
u
p
o
f
d
ata,
in
th
is
way
we
will
o
b
tai
n
a
s
o
lu
tio
n
a
d
ap
ted
to
th
e
co
m
p
lex
ity
in
h
e
r
en
t in
t
h
e
s
eg
m
en
ted
d
ataset
s
u
b
ject
o
f
o
u
r
s
tu
d
y
.
C
r
ea
tin
g
s
ep
ar
ate
SVR
m
o
d
els
f
o
r
ea
c
h
cl
u
s
ter
allo
ws
th
e
o
p
tim
izatio
n
o
f
o
v
er
all
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
b
y
ca
p
tu
r
in
g
th
e
n
u
an
ce
s
an
d
v
a
r
iatio
n
s
s
p
ec
if
ic
to
ea
ch
s
u
b
g
r
o
u
p
as
C
L
0
an
d
C
L
2
h
as
an
R
2
=
0
.
9
8
an
d
C
L
1
h
as
an
R
2
=
0
.
8
5
.
T
h
u
s
,
th
e
ch
o
ice
o
f
SV
R
tu
r
n
s
o
u
t
to
b
e
ju
d
icio
u
s
,
it
ex
ce
ls
in
m
o
d
elin
g
non
-
lin
ea
r
r
elatio
n
s
h
ip
s
wh
ile
m
in
im
izin
g
th
e
p
r
ed
ictio
n
er
r
o
r
,
h
en
ce
t
h
e
lo
w
R
MSE
f
o
r
th
e
th
r
ee
clu
s
ter
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
648
-
6
5
9
656
Fig
u
r
e
10
.
Sil
h
o
u
ette
a
n
aly
s
is
f
o
r
K
-
m
ea
n
s
(
k
=3
)
Fig
u
r
e
11
.
Sil
h
o
u
ette
a
n
aly
s
is
f
o
r
K
-
m
ea
n
s
(
k
=5
)
Fig
u
r
e
12
.
C
o
m
b
in
ed
K
-
m
ea
n
s
/SV
R
r
esu
lts
g
r
ap
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
MODI
S
-
N
DV
I
a
n
d
w
h
ea
t y
iel
d
p
a
tter
n
s
a
n
d
p
r
ed
ictio
n
s
in
Ta
o
u
n
a
te,
Mo
r
o
cc
o
(
S
a
r
a
B
o
u
s
ko
u
r
)
657
5.
DIS
CU
SS
I
O
N
Ou
r
s
tu
d
y
e
x
ce
ed
s
th
e
r
esu
lts
o
f
p
r
ev
io
u
s
r
esear
ch
in
ter
m
s
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
ML
alg
o
r
ith
m
s
,
as
s
h
o
wn
in
T
ab
le
1
.
W
h
ile
p
r
ev
io
u
s
s
tu
d
ies
m
ain
ly
u
s
ed
g
lo
b
al
ap
p
r
o
ac
h
es,
we
d
e
m
o
n
s
tr
ated
t
h
at
o
u
r
alg
o
r
ith
m
s
,
n
o
ta
b
ly
SVR
,
d
eliv
er
r
esu
lts
s
u
p
er
io
r
s
.
T
o
f
u
r
th
er
im
p
r
o
v
e
th
is
p
er
f
o
r
m
a
n
ce
,
we
co
m
b
in
ed
K
-
m
ea
n
s
with
SV
R
,
wh
ich
al
lo
wed
u
s
to
b
etter
m
an
ag
e
d
a
ta
h
eter
o
g
en
eity
an
d
o
b
tain
m
o
r
e
ac
cu
r
ate
y
ield
f
o
r
ec
asts
.
Ou
r
r
esu
lts
s
h
o
w
a
s
tr
o
n
g
co
r
r
elatio
n
b
etwe
en
NDVI
an
d
wh
ea
t
p
r
o
d
u
ctio
n
.
LR
y
ield
ed
an
R
²
o
f
0
.
9
3
an
d
an
R
MSE
o
f
0
.
0
1
5
,
i
n
d
icatin
g
a
s
tr
o
n
g
b
u
t
lim
ited
m
atch
in
ca
p
tu
r
in
g
n
o
n
-
lin
ea
r
d
y
n
am
ics
b
etwe
en
v
ar
iab
les.
I
n
co
n
tr
ast,
SVR
d
em
o
n
s
tr
ated
in
cr
ea
s
ed
a
b
ilit
y
to
m
o
d
el
th
ese
m
o
r
e
co
m
p
lex
r
elatio
n
s
h
i
p
s
,
with
an
R
²
o
f
0
.
9
6
an
d
an
R
MSE
o
f
0
.
0
8
5
,
o
u
tp
er
f
o
r
m
in
g
LR
in
ter
m
s
o
f
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
T
h
e
DT
m
o
d
el,
alth
o
u
g
h
h
a
v
in
g
a
n
ab
i
lity
to
h
an
d
le
n
o
n
-
lin
ea
r
r
elati
o
n
s
h
ip
s
,
p
r
esen
ted
lo
wer
p
er
f
o
r
m
an
ce
with
an
R
²
o
f
0
.
8
1
an
d
an
R
MSE
o
f
0
.
2
4
7
,
wh
ich
h
ig
h
lig
h
ts
its
lim
itatio
n
s
in
th
e
f
ac
e
o
f
th
e
c
o
m
p
lex
it
y
o
f
th
e
d
ata.
T
o
i
m
p
r
o
v
e
th
e
m
o
d
elin
g
o
f
d
ata
h
eter
o
g
e
n
eity
,
we
s
eg
m
e
n
ted
th
e
d
ataset
in
to
th
r
ee
clu
s
ter
s
u
s
in
g
th
e
K
-
m
ea
n
s
alg
o
r
ith
m
.
T
h
is
s
eg
m
en
tatio
n
h
elp
ed
r
e
v
ea
l
u
n
d
er
ly
in
g
s
tr
u
ct
u
r
es
in
th
e
d
ata,
with
a
f
ir
s
t
clu
s
ter
p
r
im
ar
ily
co
m
p
o
s
ed
o
f
lin
ea
r
r
elatio
n
s
h
ip
s
,
wh
ile
t
h
e
o
th
er
t
wo
clu
s
ter
s
r
ep
r
esen
ted
m
o
r
e
co
m
p
lex
n
o
n
-
lin
ea
r
b
eh
av
io
r
s
.
Fo
r
n
o
n
-
lin
ea
r
clu
s
ter
s
,
we
ap
p
lied
SVR
wi
th
a
R
B
F
k
er
n
el,
wh
ich
is
b
etter
s
u
ited
to
ca
p
tu
r
in
g
n
o
n
lin
ea
r
r
elatio
n
s
h
i
p
s
.
T
h
is
ap
p
r
o
ac
h
s
ig
n
if
ican
tly
im
p
r
o
v
ed
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el,
r
ea
ch
in
g
an
R
²
o
f
0
.
9
8
f
o
r
clu
s
ter
s
0
an
d
2
,
an
d
an
R
²
o
f
0
.
8
5
f
o
r
clu
s
ter
1
.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
at
th
e
clu
s
ter
in
g
ap
p
r
o
ac
h
f
o
llo
wed
b
y
r
eg
r
ess
io
n
ad
ap
ted
m
a
k
es
it
p
o
s
s
ib
le
to
b
etter
m
o
d
el
th
e
co
m
p
lex
ity
o
f
th
e
i
n
ter
ac
tio
n
s
b
etwe
en
NDVI
an
d
wh
ea
t
p
r
o
d
u
ctio
n
,
co
m
p
ar
ed
to
g
lo
b
al
m
eth
o
d
s
.
Ho
we
v
er
,
lik
e
a
n
y
s
tu
d
y
,
o
u
r
s
h
as
lim
itati
o
n
s
.
Data
in
ter
r
u
p
tio
n
s
i
n
Feb
r
u
ar
y
2
0
1
6
,
alth
o
u
g
h
m
an
ag
ed
b
y
th
e
in
cl
u
s
io
n
o
f
av
er
a
g
es
o
f
n
eig
h
b
o
r
in
g
d
ata,
m
ay
h
a
v
e
in
tr
o
d
u
ce
d
b
ias.
Ad
d
itio
n
ally
,
th
e
s
p
atial
an
d
tem
p
o
r
al
v
ar
ia
b
ilit
y
o
f
NDVI
d
ata
an
d
t
h
e
c
o
m
p
lex
ity
o
f
en
v
ir
o
n
m
e
n
tal
in
ter
ac
tio
n
s
m
ay
lim
it
th
e
g
en
er
aliza
b
ilit
y
o
f
th
e
r
esu
lts
.
T
h
e
r
esu
lts
o
b
tain
ed
in
th
is
s
tu
d
y
p
av
e
th
e
way
f
o
r
f
u
tu
r
e
im
p
r
o
v
em
en
ts
in
ag
r
icu
ltu
r
al
y
ield
m
o
d
elin
g
.
A
m
o
r
e
r
ef
in
ed
ap
p
r
o
ac
h
,
in
teg
r
atin
g
u
n
m
an
n
e
d
ae
r
ial
v
eh
icle
(
UAV
)
im
ag
er
y
d
ata
co
m
b
in
e
d
with
s
atellite
im
ag
er
y
,
c
o
u
ld
c
o
n
s
id
er
ab
ly
im
p
r
o
v
e
t
h
e
s
p
atial
r
eso
lu
tio
n
an
d
ac
c
u
r
ac
y
o
f
f
o
r
ec
asts
.
Ad
d
itio
n
ally
,
in
clu
d
in
g
o
th
er
en
v
ir
o
n
m
en
tal
an
d
clim
atic
v
ar
iab
les
in
m
o
d
els
co
u
ld
h
elp
ca
p
tu
r
e
th
e
co
m
p
lex
m
u
ltifa
cto
r
ial
in
ter
ac
tio
n
s
th
at
in
f
lu
en
ce
a
g
r
ic
u
ltu
r
al
y
ield
s
.
An
o
th
e
r
av
en
u
e
wo
u
ld
b
e
to
test
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es,
s
u
ch
as
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
e
two
r
k
s
(
C
NN)
,
to
im
p
r
o
v
e
th
e
m
o
d
els'
ab
ilit
y
to
h
an
d
le
d
ata
v
ar
iab
ilit
y
an
d
co
m
p
lex
ities
[2
8
]
.
T
ab
le
1
.
Pre
v
i
o
u
s
s
tu
d
ies
’
s
y
n
o
p
tic
tab
le
A
u
t
h
o
r
Lo
c
a
t
i
o
n
R
S
i
m
a
g
e
s
M
L
a
l
g
o
r
i
t
h
ms
R
2
R
M
S
E
S
h
a
f
i
e
e
e
t
a
l
.
[
3
]
V
o
l
l
e
b
e
k
k
r
e
se
a
r
c
h
f
a
r
m
,
a
t
t
h
e
N
M
B
U
,
S
o
u
t
h
-
Ea
st
e
r
n
N
o
r
w
a
y
UAV
S
V
R
LA
S
S
O
0
.
9
0
0
.
9
0
0
.
4
7
9
0
.
5
0
0
A
sh
o
u
r
l
o
o
e
t
a
l
.
[
4
]
H
a
med
a
n
,
I
r
a
n
S
e
n
t
i
n
e
l
-
2
G
P
R
RF
S
V
R
DT
0
.
7
3
0
.
7
1
0
.
6
8
0
.
5
8
0
.
2
2
8
0
.
2
3
7
0
.
2
4
9
0
.
2
8
3
B
e
l
ma
h
i
e
t
a
l
.
[
1
2
]
F
e
z
-
M
e
k
n
e
s
r
e
g
i
o
n
,
M
o
r
o
c
c
o
M
O
D
I
S
-
N
D
V
I
LR
[
0
.
5
8
-
0
.
7
9
]
[
2
.
1
2
-
4
.
9
6
]
q
/
h
a
A
sh
f
a
q
e
t
a
l
.
[
5
]
P
u
n
j
a
b
P
r
o
v
i
n
c
e
,
P
a
k
i
s
t
a
n
La
n
d
sa
t
8
S
V
M
RF
LA
S
S
O
0
.
8
8
0
.
7
4
0
.
8
0
0
.
0
5
0
.
0
3
0
.
6
0
O
u
r
p
r
e
se
n
t
st
u
d
y
Ta
o
u
n
a
t
e
P
r
o
v
i
n
c
e
,
F
e
z
-
M
e
k
n
e
s
r
e
g
i
o
n
,
M
o
r
o
c
c
o
M
O
D
I
S
-
N
D
V
I
LR
DT
S
V
R
0
.
9
3
0
.
8
1
0
.
9
6
0
.
1
5
5
0
.
2
4
7
0
.
0
8
5
6.
CO
NCLU
SI
O
N
AND
P
E
RS
P
E
CT
I
VE
S
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ated
t
h
e
ef
f
ec
tiv
en
ess
o
f
MO
DI
S
s
p
ec
tr
al
d
ata,
an
d
in
p
ar
ticu
lar
th
e
NDVI
in
d
ex
,
f
o
r
f
o
r
ec
asti
n
g
wh
ea
t
y
ield
s
.
T
h
e
r
esu
lts
r
ev
ea
led
a
s
ig
n
if
ican
t
r
elatio
n
s
h
ip
b
etwe
e
n
NDVI
an
d
wh
ea
t
p
r
o
d
u
ctio
n
,
v
alid
atin
g
its
u
s
e
as
a
r
eliab
le
y
ield
in
d
i
ca
t
o
r
.
T
h
e
a
p
p
licatio
n
o
f
v
a
r
io
u
s
ML
alg
o
r
ith
m
s
,
in
clu
d
in
g
LR
,
DT
,
an
d
SVR
,
h
as
h
elp
ed
d
ev
elo
p
r
o
b
u
s
t
p
r
ed
ictiv
e
m
o
d
els.
T
h
e
in
teg
r
atio
n
o
f
clu
s
ter
in
g
with
K
-
m
ea
n
s
f
u
r
th
er
m
a
d
e
it
p
o
s
s
ib
le
to
p
er
s
o
n
alize
f
o
r
ec
asts
b
y
s
eg
m
en
t,
th
er
eb
y
im
p
r
o
v
in
g
t
h
e
ac
cu
r
ac
y
o
f
th
e
esti
m
ates.
A
n
o
tab
le
a
d
v
an
ce
m
en
t
o
f
th
is
r
esear
ch
is
th
e
ab
i
lity
to
m
a
k
e
y
ield
f
o
r
ec
asts
s
in
ce
th
e
b
eg
i
n
n
in
g
o
f
th
e
g
r
o
win
g
s
ea
s
o
n
.
B
y
u
s
in
g
NDVI
at
th
e
wel
l
-
d
ef
in
ed
p
er
i
o
d
m
en
tio
n
e
d
ab
o
v
e
,
it
is
p
o
s
s
ib
le
to
p
r
o
v
id
e
an
esti
m
ate
o
f
y
ield
s
ea
r
ly
en
o
u
g
h
to
allo
w
g
r
o
wer
s
to
an
ticip
ate
ch
allen
g
es
an
d
im
p
l
em
en
t
s
o
lu
tio
n
s
to
o
p
tim
ize
p
r
o
d
u
ctio
n
.
T
h
is
ap
p
r
o
ac
h
n
o
t
o
n
ly
m
a
k
es
it
p
o
s
s
ib
le
to
b
etter
p
lan
t
h
e
n
e
ce
s
s
ar
y
in
ter
v
en
tio
n
s
,
b
u
t
also
to
a
d
ap
t
a
g
r
icu
ltu
r
al
p
r
ac
tices
b
ased
o
n
f
o
r
ec
asts
,
th
u
s
in
cr
ea
s
in
g
y
ield
s
an
d
th
e
ag
r
icu
ltu
r
al
s
y
s
tem
s
s
u
s
tain
ab
ilit
y
.
I
n
co
n
clu
s
io
n
,
th
is
r
esear
ch
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
ce
o
f
r
em
o
te
s
en
s
in
g
tech
n
o
lo
g
ies
an
d
ad
v
an
ce
d
an
aly
tical
tec
h
n
iq
u
es
to
im
p
r
o
v
e
ag
r
icu
ltu
r
al
m
an
ag
em
en
t
an
d
b
u
ild
r
esil
ien
ce
to
e
n
v
ir
o
n
m
en
tal
v
ar
iatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.