I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
4
0
5
~
4
1
5
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
5
.
i
1
.
pp
405
-
4
1
5
405
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Cro
p predi
ction i
n
Ta
mil Na
du
a
cc
o
rding
t
o
enviro
n
menta
l and
so
il f
a
ctors
using
h
y
brid ma
chine
l
ea
rning
architec
t
ure
Su
nd
a
ra
j
K
a
nn
a
n Sus
ee
1
,
Sh
enba
g
a
ra
ma
s
ub
ra
m
a
nia
n Shenb
a
g
a
Va
div
u
2
,
M
urug
esa
n
Senthil K
um
a
r
3
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
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
M
o
h
a
me
d
S
a
t
h
a
k
A
J
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
C
h
e
n
n
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
S
R
M
V
a
l
l
i
a
mm
a
i
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
C
h
e
n
n
a
i
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
a
r
p
a
g
a
V
i
n
a
y
a
g
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
e
n
g
a
l
p
a
t
t
u
,
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
May
14
,
2
0
2
5
R
ev
is
ed
No
v
2
6
,
2
0
2
5
Acc
ep
ted
Feb
17
,
2
0
2
6
M
a
th
u
ra
n
th
a
g
a
m
,
Tam
il
Na
d
u
,
I
n
d
ia
is
th
e
si
te
o
f
t
h
is
re
se
a
rc
h
in
it
i
a
ti
v
e
th
a
t
e
m
p
lo
y
s
sta
te
-
of
-
th
e
-
a
rt
h
y
b
ri
d
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
rc
h
it
e
c
tu
re
s
to
fo
re
c
a
st
c
ro
p
s
u
it
a
b
i
li
ty
i
n
re
lati
o
n
t
o
e
n
v
ir
o
n
m
e
n
tal
a
n
d
so
il
c
h
a
ra
c
teristics
.
Th
e
m
o
d
e
l
ta
k
e
s
a
d
v
a
n
ta
g
e
o
f
t
h
e
stre
n
g
t
h
s
o
f
l
in
e
a
r
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
c
las
sifier,
b
i
d
irec
ti
o
n
a
l
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(B
iL
S
TM
)
,
a
n
d
c
o
n
v
o
lu
ti
o
n
a
l
LS
TM
(C
o
n
v
LS
TM
)
n
e
two
r
k
s,
a
n
d
t
h
e
d
a
ta
to
c
a
p
tu
re
c
o
m
p
li
c
a
ted
tem
p
o
ra
l
a
n
d
sp
a
ti
a
l
c
o
rre
latio
n
s.
To
p
re
p
a
re
t
h
e
d
a
tas
e
t
fo
r
m
o
d
e
l
train
in
g
,
i
t
is
n
o
rm
a
li
z
e
d
u
sin
g
m
i
n
-
m
a
x
sc
a
li
n
g
a
n
d
t
h
e
n
fe
a
tu
re
se
lec
ted
u
sin
g
a
Ja
y
a
o
p
ti
m
iza
ti
o
n
tec
h
n
iq
u
e
.
Th
e
d
a
tas
e
t
c
o
n
tain
s
v
a
riab
les
su
c
h
a
s
h
u
m
id
it
y
,
ra
in
fa
ll
,
tem
p
e
ra
tu
re
,
a
n
d
p
H.
B
o
th
th
e
BiL
S
T
M
a
n
d
th
e
Co
n
v
LS
TM
im
p
ro
v
e
th
e
m
o
d
e
l'
s
c
o
m
p
re
h
e
n
sio
n
o
f
c
o
n
tex
t
fro
m
b
o
t
h
pr
e
v
io
u
s
a
n
d
s
u
b
se
q
u
e
n
t
ti
m
e
st
e
p
s.
Th
e
Co
n
v
LS
TM
a
lso
re
c
o
r
d
s
sp
a
ti
a
l
d
e
p
e
n
d
e
n
c
ies
.
A
p
o
we
rfu
l
d
e
c
isio
n
-
m
a
k
i
n
g
to
o
l
fo
r
d
iffere
n
ti
a
ti
n
g
a
c
ro
ss
c
ro
p
v
a
rieties
is
t
h
e
li
n
e
a
r
S
VM
c
las
sifier.
Co
m
p
a
rin
g
t
h
e
h
y
b
ri
d
m
o
d
e
l'
s
p
e
rfo
rm
a
n
c
e
to
th
a
t
o
f
tra
d
it
i
o
n
a
l
LS
TM
a
p
p
r
o
a
c
h
e
s
u
si
n
g
m
e
a
su
r
e
s
su
c
h
a
s
re
c
a
ll
,
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
a
n
d
F
1
-
sc
o
re
sh
o
ws
t
h
a
t
it
p
e
rfo
rm
s
m
u
c
h
b
e
tt
e
r.
Us
in
g
t
h
is
a
p
p
ro
a
c
h
c
a
n
se
e
h
o
w
d
e
e
p
lea
rn
i
n
g
(DL)
c
a
n
su
p
p
le
m
e
n
t
m
o
re
c
o
n
v
e
n
ti
o
n
a
l
M
L
m
e
th
o
d
s
a
n
d
s
e
e
h
o
w
imp
o
rta
n
t
l
o
c
a
l
e
n
v
ir
o
n
m
e
n
tal
d
a
ta
is
fo
r
a
g
ric
u
lt
u
ra
l
p
o
li
c
y
a
n
d
p
lan
n
in
g
.
K
ey
w
o
r
d
s
:
B
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
C
o
n
v
o
lu
tio
n
al
L
STM
C
r
o
p
p
r
ed
ictio
n
E
n
v
ir
o
n
m
en
tal
f
ac
to
r
s
L
in
ea
r
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
So
il p
ar
am
eter
s
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
:
Su
n
d
ar
aj
Kan
n
a
n
Su
s
ee
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
Mo
h
am
ed
Sath
a
k
A
J
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
C
h
en
n
ai,
I
n
d
ia
E
m
ail: su
s
ee
k
an
n
an
0
7
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Ag
r
icu
ltu
r
e
is
a
f
u
n
d
am
e
n
t
al
co
m
p
o
n
en
t
o
f
I
n
d
ia’
s
ec
o
n
o
m
y
,
with
cr
o
p
y
ield
s
ig
n
if
ican
tly
in
f
lu
en
ce
d
b
y
s
o
il p
r
o
p
er
ties
an
d
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
.
I
n
ar
ea
s
in
clu
d
e
Ma
th
u
r
an
th
a
g
am
,
T
am
il Na
d
u
,
I
n
d
ia
er
r
atic
wea
th
er
p
atter
n
s
,
s
o
il
h
eter
o
g
en
eity
,
an
d
clim
a
te
ch
an
g
e
p
r
o
v
i
d
e
co
n
s
id
er
ab
le
o
b
s
tacle
s
to
co
n
v
en
tio
n
al
cr
o
p
p
lan
n
in
g
a
n
d
m
an
ag
em
e
n
t.
T
r
ad
itio
n
al
m
eth
o
d
s
,
d
ep
e
n
d
en
t
o
n
h
is
to
r
ical
d
ata
o
r
ex
p
er
t
h
eu
r
is
tics
,
o
f
ten
n
e
g
lect
th
e
c
o
m
p
lex
s
p
atio
-
tem
p
o
r
al
i
n
ter
ac
tio
n
s
am
o
n
g
en
v
ir
o
n
m
en
tal
an
d
s
o
il
v
ar
ia
b
les,
r
esu
ltin
g
in
in
ad
eq
u
ate
cr
o
p
s
elec
tio
n
an
d
r
ed
u
ce
d
y
ield
s
.
Pre
cise
cr
o
p
s
u
itab
ilit
y
p
r
ed
ictio
n
is
es
s
en
tial
f
o
r
f
ar
m
er
s
,
in
s
u
r
er
s
,
an
d
r
eg
u
lat
o
r
s
,
f
ac
il
itatin
g
in
f
o
r
m
e
d
ch
o
ices
ab
o
u
t
cr
o
p
p
lan
n
in
g
,
r
is
k
m
an
ag
em
e
n
t,
an
d
r
eso
u
r
ce
d
is
tr
ib
u
tio
n
.
T
h
is
r
e
s
ea
r
ch
in
tr
o
d
u
ce
s
a
h
y
b
r
id
m
ac
h
in
e
lear
n
in
g
(
ML
)
f
r
am
e
wo
r
k
th
at
co
m
b
in
es
co
n
v
o
l
u
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
C
o
n
v
L
STM
)
,
b
i
d
ir
ec
tio
n
al
L
STM
(
B
iLST
M)
,
an
d
lin
ea
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
class
i
f
ier
s
to
p
r
ed
ict
cr
o
p
s
u
itab
ili
ty
f
o
r
2
2
p
r
in
cip
al
cr
o
p
s
,
s
u
ch
as
r
ice,
m
aize
,
ch
ick
p
ea
,
p
u
ls
es,
f
r
u
its
,
an
d
co
m
m
er
cial
c
o
m
m
o
d
ities
.
T
h
e
m
o
d
el
u
tili
s
es
C
o
n
v
L
STM
to
ca
p
tu
r
e
s
p
atial
d
ep
en
d
e
n
cies
in
s
o
il
an
d
cl
i
m
atic
d
ata,
B
iL
STM
to
an
aly
s
e
tem
p
o
r
al
tr
en
d
s
,
an
d
SVM
to
en
h
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
405
-
4
1
5
406
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
in
p
u
t
f
ea
tu
r
es
ar
e
te
m
p
er
atu
r
e,
r
ain
f
all,
h
u
m
id
it
y
,
s
o
il
p
H,
NPK
co
n
ce
n
tr
atio
n
,
an
d
tex
tu
r
e
,
wh
ich
ar
e
n
o
r
m
alis
ed
an
d
o
p
tim
is
ed
b
y
f
ea
t
u
r
e
s
elec
tio
n
u
s
in
g
th
e
J
ay
a
alg
o
r
ith
m
.
T
h
e
p
r
im
ar
y
aim
s
o
f
t
h
is
s
tu
d
y
ar
e
to
i)
im
p
r
o
v
e
p
r
ed
icti
o
n
ac
cu
r
ac
y
co
m
p
ar
ed
to
in
d
i
v
id
u
al
class
if
ier
s
o
r
co
n
v
en
tio
n
al
m
o
d
els,
ii)
p
r
o
v
i
d
e
s
ea
s
o
n
al
an
d
g
eo
g
r
ap
h
ical
cr
o
p
s
u
itab
ilit
y
m
ap
s
,
an
d
iii)
d
eliv
er
ac
tio
n
ab
le
in
s
ig
h
ts
f
o
r
ag
r
ic
u
ltu
r
al
p
lan
n
i
n
g
.
T
h
e
p
r
im
ar
y
c
o
n
tr
ib
u
tio
n
s
ar
e:
i)
a
r
eg
io
n
-
s
p
ec
if
ic
d
ataset
th
at
ca
p
t
u
r
es
th
e
s
o
il
an
d
clim
ate
v
ar
iab
ilit
y
o
f
Ma
th
u
r
an
t
h
ag
am
,
ii)
a
h
y
b
r
i
d
m
o
d
el
ex
h
ib
itin
g
e
x
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
with
an
ac
cu
r
ac
y
,
an
d
iii)
v
is
u
alis
atio
n
s
co
m
p
r
is
in
g
f
ea
tu
r
e
i
m
p
o
r
tan
ce
r
an
k
in
g
s
,
s
ea
s
o
n
al
s
u
itab
ilit
y
ch
ar
ts
,
an
d
g
eo
g
r
a
p
h
ic
i
n
f
o
r
m
atio
n
s
y
s
tem
s
(
GI
S)
-
b
ased
p
r
e
d
ictio
n
m
a
p
s
to
f
ac
ilit
ate
d
ec
is
io
n
-
m
a
k
in
g
.
C
r
o
p
f
o
r
ec
asti
n
g
in
Ma
th
u
r
an
th
a
g
am
,
C
h
en
g
al
p
attu
,
T
am
il
Nad
u
,
I
n
d
ia
is
cr
u
cial
f
o
r
f
o
o
d
s
ec
u
r
it
y
,
ag
r
ic
u
ltu
r
e,
an
d
f
ar
m
er
liv
elih
o
o
d
s
.
W
ea
th
er
,
r
ain
f
al
l,
an
d
s
o
il
v
ar
iab
les,
in
clu
d
in
g
p
H,
o
r
g
a
n
ic
co
n
ten
t
,
a
n
d
n
u
tr
ie
n
t
lev
els,
co
m
p
licate
cr
o
p
p
r
e
d
ictio
n
.
An
I
o
T
-
b
ased
clim
ate
-
a
d
ap
tiv
e
cr
o
p
r
ec
o
m
m
en
d
atio
n
m
eth
o
d
th
at
u
s
es
d
ee
p
en
s
em
b
le
le
ar
n
in
g
an
d
d
ata
d
etec
ted
b
y
I
o
T
s
en
s
o
r
s
to
ac
cu
r
ately
p
r
o
p
o
s
e
th
e
b
e
s
t
cr
o
p
s
to
g
r
o
w
in
s
p
ec
if
ic
l
o
ca
tio
n
s
at
ce
r
tain
tim
es
[
1
]
.
T
h
is
r
esear
ch
p
r
esen
ts
a
n
eu
r
al
n
etwo
r
k
m
ath
em
atica
l
o
p
tim
is
atio
n
h
y
b
r
id
m
o
d
el
f
o
r
en
v
ir
o
n
m
en
tally
f
r
ie
n
d
ly
f
o
o
d
s
u
p
p
ly
c
h
ain
s
[
2
]
.
I
t
d
ea
ls
with
is
s
u
es
in
clu
d
in
g
m
an
u
f
ac
tu
r
in
g
e
x
p
en
s
es,
wate
r
s
h
o
r
tag
es,
p
o
llu
tio
n
,
a
n
d
in
d
u
s
tr
ial
waste.
T
h
is
r
esea
r
ch
u
s
ed
th
e
Fo
o
d
an
d
Ag
r
icu
ltu
r
e
Or
g
an
izatio
n
(
FAO
)
-
ag
r
o
-
clim
ate
a
p
p
r
o
ac
h
in
co
n
ju
n
ctio
n
with
ML
al
g
o
r
ith
m
s
to
wh
ea
t
y
iel
d
(
W
Y)
p
r
o
d
u
ctio
n
in
So
u
th
west
I
r
an
b
y
an
aly
s
in
g
s
o
il
an
d
en
v
ir
o
n
m
e
n
tal
p
ar
am
eter
s
[
3
]
.
C
o
n
tin
u
o
u
s
W
Y
m
ap
p
in
g
was
ac
co
m
p
lis
h
ed
u
s
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
an
d
r
an
d
o
m
f
o
r
ests
(
R
F)
[
4
]
.
T
h
is
r
esear
ch
co
m
p
a
r
ed
th
e
ef
f
ec
ts
o
f
clim
atic
v
ar
iab
les
o
n
th
e
tr
an
s
m
is
s
io
n
o
f
an
th
r
ax
in
f
ec
tio
n
s
in
I
n
d
ia
with
th
o
s
e
o
f
m
o
r
e
co
n
v
en
tio
n
al
p
a
r
am
eter
s
,
s
u
c
h
as
th
e
d
is
tr
ib
u
tio
n
o
f
a
n
im
a
l
p
o
p
u
latio
n
s
an
d
th
e
s
o
il
-
m
o
is
tu
r
e
m
an
ag
em
e
n
t,
s
o
il
en
r
ich
m
en
t,
a
n
d
s
u
s
tain
a
b
le
ag
r
icu
ltu
r
e
.
T
h
e
s
tu
d
y
p
r
o
p
o
s
es
a
s
m
ar
t
co
m
p
o
s
tin
g
a
p
p
r
o
ac
h
th
at
u
s
es
I
o
T
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
alg
o
r
ith
m
s
[
5
]
.
Pre
d
ictin
g
ag
r
ic
u
ltu
r
al
y
ield
s
,
m
a
p
p
in
g
s
o
il
f
er
til
ity
,
ass
ess
in
g
f
o
o
d
g
r
ain
q
u
ality
,
an
d
p
r
ed
ictin
g
p
est
an
d
d
is
ea
s
e
o
u
tb
r
ea
k
s
ar
e
all
b
ein
g
tr
an
s
f
o
r
m
ed
b
y
AI
a
p
p
licatio
n
s
[
6
]
.
T
h
e
g
o
al
o
f
th
is
r
esear
ch
is
to
cr
ea
te
a
cr
o
p
f
o
r
ec
ast
s
y
s
tem
th
at
u
s
es
wea
th
er
,
s
o
il
p
H,
an
d
n
u
t
r
ien
t
d
ata
co
llected
in
r
ea
l
-
tim
e
a
n
d
i
n
teg
r
ated
in
t
o
th
e
I
o
T
[
7
]
.
T
h
e
tech
n
o
lo
g
y
u
s
es
d
ee
p
lear
n
in
g
(
DL
)
a
n
d
ML
to
d
ete
r
m
in
e
t
h
e
lo
ca
l
en
v
ir
o
n
m
e
n
t
an
d
t
h
en
p
r
o
p
o
s
es
cr
o
p
s
th
at
will
th
r
iv
e
t
h
er
e.
T
h
e
p
r
ess
in
g
p
r
o
b
lem
o
f
cr
o
p
p
r
ed
ictio
n
is
ad
d
r
ess
ed
b
y
in
co
r
p
o
r
atin
g
g
en
etic
alg
o
r
ith
m
s
i
n
to
th
e
p
r
e
d
ictiv
e
m
o
d
el
an
d
m
ak
in
g
u
s
e
o
f
s
tate
-
of
-
th
e
-
ar
t
m
ac
h
in
e
-
lear
n
i
n
g
ap
p
r
o
ac
h
es
[
8
]
.
T
h
e
I
o
T
is
a
to
o
l
f
o
r
o
p
tim
is
in
g
ag
r
icu
ltu
r
al
o
u
t
p
u
t
v
ia
th
e
u
s
e
o
f
a
d
v
an
ce
d
s
en
s
o
r
tec
h
n
o
lo
g
ies,
p
r
o
to
co
l
co
n
n
ec
tio
n
s
,
ML
tec
h
n
iq
u
es,
an
d
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
[
9
]
.
A
n
R
F
m
o
d
el
is
u
s
e
d
to
p
r
o
v
i
d
e
p
r
ec
is
e
f
o
r
ec
asts
b
ased
o
n
d
ata
s
en
t
o
v
er
lo
n
g
-
ra
n
g
e
wid
e
ar
ea
n
e
two
r
k
(
L
o
R
aWAN
)
b
y
s
en
s
o
r
s
th
at
ev
alu
ate
s
o
il
n
u
tr
ien
ts
,
m
o
is
tu
r
e,
an
d
wea
th
er
co
n
d
itio
n
s
.
T
h
r
o
u
g
h
t
h
e
in
teg
r
atio
n
o
f
I
o
T
an
d
GI
S
tech
n
o
lo
g
ies,
th
is
r
esear
ch
s
tu
d
y
p
r
esen
ts
a
n
o
v
el
ap
p
r
o
ac
h
to
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
o
f
s
o
il
h
ea
lth
a
n
d
n
u
tr
ien
t
s
tatu
s
in
ag
r
icu
ltu
r
al
r
eg
io
n
s
[
1
0
]
.
Used
I
o
T
d
ata
a
n
d
ML
alg
o
r
ith
m
s
to
p
r
ed
ict
an
d
ad
v
is
e
f
a
r
m
e
r
s
o
n
c
r
o
p
s
in
r
ea
l
tim
e
[
1
1
]
.
E
n
s
em
b
le
tech
n
iq
u
es
h
av
e
b
ec
o
m
e
p
o
p
u
lar
f
o
r
cr
o
p
p
r
e
d
ictio
n
,
m
ix
i
n
g
n
u
m
er
o
u
s
m
o
d
els.
B
ag
g
in
g
an
d
b
o
o
s
tin
g
r
e
d
u
ce
o
v
e
r
f
itti
n
g
an
d
im
p
r
o
v
e
cr
o
p
p
r
ed
i
ctio
n
m
o
d
el
g
en
er
aliza
tio
n
[
1
2
]
.
T
h
is
r
esear
ch
ev
alu
ates
th
e
ef
f
icac
y
o
f
s
e
v
er
al
ML
m
o
d
els
f
o
r
s
o
il
c
lass
if
icatio
n
,
in
clu
d
in
g
d
ec
is
i
o
n
tr
ee
s
,
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
k
-
NN
)
,
ANN,
an
d
SVM
[
1
3
]
.
Far
m
er
s
u
s
e
s
o
il a
n
d
en
v
ir
o
n
m
e
n
tal
v
ar
iab
les to
f
o
r
ec
ast th
eir
cr
o
p
s
.
B
y
in
clu
d
in
g
p
er
tin
e
n
t
in
f
o
r
m
atio
n
s
u
ch
as
s
o
il
co
m
p
o
s
itio
n
,
tem
p
er
atu
r
e,
an
d
h
u
m
id
ity
,
ML
m
o
d
els
u
s
in
g
f
ilter
,
wr
ap
p
er
,
an
d
em
b
ed
d
in
g
ap
p
r
o
ac
h
es
d
ec
r
ea
s
e
r
ed
u
n
d
an
cy
an
d
tem
p
o
r
al
co
m
p
lex
ity
[
1
4
]
.
An
e
f
f
icien
t
s
eq
u
en
tial
p
atter
n
d
is
co
v
er
y
ap
p
r
o
ac
h
ev
alu
ates
th
e
Pre
f
ix
Sp
an
alg
o
r
ith
m
th
at
r
ec
u
r
s
iv
e
ly
m
ak
es
f
r
e
q
u
en
t
p
atter
n
s
f
r
o
m
p
r
ef
ix
es,
th
u
s
m
in
im
izin
g
th
e
s
ea
r
ch
s
p
ac
e
an
d
im
p
r
o
v
in
g
ef
f
icien
cy
[
1
5
]
.
I
m
p
r
o
v
ed
f
o
o
d
s
af
ety
,
ec
o
n
o
m
i
c
s
tead
in
ess
,
an
d
r
eso
u
r
ce
ef
f
icien
cy
ar
e
al
l
o
u
tco
m
es
o
f
th
is
s
tu
d
y
'
s
u
s
e
o
f
ML
to
f
o
r
ec
ast
ag
r
icu
ltu
r
al
p
r
o
d
u
ctio
n
[
1
6
]
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
e
d
ic
ts
th
e
n
ee
d
f
o
r
ex
p
en
s
iv
e
an
d
tim
e
-
co
n
s
u
m
in
g
tr
ad
itio
n
al
s
o
il
test
in
g
b
y
p
r
e
d
ictin
g
cr
o
p
c
o
m
p
atib
ilit
y
f
o
r
s
o
il
b
ased
o
n
p
H,
m
o
is
tu
r
e
,
tem
p
er
atu
r
e,
a
n
d
h
u
m
id
ity
m
ea
s
u
r
em
e
n
ts
[
1
7
]
.
Utilis
in
g
d
ec
is
io
n
tr
ee
s
,
RF
,
n
aiv
e
B
ay
es,
k
-
NN,
an
d
SV
M
p
r
o
p
o
s
es
an
ML
s
tr
ateg
y
f
o
r
c
r
o
p
t
y
p
e
p
r
ed
icti
o
n
u
tili
s
in
g
s
o
il a
n
d
e
n
v
ir
o
n
m
en
tal
v
ar
iab
les
[
1
8
]
.
B
y
u
s
in
g
en
v
ir
o
n
m
en
tal
p
ar
a
m
eter
s
to
f
o
r
ec
ast
cr
o
p
r
esu
lt
s
,
ML
is
tr
an
s
f
o
r
m
in
g
a
g
r
icu
ltu
r
e.
Fo
r
b
etter
y
ield
p
r
ed
ictio
n
a
n
d
b
etter
f
ar
m
in
g
m
eth
o
d
s
,
th
is
r
esear
ch
an
aly
s
es
m
eteo
r
o
lo
g
i
ca
l
co
n
d
itio
n
s
,
s
o
il
q
u
alities
,
an
d
cr
o
p
t
r
aits
to
cr
ea
te
ML
m
o
d
els
[
1
9
]
.
T
h
r
o
u
g
h
th
e
in
te
g
r
atio
n
o
f
d
ata
in
p
u
t
an
d
I
o
T
s
en
s
o
r
s
,
a
web
-
b
ased
ap
p
licatio
n
p
r
ed
ict
s
an
d
r
ec
o
m
m
e
n
d
s
ag
r
icu
ltu
r
al
y
ield
s
u
s
in
g
ML
alg
o
r
ith
m
s
[
2
0
]
.
T
h
e
s
y
s
tem
f
in
d
s
th
e
b
est
m
eth
o
d
s
f
o
r
p
r
ed
ictio
n
wo
r
k
s
b
y
an
aly
s
in
g
m
o
d
els
s
u
ch
as
S
VM
,
RF
,
an
d
g
r
ad
ie
n
t
b
o
o
s
tin
g
.
Aim
in
g
to
r
e
v
o
lu
tio
n
is
e
cr
o
p
m
an
ag
em
e
n
t
u
s
in
g
an
ML
m
eth
o
d
,
th
is
p
r
o
ject
is
m
o
tiv
ated
b
y
th
e
p
r
ess
in
g
n
ee
d
f
o
r
m
o
d
er
n
ag
r
icu
ltu
r
al
tech
n
iq
u
es
[
2
1
]
.
C
r
o
p
r
ec
o
m
m
en
d
atio
n
m
et
h
o
d
s
th
at
tak
e
s
o
il
an
d
en
v
ir
o
n
m
en
tal
d
ata
in
t
o
ac
c
o
u
n
t
ar
e
d
e
v
elo
p
e
d
u
s
in
g
DL
m
o
d
els
s
u
ch
as
DE
NSE,
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
,
an
d
L
STM
[
2
2
]
.
Sm
ar
t
ag
r
icu
ltu
r
e
y
ield
a
n
d
f
er
tili
ze
r
o
p
tim
izatio
n
s
y
s
tem
(
SAYFOS
)
,
a
n
ew
m
eth
o
d
f
o
r
o
p
tim
i
z
in
g
a
g
r
icu
ltu
r
al
y
ield
s
an
d
f
er
tili
s
er
s
.
W
ith
SAYFOS,
u
s
er
s
ca
n
m
o
n
ito
r
th
e
cr
o
p
s
a
n
d
s
o
il
co
n
d
itio
n
s
in
r
ea
l
tim
e
d
u
e
t
o
its
s
u
p
er
io
r
d
ata
an
al
y
tics
,
I
o
T
tech
n
o
lo
g
y
,
a
n
d
ML
al
g
o
r
ith
m
s
[
2
3
]
.
Usi
n
g
ML
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
r
o
p
p
r
ed
ictio
n
in
Ta
mil Na
d
u
a
cc
o
r
d
in
g
to
en
viro
n
men
ta
l
a
n
d
s
o
il fa
cto
r
s
…
(
S
u
n
d
a
r
a
j Ka
n
n
a
n
S
u
s
ee
)
407
m
eth
o
d
s
f
o
r
in
p
u
t
c
h
ar
a
cter
is
tics
,
th
e
r
esear
ch
d
em
o
n
s
tr
ates
two
s
tr
o
n
g
ML
ar
ch
itectu
r
es
f
o
r
r
eg
r
ess
io
n
an
d
class
if
icatio
n
f
o
r
th
e
cr
o
p
r
ec
o
m
m
en
d
atio
n
d
ataset
[
2
4
]
.
R
ed
u
ce
d
ag
r
icu
ltu
r
al
y
ield
lo
s
s
in
I
n
d
ia
is
ac
h
iev
e
d
u
s
in
g
alg
o
r
ith
m
s
s
u
ch
as
lin
ea
r
r
eg
r
ess
io
n
,
lo
g
is
tic
r
eg
r
ess
io
n
,
an
d
SVM
to
d
eter
m
in
e
th
e
o
p
tim
al
cr
o
p
f
o
r
a
g
iv
en
s
o
il
a
n
d
e
n
v
ir
o
n
m
en
t
[
2
5
]
.
Su
s
tain
ab
le
ag
r
icu
ltu
r
e
b
en
ef
its
f
r
o
m
th
is
m
o
d
el'
s
ab
ilit
y
to
m
a
x
im
i
z
e
ef
f
icien
cy
wh
ile
r
ed
u
cin
g
n
eg
ativ
e
ef
f
ec
ts
o
n
th
e
en
v
ir
o
n
m
en
t.
B
y
r
o
tatin
g
cr
o
p
s
,
f
ar
m
e
r
s
m
ay
im
p
r
o
v
e
s
o
il
f
er
tili
ty
,
s
tr
u
ctu
r
e,
an
d
b
io
d
iv
e
r
s
ity
[
2
6
]
.
i)
Pro
b
lem
d
o
m
ain
:
t
h
e
c
o
m
p
lex
a
n
d
e
v
er
-
c
h
an
g
in
g
s
o
il
an
d
en
v
i
r
o
n
m
e
n
tal
co
n
d
itio
n
s
o
f
Ma
th
u
r
an
th
a
g
am
,
T
am
il
Nad
u
,
I
n
d
ia
p
o
s
e
s
u
b
s
tan
tial
ch
allen
g
es
to
th
e
ag
r
icu
ltu
r
e
s
ec
to
r
.
I
m
p
r
o
v
i
n
g
ag
r
icu
ltu
r
al
m
eth
o
d
s
,
in
cr
ea
s
in
g
cr
o
p
y
ield
s
,
an
d
p
r
o
v
id
in
g
s
u
s
tain
ab
le
f
o
o
d
p
r
o
d
u
ctio
n
all
d
ep
en
d
o
n
ac
cu
r
ate
cr
o
p
p
r
e
d
ictio
n
,
as
s
h
o
wn
i
n
Fig
u
r
e
1
.
T
h
is
r
esear
ch
p
r
esen
ts
a
h
y
b
r
i
d
C
o
n
v
L
STM
-
B
iLST
M
-
SVM
m
o
d
el
f
o
r
c
r
o
p
p
r
e
d
ictio
n
in
Ma
th
u
r
an
th
ag
a
m
,
T
am
i
l
Nad
u
,
I
n
d
ia
u
s
in
g
s
o
il
an
d
en
v
ir
o
n
m
en
tal
d
ata.
Sig
n
if
ican
t
c
o
n
tr
ib
u
tio
n
s
in
clu
d
e
a
r
eg
io
n
-
s
p
ec
if
ic
d
atase
t,
f
ea
tu
r
e
o
p
tim
is
atio
n
,
s
p
atio
-
tem
p
o
r
al
m
o
d
ellin
g
,
en
h
an
ce
d
p
er
f
o
r
m
an
ce
r
elativ
e
to
b
aselin
es,
an
d
d
ec
is
io
n
-
s
u
p
p
o
r
t
v
is
u
alis
atio
n
s
f
o
r
ag
r
icu
ltu
r
alis
ts
,
in
s
u
r
an
ce
s
tr
ateg
izin
g
,
an
d
p
o
licy
d
ev
el
o
p
m
e
n
t.
ii)
Desig
n
:
Ma
th
u
r
an
th
ag
am
,
T
a
m
il
Nad
u
,
I
n
d
ia
s
o
il
an
d
e
n
v
i
r
o
n
m
en
tal
d
ata
ar
e
u
s
ed
in
th
e
ar
ch
itectu
r
al
d
esig
n
to
im
p
r
o
v
e
cr
o
p
f
o
r
e
ca
s
ts
.
W
ea
th
er
p
ar
am
eter
s
,
in
clu
d
in
g
tem
p
er
atu
r
e,
h
u
m
id
ity
,
p
H,
an
d
r
ain
f
all
,
ar
e
co
llected
in
itially
.
Sp
lit
th
e
d
ata
in
to
tr
ain
in
g
a
n
d
test
d
atasets
af
ter
m
i
n
-
m
a
x
s
ca
lin
g
an
d
m
is
s
in
g
v
alu
es.
J
ay
a
o
p
tim
iz
atio
n
m
in
im
i
z
es
d
ata
d
im
en
s
i
o
n
ality
an
d
p
ic
k
s
k
ey
f
ea
tu
r
e
s
.
I
t
im
p
r
o
v
es
m
o
d
el
p
er
f
o
r
m
an
ce
.
SVM
cla
s
s
if
ier
s
an
d
p
o
we
r
f
u
l
DL
alg
o
r
i
th
m
s
,
s
u
ch
as
Bi
L
STM
an
d
C
o
n
v
L
ST
M
n
etwo
r
k
s
,
ar
e
u
s
ed
to
cr
ea
te
Fi
g
u
r
e
2
m
o
d
els.
Fig
u
r
e
1
.
R
eg
io
n
o
f
Ma
d
u
r
a
n
th
ag
am
m
a
p
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
d
iag
r
a
m
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
s
tu
d
y
'
s
n
o
v
elty
is
in
its
h
y
b
r
id
a
r
ch
itectu
r
e,
wh
ic
h
u
n
iq
u
ely
co
m
b
in
es
lin
ea
r
SVM,
B
iLST
M,
an
d
C
o
n
v
L
STM
to
e
f
f
ec
tiv
e
ly
h
ar
n
ess
tem
p
o
r
al,
s
p
atial,
an
d
class
if
icatio
n
ca
p
ab
ilit
ies.
Fu
r
th
er
m
o
r
e,
it
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
405
-
4
1
5
408
em
p
lo
y
s
J
ay
a
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
f
o
r
o
p
tim
izatio
n
an
d
in
teg
r
ates
b
o
th
s
o
il
an
d
clim
atic
v
ar
iab
les
f
r
o
m
lo
ca
lized
Ma
th
u
r
an
th
ag
a
m
d
a
ta,
p
r
o
v
id
in
g
th
e
m
o
d
el
m
eth
o
d
o
lo
g
ically
cr
ea
tiv
e
a
n
d
co
n
tex
tu
ally
p
er
tin
en
t
f
o
r
cr
o
p
p
r
ed
ictio
n
i
n
T
am
i
l
Nad
u
.
T
h
e
r
esear
ch
u
s
es
B
iLST
M
an
d
C
o
n
v
L
STM
f
o
r
tem
p
o
r
al
cr
o
p
f
o
r
ec
asti
n
g
,
s
in
ce
L
STM
s
p
r
o
f
icien
tly
ca
p
tu
r
e
l
o
n
g
-
ter
m
r
elatio
n
s
h
ip
s
an
d
s
ea
s
o
n
al
v
a
r
iatio
n
s
in
s
o
il
an
d
clim
atic
d
ata.
T
h
eir
in
teg
r
atio
n
with
C
o
n
v
L
STM
m
o
d
els ca
p
tu
r
es sp
atial
co
r
r
elatio
n
s
,
y
ield
in
g
g
r
ea
t a
cc
u
r
ac
y
an
d
in
ter
p
r
etab
ilit
y
,
wh
ile
alter
n
ativ
es
s
u
ch
as
tr
an
s
f
o
r
m
er
o
r
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U
)
,
d
esp
ite
th
eir
p
o
ten
tial,
in
cr
ea
s
e
co
m
p
lex
ity
.
W
ea
th
er
an
d
s
o
il
ch
a
r
ac
ter
is
tics
,
in
clu
d
in
g
h
u
m
id
ity
,
tem
p
er
atu
r
e,
p
H,
an
d
p
r
ec
ip
itatio
n
in
r
ec
o
r
d
o
f
Ma
t
h
u
r
an
th
a
g
am
'
s
d
is
tin
ct.
R
eg
u
lar
izin
g
d
ata
v
ia
m
in
-
m
ax
s
ca
li
n
g
im
p
r
o
v
es
m
o
d
el
p
er
f
o
r
m
an
ce
an
d
co
n
s
is
ten
cy
.
T
h
e
m
in
-
m
ax
s
ca
ler
s
ets
a
p
er
-
f
ea
tu
r
e
m
in
im
u
m
an
d
m
ax
i
m
u
m
v
alu
e
d
u
r
in
g
f
itti
n
g
.
Du
r
in
g
tr
an
s
f
o
r
m
atio
n
,
th
e
(
1
)
co
n
v
er
ts
all
f
ea
tu
r
e
v
al
u
es to
0
-
1
.
=
−
−
(
1
)
W
h
er
e
X
r
ep
r
esen
ts
th
e
in
itial
f
ea
tu
r
e.
an
d
ar
e
th
e
f
ea
tu
r
e
m
in
im
u
m
an
d
m
ax
im
u
m
v
alu
es.
i)
Pro
p
er
n
ess
:
t
h
e
s
ca
le
s
ets
u
p
p
er
an
d
l
o
wer
b
o
u
n
d
a
r
ies
f
o
r
e
v
er
y
tr
ain
i
n
g
d
ataset
f
ea
tu
r
e.
Nex
t,
tr
an
s
late
f
ea
tu
r
e
v
alu
es to
a
0
-
1
s
ca
le.
Scalin
g
is
n
ee
d
ed
f
o
r
all
f
ea
t
u
r
e
s
to
af
f
ec
t m
o
d
el
lea
r
n
in
g
eq
u
ally
.
ii)
No
r
m
aliza
tio
n
:
co
n
tin
u
o
u
s
v
ar
iab
les,
in
clu
d
in
g
tem
p
er
atu
r
e
,
r
ain
f
all,
h
u
m
id
ity
,
an
d
s
o
il
n
u
tr
ien
t
v
alu
es
(
NPK
an
d
p
H)
,
a
r
e
s
tan
d
ar
d
i
z
ed
b
y
m
in
-
m
ax
n
o
r
m
ali
z
atio
n
to
en
s
u
r
e
u
n
if
o
r
m
ity
ac
r
o
s
s
all
f
ea
tu
r
es.
iii)
C
ateg
o
r
ical
en
co
d
in
g
:
c
r
o
p
c
ateg
o
r
ies
ar
e
r
ep
r
esen
ted
b
y
o
n
e
-
h
o
t
en
co
d
i
n
g
,
f
ac
ilit
atin
g
th
e
m
o
d
el'
s
ef
f
icien
t p
r
o
ce
s
s
in
g
o
f
ca
teg
o
r
ical
d
ata.
iv
)
Miss
in
g
d
ata
m
an
ag
em
en
t:
in
co
m
p
lete
o
r
m
is
s
in
g
v
alu
e
s
ar
e
ad
d
r
ess
ed
b
y
m
ea
n
i
m
p
u
tatio
n
f
o
r
n
u
m
er
ic
al
attr
ib
u
tes
an
d
m
o
d
e
im
p
u
tatio
n
f
o
r
ca
teg
o
r
ic
al
v
ar
iab
les,
th
er
e
f
o
r
e
p
r
ese
r
v
in
g
d
ataset
in
teg
r
ity
.
T
h
e
co
d
e
im
p
o
r
ts
t
h
e
d
ata
in
t
o
a
N
u
m
Py
ar
r
ay
,
n
o
r
m
alize
s
th
e
f
ea
tu
r
es
with
th
e
m
in
-
m
ax
s
ca
le
r
,
an
d
th
en
o
u
tp
u
ts
th
e
s
ca
led
d
ata
to
test
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
ar
c
h
itectu
r
e
in
teg
r
ate
s
lin
ea
r
SVM,
B
iLST
M,
an
d
C
o
n
v
L
STM
n
et
wo
r
k
s
to
ex
p
l
o
it th
eir
s
y
n
er
g
is
tic
ad
v
an
tag
es f
o
r
cr
o
p
p
r
e
d
ictio
n
.
v)
C
o
n
v
L
STM
:
ca
p
tu
r
es
s
p
atial
r
elatio
n
s
h
ip
s
with
in
th
e
d
ataset,
in
clu
d
in
g
d
i
f
f
er
en
ce
s
in
s
o
il
an
d
en
v
ir
o
n
m
en
tal
ch
ar
ac
te
r
is
tics
o
v
er
Ma
th
u
r
an
th
a
g
am
.
v
i)
L
STM
:
an
aly
s
i
s
tem
p
o
r
al
p
a
tter
n
s
b
y
p
r
o
ce
s
s
in
g
s
eq
u
en
c
es
in
b
o
th
d
ir
ec
tio
n
s
,
th
er
ef
o
r
e
ca
p
tu
r
in
g
in
ter
d
ep
en
d
en
ce
ac
r
o
s
s
s
ev
er
al
cr
o
p
p
in
g
s
ea
s
o
n
s
.
v
ii)
L
in
ea
r
SVM:
f
u
n
ctio
n
s
as
a
co
n
clu
s
iv
e
class
if
ier
,
d
eliv
er
in
g
ef
f
ec
tiv
e
d
ec
is
io
n
-
m
a
k
in
g
f
o
r
cr
o
p
ap
p
r
o
p
r
iaten
ess
b
y
d
is
tin
g
u
is
h
in
g
cr
o
p
class
es a
cc
o
r
d
in
g
to
t
h
e
ac
q
u
ir
e
d
f
ea
tu
r
e
r
ep
r
esen
ta
tio
n
s
.
v
iii)
Fu
s
io
n
s
tr
ateg
y
:
th
e
o
u
tp
u
ts
f
r
o
m
B
iLST
M
an
d
C
o
n
v
L
ST
M
ar
e
co
n
ca
te
n
ated
an
d
in
p
u
t
in
to
th
e
lin
ea
r
SVM
u
s
in
g
a
s
tack
ed
en
s
em
b
le
m
eth
o
d
o
lo
g
y
.
T
h
is
en
ab
les
th
e
m
o
d
el
to
in
clu
d
e
s
p
atial,
tem
p
o
r
al,
an
d
class
if
icatio
n
f
u
n
ctio
n
alities
,
im
p
r
o
v
i
n
g
f
o
r
ec
ast p
r
ec
is
io
n
.
2
.
1
.
L
inea
r
s
up
po
rt
v
ec
t
o
r
m
a
chine
cla
s
s
if
ier
T
h
e
SVM
is
a
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
p
r
im
ar
ily
u
s
ed
f
o
r
c
lass
if
icatio
n
task
s
.
I
t
wo
r
k
s
b
y
f
in
d
in
g
a
h
y
p
er
p
lan
e
th
at
b
est
d
iv
id
es
t
h
e
d
ata
in
to
class
e
s
.
L
in
ea
r
S
VM
is
p
ar
ticu
lar
ly
u
s
ef
u
l
wh
en
th
e
d
ata
is
lin
ea
r
ly
s
ep
ar
ab
le,
m
ea
n
in
g
th
at
a
s
tr
ai
g
h
t
lin
e
(
o
r
h
y
p
e
r
p
lan
e
in
h
ig
h
er
d
im
e
n
s
io
n
s
)
ca
n
s
ep
ar
ate
th
e
d
if
f
e
r
en
t
class
es.
I
n
th
e
co
n
tex
t
o
f
cr
o
p
s
u
itab
ilit
y
,
th
e
l
in
ea
r
SVM
c
lass
if
ie
r
wo
u
ld
b
e
u
s
ed
to
p
r
ed
ict
wh
ich
ty
p
e
is
m
o
s
t
s
u
itab
le
b
ased
o
n
en
v
ir
o
n
m
en
tal
an
d
s
o
il
f
ea
tu
r
es
s
u
ch
as
h
u
m
id
ity
,
r
ain
f
all,
tem
p
er
atu
r
e,
an
d
p
H.
SVMs
ar
e
r
o
b
u
s
t
a
g
ain
s
t
o
v
er
f
itti
n
g
,
esp
ec
ially
in
h
ig
h
-
d
im
en
s
io
n
al
s
p
ac
es,
an
d
th
ey
ca
n
ef
f
icien
tly
p
er
f
o
r
m
n
o
n
-
lin
ea
r
class
if
icatio
n
u
s
in
g
th
e
k
er
n
el
tr
ick
.
I
n
th
is
ca
s
e,
t
h
e
lin
ea
r
SVM
h
elp
s
d
if
f
er
e
n
tiate
b
et
wee
n
cr
o
p
v
ar
ieties
ef
f
ec
tiv
ely
,
p
r
o
v
id
i
n
g
p
o
wer
f
u
l d
ec
is
io
n
-
m
ak
in
g
.
2.
2.
B
idi
re
ct
io
na
l
lo
ng
s
ho
rt
-
t
er
m
m
emo
ry
A
B
iLST
M
n
etwo
r
k
is
a
ty
p
e
o
f
R
NN
d
esig
n
ed
to
p
r
o
ce
s
s
s
eq
u
en
tial
d
ata.
B
id
ir
ec
tio
n
ali
ty
:
u
n
lik
e
tr
ad
itio
n
al
L
STM
s
th
at
p
r
o
ce
s
s
d
ata
s
eq
u
en
tially
f
r
o
m
th
e
p
ast
(
f
o
r
war
d
)
,
B
iLST
Ms
p
r
o
ce
s
s
d
ata
in
b
o
th
d
ir
ec
tio
n
s
(
p
ast
-
to
-
f
u
t
u
r
e
an
d
f
u
tu
r
e
-
to
-
p
ast).
T
h
is
is
esp
ec
ially
b
en
ef
icial
wh
en
p
r
ed
icti
n
g
cr
o
p
s
u
itab
ilit
y
b
ec
au
s
e
it
allo
ws
th
e
m
o
d
el
to
ca
p
tu
r
e
b
o
th
p
ast
an
d
f
u
tu
r
e
tem
p
o
r
al
d
e
p
en
d
e
n
cies.
Fo
r
ex
am
p
le,
wea
th
er
co
n
d
itio
n
s
s
u
ch
as
r
ain
f
all
o
r
t
em
p
er
atu
r
e
at
an
y
g
iv
en
tim
e
m
ig
h
t
in
f
lu
e
n
ce
cr
o
p
g
r
o
wth
n
o
t
o
n
l
y
in
t
h
e
p
ast
b
u
t
also
in
th
e
f
u
tu
r
e.
L
STM
s
ar
e
a
ty
p
e
o
f
R
NN
th
at
ar
e
g
o
o
d
at
ca
p
tu
r
i
n
g
lo
n
g
-
r
a
n
g
e
d
ep
en
d
en
cies
in
s
eq
u
en
ce
s
,
m
ak
in
g
th
em
p
ar
ti
cu
lar
ly
s
u
ited
f
o
r
tim
e
-
s
er
ies
f
o
r
e
ca
s
tin
g
,
s
u
c
h
as
p
r
ed
ictin
g
th
e
s
u
itab
ilit
y
o
f
cr
o
p
s
o
v
e
r
tim
e
b
ased
o
n
wea
t
h
er
an
d
s
o
il c
o
n
d
itio
n
s
.
2.
3.
C
o
nv
o
lutio
na
l
lo
ng
s
ho
r
t
-
t
er
m m
e
m
o
ry
T
h
e
C
o
n
v
L
STM
is
an
o
th
er
v
a
r
ian
t
o
f
th
e
L
STM
th
at
in
co
r
p
o
r
ates
co
n
v
o
lu
ti
o
n
al
o
p
e
r
atio
n
s
in
to
th
e
L
STM
f
r
am
ewo
r
k
,
m
ak
i
n
g
it
s
u
itab
le
f
o
r
d
ata
with
s
p
atial
-
tem
p
o
r
al
d
ep
en
d
en
cies.
Sp
atial
-
t
em
p
o
r
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
r
o
p
p
r
ed
ictio
n
in
Ta
mil Na
d
u
a
cc
o
r
d
in
g
to
en
viro
n
men
ta
l
a
n
d
s
o
il fa
cto
r
s
…
(
S
u
n
d
a
r
a
j Ka
n
n
a
n
S
u
s
ee
)
409
d
ep
en
d
e
n
cies:
C
o
n
v
L
STM
is
p
ar
ticu
lar
ly
u
s
ef
u
l
wh
e
n
th
e
d
ata
h
as
b
o
th
tem
p
o
r
al
an
d
s
p
a
tial
co
m
p
o
n
en
ts
.
I
n
th
e
co
n
tex
t
o
f
cr
o
p
f
o
r
ec
asti
n
g
,
s
p
atial
d
ata
ca
n
i
n
clu
d
e
g
eo
g
r
a
p
h
ic
lo
ca
tio
n
s
,
s
o
il
q
u
ality
v
ar
iatio
n
s
,
o
r
d
if
f
er
en
t
e
n
v
ir
o
n
m
en
tal
c
o
n
d
i
tio
n
s
ac
r
o
s
s
r
eg
io
n
s
.
B
y
u
s
in
g
co
n
v
o
lu
tio
n
al
o
p
er
atio
n
s
in
co
n
ju
n
ctio
n
with
L
STM
,
th
e
C
o
n
v
L
STM
ca
p
tu
r
es
s
p
atial
r
elatio
n
s
h
ip
s
b
etwe
en
d
if
f
er
en
t
r
e
g
io
n
s
o
f
th
e
d
at
aset,
en
h
an
cin
g
th
e
m
o
d
el'
s
ab
ilit
y
to
lear
n
b
o
th
th
e
tem
p
o
r
al
an
d
s
p
atial
f
ea
tu
r
es
o
f
th
e
d
ata.
T
h
e
C
o
n
v
L
STM
will
ca
p
tu
r
e
d
ep
en
d
e
n
cies n
o
t o
n
ly
ac
r
o
s
s
tim
e
b
u
t a
ls
o
ac
r
o
s
s
s
p
atial
d
im
en
s
io
n
s
.
2.
4
.
M
in
-
m
a
x
s
ca
lin
g
B
ef
o
r
e
ap
p
ly
in
g
th
e
ML
m
o
d
els,
th
e
d
ataset
is
n
o
r
m
alize
d
u
s
in
g
m
in
-
m
a
x
s
ca
lin
g
,
a
f
ea
t
u
r
e
s
ca
lin
g
tech
n
iq
u
e
th
at
r
escales
all
f
ea
tu
r
e
v
alu
es
to
a
co
m
m
o
n
r
an
g
e
.
T
h
e
m
ain
r
ea
s
o
n
f
o
r
ap
p
ly
i
n
g
m
in
-
m
a
x
s
ca
lin
g
is
to
m
ak
e
s
u
r
e
th
at
all
f
ea
tu
r
es
h
av
e
eq
u
al
weig
h
t
i
n
th
e
le
ar
n
in
g
p
r
o
ce
s
s
.
T
h
is
is
p
ar
ticu
lar
ly
im
p
o
r
ta
n
t
f
o
r
m
o
d
els
s
u
ch
as
SVMs,
n
eu
r
al
n
etwo
r
k
s
,
an
d
o
th
e
r
s
th
at
ar
e
s
en
s
itiv
e
to
th
e
s
ca
le
o
f
in
p
u
t
f
ea
tu
r
es.
W
ith
o
u
t
s
ca
lin
g
,
f
ea
tu
r
es with
lar
g
er
v
alu
es c
o
u
ld
d
o
m
in
ate
th
e
lear
n
in
g
p
r
o
ce
s
s
,
m
ak
in
g
th
e
m
o
d
el
in
ef
f
icien
t.
2.
5
.
J
a
y
a
o
ptim
iz
a
t
io
n
t
ec
hn
iqu
e
f
o
r
f
ea
t
ure
s
elec
t
io
n
J
ay
a
o
p
tim
izatio
n
is
an
o
p
tim
izatio
n
alg
o
r
ith
m
th
at
wo
r
k
s
o
n
f
i
n
d
in
g
th
e
b
est
p
o
s
s
ib
le
s
o
lu
tio
n
b
y
iter
ativ
ely
im
p
r
o
v
in
g
th
e
ca
n
d
id
ate
s
o
lu
tio
n
s
.
Featu
r
e
s
elec
tio
n
:
in
y
o
u
r
m
et
h
o
d
o
lo
g
y
,
J
ay
a
o
p
tim
izatio
n
is
u
s
ed
to
s
elec
t
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
f
r
o
m
th
e
d
ataset.
I
n
cr
o
p
s
u
itab
ilit
y
f
o
r
ec
asti
n
g
,
f
ea
tu
r
es
s
u
ch
as
h
u
m
id
ity
,
r
ain
f
all,
an
d
p
H
ar
e
u
s
ed
,
b
u
t
n
o
t
all
f
ea
tu
r
es
m
ay
b
e
e
q
u
ally
im
p
o
r
tan
t.
J
ay
a
o
p
tim
izatio
n
h
elp
s
in
au
to
m
atica
lly
id
en
tify
i
n
g
a
n
d
s
elec
tin
g
th
e
b
est
f
ea
tu
r
es
th
at
co
n
tr
ib
u
te
m
o
s
t
to
p
r
ed
ic
tiv
e
ac
cu
r
ac
y
.
J
ay
a
o
p
tim
izatio
n
w
o
r
k
s
b
y
iter
atin
g
th
r
o
u
g
h
ca
n
d
i
d
ate
s
o
lu
tio
n
s
an
d
ad
ju
s
tin
g
th
em
b
ased
o
n
th
e
b
est
-
f
o
u
n
d
s
o
lu
tio
n
an
d
t
h
e
wo
r
s
t
-
f
o
u
n
d
s
o
lu
tio
n
.
2.
6
.
P
er
f
o
r
m
a
nce
m
e
t
rics
Usi
n
g
m
etr
ics f
o
r
b
o
th
class
if
i
ca
tio
n
an
d
r
eg
r
ess
io
n
,
ev
alu
at
e
th
e
h
y
b
r
id
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
W
h
en
f
alse
p
o
s
itiv
es
ar
e
ex
p
en
s
iv
e,
ac
cu
r
ac
y
is
m
o
r
e
im
p
o
r
tan
t
th
an
p
r
ec
is
io
n
i
n
d
eter
m
i
n
in
g
to
tal
co
r
r
ec
t
n
ess
b
ec
au
s
e
p
r
ec
is
io
n
ass
ess
e
s
th
e
ac
cu
r
ac
y
o
f
p
o
s
itiv
e
p
r
ed
ict
io
n
s
.
An
all
-
en
c
o
m
p
ass
in
g
p
e
r
f
o
r
m
a
n
ce
m
ea
s
u
r
e
,
th
e
F1
-
s
co
r
e
s
tr
ik
es a
g
o
o
d
b
al
an
ce
b
etwe
en
r
ec
all
a
n
d
ac
cu
r
ac
y
b
y
i
d
en
tify
in
g
r
ea
l p
o
s
itiv
e
ev
en
ts
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
'
s
d
ataset
was
co
llected
f
r
o
m
Ma
th
u
r
an
th
a
g
am
,
T
am
il
Nad
u
,
I
n
d
ia
an
d
it
was
d
esig
n
ed
to
ass
is
t
r
eliab
le
cr
o
p
p
r
e
d
ictio
n
u
s
in
g
th
e
h
y
b
r
id
ML
ar
ch
itectu
r
e.
T
h
e
d
ataset
in
clu
d
e
d
s
o
il,
cr
o
p
s
,
an
d
en
v
ir
o
n
m
en
tal
d
ata.
Pro
v
id
in
g
g
e
o
g
r
ap
h
ical
r
eso
lu
tio
n
d
o
wn
to
t
h
e
b
lo
ck
lev
el,
t
h
e
d
ata
s
et
ca
p
tu
r
es
t
h
e
lo
ca
lized
ag
r
o
-
clim
atic
co
n
d
it
io
n
s
in
Ma
th
u
r
an
th
a
g
am
a
n
d
s
p
an
s
n
u
m
er
o
u
s
cr
o
p
p
in
g
s
ea
s
o
n
s
.
R
ice,
m
aize
,
an
d
ch
ick
p
ea
ar
e
s
o
m
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
cr
o
p
s
g
r
o
w
n
in
th
e
ar
ea
,
an
d
th
is
in
f
o
r
m
a
tio
n
co
n
tain
s
th
eir
cu
ltiv
atio
n
p
atter
n
s
an
d
p
r
ac
ti
ce
s
.
So
il
ch
ar
ac
ter
is
tics
s
u
ch
as
p
H,
n
itro
g
en
(
N)
,
p
h
o
s
p
h
o
r
u
s
(
P),
p
o
tass
iu
m
(
K)
,
an
d
s
o
il
te
x
t
u
r
e
a
r
e
ess
en
tial
f
o
r
d
eter
m
in
in
g
cr
o
p
co
m
p
atib
ilit
y
an
d
f
er
tili
ty
.
T
em
p
er
atu
r
e,
p
r
ec
ip
itatio
n
,
an
d
h
u
m
id
ity
ar
e
ex
am
p
les
o
f
en
v
ir
o
n
m
en
tal
f
a
cto
r
s
th
at
m
ir
r
o
r
clim
atic
an
d
s
ea
s
o
n
al
ch
an
g
es
th
at
im
p
ac
t
ag
r
icu
ltu
r
al
y
ield
s
.
Featu
r
e
s
elec
tio
n
u
tili
zin
g
J
ay
a
o
p
tim
izatio
n
an
d
m
i
n
-
m
ax
n
o
r
m
aliza
tio
n
ar
e
two
o
f
t
h
e
d
ata
p
r
ep
ar
atio
n
s
tep
s
u
s
ed
to
k
ee
p
th
e
m
o
s
t
im
p
o
r
ta
n
t
v
ar
iab
les
f
o
r
tr
ain
in
g
th
e
m
o
d
el.
C
o
m
p
lex
s
p
atio
-
tem
p
o
r
al
r
elatio
n
s
h
ip
s
m
ay
b
e
ca
p
tu
r
ed
b
y
th
e
h
y
b
r
id
ar
c
h
itectu
r
e,
wh
ich
co
n
s
is
ts
o
f
C
o
n
v
L
STM
f
o
r
s
p
atial
d
ep
en
d
e
n
cies,
B
iLST
M
f
o
r
tem
p
o
r
al
p
atter
n
s
,
a
n
d
lin
ea
r
S
VM
f
o
r
class
if
icatio
n
.
T
h
e
d
a
taset
in
teg
r
ates
b
o
th
s
o
il
an
d
clim
atic
in
f
o
r
m
atio
n
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
ar
c
h
itectu
r
e
f
o
r
cr
o
p
p
r
ed
ictio
n
in
Ma
th
u
r
an
th
a
g
am
,
T
am
il
Nad
u
,
I
n
d
ia
is
ass
es
s
ed
u
s
in
g
a
th
o
r
o
u
g
h
tech
n
iq
u
e
to
p
r
o
v
id
e
r
o
b
u
s
tn
ess
an
d
d
e
p
en
d
a
b
ilit
y
.
Hy
p
er
p
ar
a
m
eter
tu
n
i
n
g
is
co
n
d
u
cted
f
o
r
th
e
C
o
n
v
L
STM
a
n
d
B
iLST
M
n
etwo
r
k
s
,
o
p
tim
izin
g
th
e
n
u
m
b
e
r
o
f
lay
er
s
,
h
id
d
en
u
n
its
,
d
r
o
p
o
u
t
r
ates,
an
d
lear
n
in
g
r
ates
u
s
in
g
g
r
id
s
ea
r
ch
an
d
B
ay
esian
o
p
ti
m
izati
on
,
wh
ile
th
e
r
eg
u
lar
izatio
n
p
ar
am
eter
o
f
th
e
lin
ea
r
SVM
is
m
o
d
i
f
ied
f
o
r
o
p
tim
u
m
class
if
icatio
n
.
J
ay
a
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
s
ig
n
if
ican
tly
im
p
r
o
v
es
m
o
d
el
ef
f
icien
cy
.
T
h
e
m
o
d
el
is
v
alid
ated
u
s
in
g
m
u
lti
-
s
ea
s
o
n
al
r
ec
o
r
d
s
o
f
r
ice,
m
aize
,
an
d
ch
ick
p
ea
to
m
ea
s
u
r
e
p
er
f
o
r
m
an
ce
s
tab
ilit
y
an
d
en
s
u
r
e
ac
cu
r
ate
f
o
r
ec
a
s
ts
d
esp
ite
clim
atic
f
lu
ctu
atio
n
.
Per
f
o
r
m
a
n
ce
m
ea
s
u
r
es
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
e
u
s
ed
to
q
u
an
tif
y
b
o
t
h
p
r
ed
ictiv
e
ca
p
a
b
ilit
y
an
d
m
is
tak
e
r
ates.
T
h
is
ass
es
s
m
en
t
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates
th
at
th
e
h
y
b
r
id
m
o
d
el
p
r
o
v
id
es
co
n
s
is
ten
t,
h
ig
h
-
ac
cu
r
ac
y
,
a
n
d
co
n
tex
t
-
s
p
ec
if
ic
p
r
e
d
ictio
n
s
o
f
cr
o
p
s
u
itab
ilit
y
,
m
ak
in
g
it
ap
p
r
o
p
r
iate
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
s
u
ch
as
f
ar
m
er
ad
v
is
o
r
ies,
cr
o
p
in
s
u
r
an
ce
p
lan
n
in
g
,
an
d
r
eg
io
n
al
ag
r
ic
u
ltu
r
al
p
o
licy
f
o
r
m
u
latio
n
.
Fig
u
r
e
3
s
h
o
ws
th
e
m
o
n
t
h
ly
tr
e
n
d
s
o
f
tem
p
er
atu
r
e
,
h
u
m
i
d
ity
,
s
o
il
p
H,
an
d
r
ain
f
all
at
Ma
th
u
r
an
th
a
g
am
.
Data
was
g
ath
er
ed
o
v
e
r
a
s
p
an
o
f
1
0
0
c
o
n
s
ec
u
tiv
e
d
ay
s
in
Ma
th
u
r
a
n
th
ag
am
,
T
am
il
Nad
u
,
I
n
d
ia
a
r
ep
r
esen
tativ
e
ag
r
icu
lt
u
r
al
ar
ea
.
Me
asu
r
e
m
en
ts
in
clu
d
ed
d
aily
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
r
ec
o
r
d
ed
b
y
wea
th
er
s
tatio
n
s
o
r
I
o
T
s
en
s
o
r
s
,
s
o
il
p
H
ass
ess
ed
u
s
in
g
a
d
ig
ital
m
eter
,
a
n
d
p
r
ec
ip
ita
tio
n
o
b
tain
e
d
f
r
o
m
m
eteo
r
o
lo
g
ical
s
tatio
n
s
.
T
h
e
d
ataset
co
n
ce
n
tr
ated
o
n
p
r
im
a
r
y
cr
o
p
s
:
r
ice,
m
aize
,
an
d
c
h
i
ck
p
ea
,
d
o
cu
m
e
n
tin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
405
-
4
1
5
410
th
eir
d
is
tin
ct
m
icr
o
clim
ates.
Do
cu
m
en
ted
p
ar
am
ete
r
s
in
cl
u
d
ed
d
aily
m
ea
n
tem
p
er
atu
r
e
,
r
elativ
e
h
u
m
id
ity
,
in
ter
p
o
lated
s
o
il
p
H,
an
d
d
ail
y
p
r
ec
ip
itatio
n
.
T
h
is
d
ata
aim
s
to
p
r
ed
ict
tem
p
o
r
al
c
h
an
g
es
in
cr
o
p
a
d
ap
tab
ilit
y
,
f
u
n
ctio
n
in
g
as
i
n
p
u
t
f
o
r
a
h
y
b
r
id
ML
ar
c
h
itectu
r
e
(
C
o
n
v
L
STM
-
B
iLST
M
-
SVM)
to
im
p
r
o
v
e
ag
r
icu
ltu
r
al
p
lan
n
in
g
.
Fig
u
r
e
3
(
a)
s
h
o
ws
th
e
tem
p
er
atu
r
e
g
r
ap
h
,
wh
ic
h
lik
ely
r
ep
r
esen
ts
th
e
v
ar
iatio
n
i
n
tem
p
er
atu
r
e
o
v
er
a
g
iv
en
p
er
i
o
d
.
T
em
p
er
at
u
r
e
i
s
a
k
ey
f
ac
to
r
in
f
lu
e
n
cin
g
cr
o
p
g
r
o
wth
,
a
n
d
t
h
is
g
r
ap
h
c
o
u
l
d
b
e
s
h
o
win
g
h
o
w
tem
p
er
atu
r
e
f
lu
ct
u
atio
n
s
th
r
o
u
g
h
o
u
t
th
e
y
ea
r
o
r
d
u
r
i
n
g
s
p
ec
i
f
ic
s
ea
s
o
n
s
im
p
ac
t
cr
o
p
p
r
o
d
u
ctiv
ity
.
Fig
u
r
e
3
(
b
)
s
h
o
ws
a
h
u
m
i
d
ity
g
r
ap
h
s
h
o
win
g
th
e
c
h
an
g
es
in
r
elativ
e
h
u
m
id
it
y
o
v
er
tim
e.
Hig
h
h
u
m
id
ity
lev
els
ca
n
p
r
o
m
o
te
f
u
n
g
al
g
r
o
wth
an
d
r
ed
u
ce
cr
o
p
y
ield
s
,
wh
ile
lo
w
h
u
m
id
ity
ca
n
lead
to
wat
er
s
tr
ess
f
o
r
cr
o
p
s
.
Fig
u
r
e
3
(
c)
d
e
n
o
tes
th
e
p
H
g
r
ap
h
d
is
p
lay
in
g
th
e
s
o
il'
s
ac
i
d
ity
o
r
alk
alin
ity
o
v
er
tim
e,
m
ea
s
u
r
ed
o
n
a
s
ca
le
f
r
o
m
0
t
o
1
4
,
with
7
b
ein
g
n
eu
tr
al.
Fig
u
r
e
3
(
d
)
s
h
o
ws
a
r
ai
n
f
all
g
r
ap
h
t
h
at
r
ep
r
es
en
ts
th
e
am
o
u
n
t
o
f
p
r
ec
ip
itatio
n
r
ec
eiv
ed
o
v
er
a
g
iv
en
p
er
io
d
,
ty
p
ically
s
h
o
wn
i
n
m
illi
m
eter
s
o
r
in
ch
es.
T
h
e
d
ataset
u
s
ed
f
o
r
cr
o
p
class
if
icatio
n
co
n
s
is
t
s
o
f
2
,
2
0
0
s
am
p
les
u
n
if
o
r
m
ly
allo
ca
ted
am
o
n
g
2
2
c
r
o
p
class
es,
with
ea
ch
class
in
clu
d
in
g
1
0
0
s
am
p
les
[
2
7
]
.
T
h
e
d
ataset
was
d
iv
id
ed
to
ac
h
iev
e
b
alan
ce
d
r
ep
r
ese
n
tatio
n
,
in
clu
d
in
g
7
0
%
f
o
r
tr
ain
in
g
(
1
,
5
4
0
s
am
p
les)
an
d
3
0
%
f
o
r
test
in
g
(
6
6
0
s
am
p
les).
E
v
er
y
cr
o
p
ca
teg
o
r
y
p
r
o
v
id
es
7
0
t
r
ain
in
g
s
am
p
les
an
d
3
0
test
in
g
s
am
p
les,
en
s
u
r
in
g
th
e
d
ataset
r
em
ain
s
im
p
ar
tia
l
ac
r
o
s
s
cla
s
s
if
icatio
n
s
,
in
clu
d
in
g
co
co
n
u
t,
r
ice,
p
ap
ay
a,
m
aize
,
ch
ic
k
p
ea
,
p
ig
eo
n
p
ea
s
,
p
o
m
e
g
r
an
ate,
m
o
th
b
ea
n
s
,
m
u
n
g
b
ea
n
s
,
b
lack
b
ea
n
s
,
b
an
an
a
,
len
til,
ap
p
le,
m
a
n
g
o
,
g
r
ap
es,
m
u
s
k
m
elo
n
,
ju
te,
o
r
an
g
e,
wate
r
m
elo
n
,
k
id
n
ey
b
ea
n
s
,
c
o
tto
n
,
co
f
f
ee
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
r
an
k
s
o
f
f
ea
tu
r
e
r
elev
an
ce
,
h
ig
h
lig
h
tin
g
r
ain
f
all,
tem
p
er
at
u
r
e,
an
d
s
o
il p
H
as th
e
p
r
ed
o
m
in
an
t c
o
n
tr
ib
u
to
r
s
.
Fig
u
r
e
5
d
ep
icts
f
lu
ctu
atio
n
s
in
s
ea
s
o
n
al
s
u
itab
ilit
y
,
h
ig
h
lig
h
tin
g
tem
p
o
r
al
ch
a
n
g
es
in
ag
r
icu
ltu
r
al
p
o
ten
tial.
Fig
u
r
e
6
s
h
o
ws p
r
e
d
ictio
n
m
a
p
s
th
at
illu
s
tr
ate
s
p
atial
s
u
itab
i
lity
zo
n
es.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
3
.
S
ea
s
o
n
al
v
a
r
i
ati
o
n
o
f
k
e
y
en
v
i
r
o
n
m
e
n
t
al
f
ac
to
r
s
(
a)
tem
p
e
r
at
u
r
e
,
(
b
)
h
u
m
i
d
it
y
,
(
c
)
pH
,
an
d
(
d
)
r
a
in
f
a
ll
Fig
u
r
e
4
.
Featu
r
e
im
p
o
r
ta
n
ce
Fig
u
r
e
5
.
Mo
n
th
ly
s
u
itab
ilit
y
t
r
en
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
r
o
p
p
r
ed
ictio
n
in
Ta
mil Na
d
u
a
cc
o
r
d
in
g
to
en
viro
n
men
ta
l
a
n
d
s
o
il fa
cto
r
s
…
(
S
u
n
d
a
r
a
j Ka
n
n
a
n
S
u
s
ee
)
411
Fig
u
r
e
6
.
Sp
atial
d
is
tr
ib
u
tio
n
T
h
is
eq
u
itab
le
d
iv
is
io
n
f
ac
ilit
ates
r
ig
o
r
o
u
s
tr
ain
in
g
,
im
p
a
r
t
ial
ass
es
s
m
en
t,
an
d
r
ed
u
ce
s
o
v
er
f
itti
n
g
,
h
en
ce
im
p
r
o
v
i
n
g
t
h
e
m
o
d
el'
s
g
en
er
aliza
tio
n
f
o
r
v
ar
io
u
s
cr
o
p
p
r
ed
ictio
n
task
s
.
T
h
e
C
o
n
v
L
STM
co
n
f
u
s
io
n
m
atr
ix
in
Fig
u
r
e
7
s
h
o
ws
a
h
ig
h
lev
el
o
f
ac
c
u
r
ac
y
ac
r
o
s
s
all
cr
o
p
class
es,
as
s
h
o
wn
b
y
th
e
m
o
s
tly
s
tr
o
n
g
d
iag
o
n
al
e
n
tr
ies.
Sh
o
win
g
s
t
r
o
n
g
p
er
f
o
r
m
an
ce
with
m
in
i
m
al
u
n
ce
r
tain
ty
ac
r
o
s
s
co
m
p
ar
ab
le
cr
o
p
s
,
s
m
all
o
f
f
-
d
ia
g
o
n
al
v
alu
es
in
d
icate
r
ar
e
m
is
class
if
icatio
n
s
.
Fig
u
r
e
8
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
o
f
th
e
class
if
icatio
n
r
ep
o
r
t.
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
i
x
an
aly
s
is
f
o
r
cr
o
p
class
es
Fig
u
r
e
8
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
I
t m
ay
in
clu
d
e
m
etr
ics s
u
ch
as
th
e
f
o
llo
win
g
:
i)
Acc
u
r
ac
y
:
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
t
p
r
ed
ictio
n
s
(
b
o
th
tr
u
e
p
o
s
itiv
es
an
d
tr
u
e
n
e
g
ativ
es)
o
u
t
o
f
th
e
t
o
tal
p
r
ed
ictio
n
s
.
=
+
+
+
+
(
2
)
ii)
Pre
cisi
o
n
:
th
e
r
atio
o
f
c
o
r
r
ec
tl
y
p
r
ed
icted
p
o
s
itiv
e
o
b
s
er
v
atio
n
s
to
th
e
to
tal
p
r
ed
icted
p
o
s
itiv
es
.
=
+
(
3
)
iii)
R
ec
all
: th
e
r
atio
o
f
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
o
b
s
er
v
atio
n
s
to
all
ac
tu
al
p
o
s
itiv
es
.
=
+
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
405
-
4
1
5
412
iv
)
F1
-
s
co
r
e
:
th
e
weig
h
ted
av
er
a
g
e
o
f
p
r
ec
is
io
n
a
n
d
r
ec
all,
u
s
ed
to
b
alan
ce
b
o
th
m
etr
ics,
p
ar
ticu
lar
ly
in
ca
s
es o
f
im
b
alan
ce
d
class
es
.
1
−
=
2
×
(
∗
)
(
+
)
(
5
)
Miss
in
g
o
r
in
ter
f
er
en
ce
in
en
v
ir
o
n
m
e
n
tal
d
ata
ca
n
b
ias
o
u
tco
m
es,
wh
ils
t
in
s
u
f
f
icien
t
d
ataset
s
ize
s
m
ay
lead
to
o
v
e
r
f
itti
n
g
.
C
lass
im
b
alan
ce
m
ay
r
esu
lt
in
d
ec
ep
tiv
e
ac
cu
r
ac
y
f
o
r
u
n
u
s
u
al
c
r
o
p
s
u
n
less
s
u
itab
le
s
af
eg
u
ar
d
s
a
r
e
im
p
le
m
en
ted
.
I
n
a
d
eq
u
ate
co
n
tr
o
l
o
f
tem
p
o
r
al
an
d
s
p
atial
c
o
r
r
elatio
n
s
m
ay
d
is
to
r
t
m
o
d
el
ef
f
icac
y
.
Ultim
ately
,
u
s
in
g
tr
ain
in
g
d
ata
f
o
r
test
in
g
o
r
i
n
a
d
eq
u
ate
cr
o
s
s
-
v
alid
atio
n
m
ay
ar
tific
ially
en
h
an
ce
p
er
f
o
r
m
an
ce
m
etr
ics.
T
h
is
r
esear
ch
im
p
r
o
v
es
ag
r
icu
ltu
r
al
d
ec
is
io
n
-
m
ak
in
g
b
y
f
o
r
ec
asti
n
g
cr
o
p
s
u
itab
ilit
y
in
Ma
th
u
r
an
th
a
g
am
,
T
a
m
il
Nad
u
,
I
n
d
ia
u
s
in
g
a
h
y
b
r
id
m
o
d
el
th
at
co
m
b
in
es
l
in
ea
r
SVM,
B
iLST
M,
an
d
C
o
n
v
L
STM
.
I
t
in
co
r
p
o
r
ates
clim
atic
v
ar
iab
les
s
u
ch
as
tem
p
er
atu
r
e
a
n
d
p
r
ec
ip
itatio
n
,
ass
is
tin
g
f
ar
m
er
s
in
o
p
tim
u
m
cr
o
p
s
elec
tio
n
an
d
f
ac
ilit
atin
g
r
eg
io
n
al
a
g
r
ic
u
ltu
r
al
p
lan
n
in
g
.
T
h
e
m
o
d
e
ls
in
clu
d
e
clim
ate
v
ar
iab
ilit
y
,
wh
ich
f
ac
ilit
ates
t
h
e
ad
o
p
ti
o
n
o
f
r
esil
ien
t
f
ar
m
in
g
p
r
ac
tices
an
d
m
eth
o
d
s
,
e
n
h
a
n
cin
g
f
o
o
d
s
ec
u
r
ity
an
d
p
r
o
m
o
tin
g
s
u
s
tain
ab
le
ag
r
icu
ltu
r
e
in
th
e
f
ac
e
o
f
ch
an
g
in
g
clim
atic
co
n
d
itio
n
s
.
3
.
1
.
Acc
ura
cy
Acc
u
r
ac
y
r
ef
e
r
s
to
th
e
p
er
ce
n
tag
e
o
f
c
o
r
r
ec
tly
p
r
ed
icted
in
s
tan
ce
s
(
i.e
.
,
th
e
n
u
m
b
e
r
o
f
co
r
r
ec
t
cr
o
p
p
r
ed
ictio
n
s
d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
er
o
f
in
s
tan
ce
s
)
.
T
h
e
m
o
d
el
lik
ely
s
h
o
ws
h
ig
h
ac
cu
r
ac
y
b
ec
au
s
e
th
e
h
y
b
r
id
n
atu
r
e
o
f
th
e
m
o
d
el,
u
s
in
g
lin
ea
r
SVM,
B
iLST
M,
a
n
d
C
o
n
v
L
STM
,
en
ab
les
it
to
ca
p
tu
r
e
b
o
th
s
p
atial
an
d
tem
p
o
r
al
d
ep
e
n
d
en
cies in
th
e
d
ata,
lead
in
g
to
b
etter
p
r
ed
ictio
n
s
.
i)
Pre
cisi
o
n
:
p
r
ec
is
io
n
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
t
p
o
s
itiv
e
p
r
ed
ictio
n
s
.
ii)
R
ec
all
m
ea
s
u
r
es
th
e
m
o
d
el'
s
ab
ilit
y
to
co
r
r
ec
tly
id
en
tify
all
th
e
r
elev
an
t
in
s
tan
ce
s
.
A
h
i
g
h
r
ec
all
v
alu
e
in
d
icate
s
th
at
th
e
m
o
d
el
is
g
o
o
d
at
d
etec
tin
g
all
p
o
s
s
ib
le
cr
o
p
ty
p
es,
r
ed
u
cin
g
th
e
lik
elih
o
o
d
o
f
m
is
s
in
g
an
ap
p
r
o
p
r
iate
cr
o
p
r
ec
o
m
m
e
n
d
atio
n
.
iii)
F1
-
s
co
r
e:
t
h
e
F1
-
s
co
r
e
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
a
n
d
r
ec
all,
p
r
o
v
id
i
n
g
a
b
ala
n
ce
d
m
ea
s
u
r
e
o
f
th
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
.
3
.
2
.
H
y
brid
m
o
del v
s
.
t
r
a
ditio
na
l
L
ST
M
m
o
del
s
W
h
en
co
m
p
ar
in
g
th
e
h
y
b
r
id
m
o
d
el
(
l
in
ea
r
SVM+
B
iLST
M+
C
o
n
v
L
STM
)
with
tr
ad
itio
n
al
L
STM
m
o
d
els,
th
e
h
y
b
r
id
a
p
p
r
o
ac
h
is
ex
p
ec
ted
to
o
u
t
p
er
f
o
r
m
in
s
ev
er
al
way
s
,
s
u
ch
as
h
ig
h
er
g
en
er
aliza
tio
n
.
T
h
e
in
clu
s
io
n
o
f
lin
ea
r
SVM
alo
n
g
s
id
e
DL
m
o
d
els
en
s
u
r
es
b
ett
er
g
en
er
aliza
tio
n
o
v
e
r
a
v
ar
iet
y
o
f
cr
o
p
ty
p
es
an
d
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
T
r
a
d
itio
n
al
L
STM
m
o
d
els
m
ay
s
tr
u
g
g
le
to
c
ap
tu
r
e
c
o
m
p
lex
s
p
atial
r
elatio
n
s
h
ip
s
,
wh
er
ea
s
C
o
n
v
L
STM
ex
ce
ls
in
th
is
d
o
m
ain
.
T
ab
le
1
d
em
o
n
s
tr
ates
th
a
t
th
e
h
y
b
r
id
C
o
n
v
L
ST
M
-
B
iLST
M
-
SVM
m
o
d
el
o
u
tp
er
f
o
r
m
s
its
in
d
i
v
id
u
al
m
o
d
el
s
,
ac
h
iev
in
g
s
u
p
er
i
o
r
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
v
ia
th
e
s
u
cc
ess
f
u
l
in
teg
r
atio
n
o
f
s
p
atial,
tem
p
o
r
al,
an
d
class
if
icatio
n
f
u
n
ctio
n
alities
.
T
ab
le
2
h
y
b
r
id
d
esig
n
d
em
o
n
s
tr
at
es
h
ig
h
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
all
p
ar
am
eter
s
,
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
in
d
iv
id
u
al
class
if
ier
s
,
r
eg
r
ess
io
n
m
o
d
els,
a
n
d
r
u
le
-
b
a
s
ed
s
y
s
tem
s
b
y
ad
ep
tly
ca
p
t
u
r
i
n
g
s
p
atial,
tem
p
o
r
al,
an
d
ca
teg
o
r
is
atio
n
p
atter
n
s
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
h
y
b
r
i
d
an
d
in
d
iv
i
d
u
al
m
o
d
els
M
o
d
e
l
c
o
m
p
o
n
e
n
t
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
Li
n
e
a
r
S
V
M
0
.
9
4
2
1
0
.
9
4
4
0
0
.
9
4
2
1
0
.
9
4
2
0
B
i
LST
M
0
.
9
6
1
5
0
.
9
6
2
3
0
.
9
6
1
5
0
.
9
6
1
2
C
o
n
v
LST
M
0
.
9
6
7
8
0
.
9
6
8
2
0
.
9
6
7
8
0
.
9
6
7
7
H
y
b
r
i
d
(
S
V
M
+
B
i
LS
TM
+
C
o
n
v
LSTM
)
0
.
9
7
5
8
0
.
9
7
6
4
0
.
9
7
5
8
0
.
9
7
5
7
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
cr
o
p
class
if
icatio
n
tech
n
iq
u
es
M
o
d
e
l
t
y
p
e
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
R
u
l
e
-
b
a
se
d
s
y
s
t
e
m
0
.
7
8
2
0
0
.
7
9
0
0
0
.
7
8
0
0
0
.
7
8
5
0
S
t
a
t
i
st
i
c
a
l
r
e
g
r
e
ssi
o
n
0
.
8
7
0
0
0
.
8
7
5
0
0
.
8
7
0
0
0
.
8
7
2
0
Li
n
e
a
r
S
V
M
0
.
9
4
2
1
0
.
9
4
4
0
0
.
9
4
2
1
0
.
9
4
2
0
B
i
LST
M
0
.
9
6
1
5
0
.
9
6
2
3
0
.
9
6
1
5
0
.
9
6
1
2
C
o
n
v
LST
M
0
.
9
6
7
8
0
.
9
6
8
2
0
.
9
6
7
8
0
.
9
6
7
7
H
y
b
r
i
d
(
S
V
M
+
B
i
LS
TM
+
C
o
n
v
LSTM
)
0
.
9
7
5
8
0
.
9
7
6
4
0
.
9
7
5
8
0
.
9
7
5
7
T
h
is
s
tu
d
y
'
s
f
in
d
in
g
s
i
n
d
icate
th
at
a
h
y
b
r
i
d
ML
ar
ch
itectu
r
e
in
teg
r
atin
g
lin
ea
r
SVM,
B
iLST
M,
an
d
C
o
n
v
L
STM
s
ig
n
if
ican
tly
en
h
an
ce
s
cr
o
p
p
r
ed
ictio
n
ac
cu
r
a
cy
(
0
.
9
7
5
8
)
a
n
d
F1
-
s
co
r
e
(
0
.
9
7
5
7
)
r
elativ
e
t
o
s
tan
d
alo
n
e
m
o
d
els.
T
h
is
d
em
o
n
s
tr
ates
th
at
th
e
in
teg
r
atio
n
o
f
tem
p
o
r
al
(
B
iLST
M)
an
d
s
p
atial
(
C
o
n
v
L
STM
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
r
o
p
p
r
ed
ictio
n
in
Ta
mil Na
d
u
a
cc
o
r
d
in
g
to
en
viro
n
men
ta
l
a
n
d
s
o
il fa
cto
r
s
…
(
S
u
n
d
a
r
a
j Ka
n
n
a
n
S
u
s
ee
)
413
d
ep
en
d
e
n
cies
with
a
r
o
b
u
s
t
class
if
ier
(
SVM)
m
o
r
e
s
u
cc
ess
f
u
lly
ca
p
tu
r
es
co
m
p
licated
en
v
ir
o
n
m
en
tal
-
s
o
il
in
ter
ac
tio
n
s
th
an
tr
ad
itio
n
al
m
eth
o
d
s
.
T
h
e
s
u
p
e
r
io
r
p
r
e
d
ictio
n
p
er
f
o
r
m
a
n
ce
p
r
o
p
o
s
es
th
at
l
o
ca
l
en
v
i
r
o
n
m
e
n
tal
an
d
s
o
il
d
ata
m
ay
b
e
d
ep
e
n
d
a
b
ly
u
s
ed
to
g
u
id
e
ag
r
icu
ltu
r
al
p
lan
n
in
g
,
en
h
a
n
ce
cr
o
p
s
elec
tio
n
,
an
d
m
in
im
i
z
e
r
eso
u
r
ce
waste.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
ML
ar
ch
itectu
r
e
co
m
b
in
es
C
o
n
v
L
STM
,
B
iLST
M,
an
d
l
in
ea
r
SVM.
C
o
n
v
L
STM
id
en
tifie
s
s
p
atial
d
ep
en
d
e
n
cies
in
s
o
il
an
d
e
n
v
ir
o
n
m
en
tal
ch
ar
ac
ter
is
tics
,
B
iLST
M
an
aly
s
i
s
tem
p
o
r
al
p
atter
n
s
,
a
n
d
SVM
ex
ec
u
tes
th
e
f
in
al
cr
o
p
class
if
icatio
n
u
s
in
g
th
e
o
u
tp
u
ts
f
r
o
m
s
tack
ed
L
STM
,
th
u
s
h
ar
n
ess
in
g
b
o
th
s
p
atio
-
tem
p
o
r
al
an
d
class
if
icatio
n
a
d
v
an
tag
es.
T
h
e
in
f
o
r
m
atio
n
,
g
ath
e
r
ed
f
r
o
m
Ma
th
u
r
an
th
a
g
am
,
T
a
m
il
Nad
u
,
I
n
d
ia
h
as
2
,
2
0
0
s
am
p
les
s
p
an
n
in
g
2
2
cr
o
p
s
,
in
clu
d
in
g
attr
ib
u
tes
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
i
d
ity
,
r
ai
n
f
al
l,
s
o
il
p
H,
an
d
NPK
lev
els.
A
7
0
:3
0
r
atio
was
u
s
ed
f
o
r
tr
ain
i
n
g
(
1
,
5
4
0
s
am
p
les)
an
d
test
in
g
(
6
6
0
s
am
p
les).
T
h
e
h
y
b
r
id
m
o
d
el
h
a
d
an
ac
cu
r
a
cy
o
f
0
.
9
7
5
8
,
o
u
t
p
er
f
o
r
m
in
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
s
ep
ar
ate
m
o
d
els.
Hy
p
er
p
ar
a
m
eter
s
f
o
r
L
STM
lay
er
s
an
d
SVM
wer
e
ca
lib
r
ated
b
y
cr
o
s
s
-
v
alid
atio
n
an
d
p
ar
am
eter
ch
a
n
g
e
s
tu
d
ies to
e
n
h
an
ce
p
er
f
o
r
m
an
ce
.
A
h
y
b
r
i
d
m
o
d
el
th
at
co
m
b
i
n
es
C
o
n
v
L
STM
,
B
iLST
M,
an
d
l
in
ea
r
SVM
with
in
a
co
m
p
lem
en
tar
y
f
r
am
ewo
r
k
.
C
o
n
v
L
STM
ca
p
tu
r
es
s
p
atial
r
elatio
n
s
h
ip
s
,
B
i
L
STM
m
o
d
els
tem
p
o
r
al
tr
en
d
s
,
an
d
lin
ea
r
SVM
p
er
f
o
r
m
s
class
if
icatio
n
b
ased
o
n
f
ea
tu
r
es
r
etr
iev
e
d
b
y
L
ST
M.
T
h
is
lay
er
ed
m
eth
o
d
o
lo
g
y
allo
ws
an
in
teg
r
ated
p
r
ed
ictiv
e
s
y
s
te
m
th
at
im
p
r
o
v
es
th
e
ac
cu
r
ac
y
an
d
r
eliab
ili
ty
o
f
c
r
o
p
p
r
e
d
ictio
n
s
,
o
u
tp
er
f
o
r
m
in
g
in
d
i
v
id
u
al
m
o
d
els
an
d
d
em
o
n
s
tr
atin
g
th
e
ef
f
icac
y
o
f
in
teg
r
atin
g
s
p
atio
-
tem
p
o
r
al
lear
n
in
g
with
tr
ad
itio
n
al
ca
teg
o
r
i
z
atio
n
tech
n
iq
u
es.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
SVM
-
B
iLST
M
-
C
o
n
v
L
STM
m
o
d
el
with
J
ay
a
f
ea
t
u
r
e
s
e
lectio
n
in
co
r
p
o
r
ates
Ma
th
u
r
an
th
a
g
am
'
s
clim
atic
an
d
s
o
il
d
ata.
T
h
is
en
s
u
r
es
th
at
f
ar
m
in
g
d
ec
is
io
n
s
in
T
am
il
Nad
u
a
r
e
lo
ca
lized
,
d
ata
-
d
r
iv
e
n
,
an
d
s
u
s
tain
ab
le,
g
iv
en
th
e
s
tate'
s
s
p
ec
if
ic
en
v
i
r
o
n
m
en
tal
c
o
n
d
itio
n
s
.
C
o
n
n
e
ctin
g
th
e
m
o
d
el
to
ag
r
icu
ltu
r
al
ex
ten
s
io
n
n
etwo
r
k
s
,
GI
S
p
latf
o
r
m
s
,
an
d
m
o
b
i
le
ap
p
licatio
n
s
allo
ws
f
o
r
d
ata
-
d
r
iv
en
d
ec
is
io
n
ass
is
tan
ce
in
ag
r
icu
ltu
r
e,
as
well
as
r
ea
l
-
tim
e
cr
o
p
aler
ts
,
g
eo
g
r
ap
h
ic
v
is
u
aliza
tio
n
,
an
d
f
ar
m
er
o
u
tr
ea
ch
.
Desp
ite
it
s
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
,
th
e
p
r
o
p
o
s
e
d
h
y
b
r
id
C
o
n
v
L
STM
-
B
iLST
M
-
SVM
ar
ch
i
tectu
r
e
h
as
s
ev
er
al
lim
itatio
n
s
.
I
n
itially
,
alth
o
u
g
h
th
e
d
ataset
is
b
alan
ce
d
f
o
r
ex
p
er
im
en
tal
p
u
r
p
o
s
es,
ac
tu
al
a
g
r
icu
ltu
r
al
d
ata
o
f
ten
ex
h
ib
it im
b
alan
ce
s
,
p
o
ten
tially
im
p
ac
tin
g
p
er
f
o
r
m
an
ce
f
o
r
u
n
d
er
-
c
u
ltiv
ated
cr
o
p
s
.
T
h
e
m
o
d
el
is
tr
ai
n
ed
o
n
s
o
il
a
n
d
clim
atic
d
ata
p
ar
ticu
lar
to
Ma
th
u
r
an
th
a
g
am
,
p
er
h
a
p
s
r
est
r
ictin
g
its
ap
p
licab
ilit
y
to
o
th
e
r
p
lace
s
in
T
am
il
Nad
u
with
o
u
t
lo
c
alize
d
ca
lib
r
atio
n
.
W
h
ile
f
o
r
ec
asts
ex
h
ib
it
h
ig
h
ac
cu
r
ac
y
,
p
r
ac
tical
im
p
lem
en
tatio
n
in
r
ea
l
-
tim
e
en
c
o
u
n
te
r
s
o
b
s
tacle
s
,
in
clu
d
in
g
th
e
n
ee
d
f
o
r
c
o
n
s
tan
t
d
ata
s
tr
ea
m
s
f
r
o
m
m
eteo
r
o
lo
g
ical
s
tatio
n
s
,
I
o
T
s
en
s
o
r
s
,
an
d
d
ep
en
d
a
b
le
in
ter
n
et
ac
ce
s
s
in
r
em
o
te
r
eg
io
n
s
.
R
ec
tify
in
g
th
ese
d
ef
icien
cies
is
cr
u
cial
f
o
r
th
e
s
ca
lab
le,
ag
r
i
cu
ltu
r
is
t
-
f
r
ien
d
ly
im
p
lem
e
n
tatio
n
.
I
m
p
r
o
v
in
g
th
e
h
y
b
r
id
s
y
s
tem
'
s
s
ca
lab
ilit
y
,
ac
cu
r
ac
y
,
an
d
r
eliab
ilit
y
f
o
r
m
o
r
e
wid
esp
r
ea
d
ag
r
icu
ltu
r
al
u
s
es m
ay
in
v
o
l
v
e
f
u
tu
r
e
ex
ten
s
io
n
s
s
u
ch
as
in
teg
r
atin
g
d
y
n
am
ic
wea
th
er
f
o
r
r
ea
l
-
tim
e
ad
ap
tab
ilit
y
,
f
u
s
in
g
s
atellite
im
ag
er
y
to
ca
p
tu
r
e
lar
g
e
-
s
ca
le
s
p
atial
v
ar
ia
b
ilit
y
,
an
d
f
ed
er
ated
lear
n
in
g
f
r
a
m
ewo
r
k
s
to
g
u
ar
an
tee
p
r
iv
a
cy
-
p
r
eser
v
i
n
g
cr
o
p
p
r
ed
ictio
n
wh
ile
en
a
b
lin
g
in
te
r
ac
tio
n
ac
r
o
s
s
r
eg
io
n
s
.
I
n
th
e
f
u
tu
r
e,
th
ese
r
esu
lts
m
a
y
f
ac
ili
tate
th
e
cr
ea
tio
n
o
f
d
ec
is
io
n
-
s
u
p
p
o
r
t
s
y
s
tem
s
f
o
r
f
ar
m
er
s
an
d
p
o
licy
m
ak
er
s
,
allo
w
f
o
r
r
ea
l
-
tim
e
cr
o
p
r
ec
o
m
m
e
n
d
atio
n
s
u
s
in
g
I
o
T
s
en
s
o
r
s
,
an
d
in
f
o
r
m
ad
a
p
tiv
e
t
ac
tics
in
r
esp
o
n
s
e
to
ch
an
g
in
g
clim
atic
co
n
d
itio
n
s
.
4.
CO
NCLU
SI
O
NS
T
h
is
r
esear
ch
ef
f
ec
tiv
ely
a
d
d
r
ess
ed
th
e
is
s
u
e
o
f
p
r
ed
ictin
g
cr
o
p
s
u
itab
ilit
y
in
Ma
th
u
r
an
th
ag
am
,
T
am
il
Nad
u
,
I
n
d
ia
b
y
u
s
in
g
a
h
y
b
r
id
ML
f
r
am
ewo
r
k
th
at
c
o
m
b
in
es
lin
ea
r
SVM,
B
iLST
M,
an
d
C
o
n
v
L
STM
n
etwo
r
k
s
.
T
h
e
h
y
b
r
id
m
o
d
el
en
h
an
ce
d
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
b
y
ef
f
ec
tiv
ely
ca
p
tu
r
in
g
b
o
th
tem
p
o
r
al
an
d
s
p
atial
d
ep
en
d
en
cies,
ac
h
iev
i
n
g
an
ac
cu
r
ac
y
o
f
0
.
9
7
5
8
an
d
an
F1
-
s
co
r
e
o
f
0
.
9
7
5
7
,
im
p
r
o
v
in
g
lin
ea
r
SVM
(
ac
cu
r
ac
y
0
.
9
4
2
1
)
,
B
iLST
M
(
0
.
9
6
1
5
)
,
an
d
C
o
n
v
L
STM
(
0
.
9
6
7
8
)
.
Min
-
m
a
x
n
o
r
m
a
lizatio
n
an
d
J
ay
a
o
p
tim
izatio
n
ef
f
icie
n
tly
u
s
ed
en
v
ir
o
n
m
en
tal
an
d
s
o
il
v
ar
iab
les,
s
u
ch
as
h
u
m
id
ity
,
r
ain
f
all
,
tem
p
er
atu
r
e
,
an
d
p
H,
f
o
r
m
o
d
el
tr
ain
in
g
.
T
h
e
q
u
an
titativ
e
f
in
d
i
n
g
s
v
alid
ate
th
at
th
e
in
teg
r
atio
n
o
f
DL
with
tr
ad
itio
n
al
ML
m
eth
o
d
o
l
o
g
ies
o
f
f
er
s
a
f
o
r
m
i
d
ab
le
s
o
lu
tio
n
f
o
r
cr
o
p
f
o
r
ec
a
s
tin
g
an
d
u
n
d
er
s
co
r
es
th
e
im
p
o
r
tan
ce
o
f
l
o
ca
lized
en
v
ir
o
n
m
en
tal
d
ata
in
a
g
r
ic
u
ltu
r
al
s
tr
ateg
y
an
d
d
ec
is
io
n
-
m
ak
in
g
.
Fu
tu
r
e
wo
r
k
s
m
ay
co
n
ce
n
tr
ate
o
n
au
g
m
en
tin
g
th
e
d
ataset,
i
n
teg
r
atin
g
r
ea
l
-
tim
e
s
en
s
o
r
d
ata,
an
d
in
tr
o
d
u
ci
n
g
s
u
p
p
lem
en
tar
y
en
v
ir
o
n
m
en
ta
l
ch
ar
ac
ter
is
tics
to
im
p
r
o
v
e
m
o
d
el
g
e
n
er
aliza
tio
n
a
n
d
f
lex
i
b
ilit
y
,
th
er
eb
y
f
ac
ilit
atin
g
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
ac
r
o
s
s
v
ar
io
u
s
g
eo
g
r
ap
h
ies.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
405
-
4
1
5
414
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Su
n
d
ar
aj
Kan
n
a
n
Su
s
ee
✓
✓
✓
✓
✓
✓
✓
✓
Sh
en
b
ag
ar
am
asu
b
r
am
an
ia
n
Sh
en
b
ag
a
Vad
iv
u
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
M
u
r
u
g
esan
Sen
th
il Ku
m
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA
AV
AI
L
AB
I
L
I
T
Y
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
t
h
e
f
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
i
n
g
au
th
o
r
,
[
SKS]
,
o
n
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
A
.
M
.
A
.
R
i
a
z
u
l
h
a
m
e
e
d
,
C
.
S
.
R
a
n
g
a
n
a
t
h
a
n
,
P
.
P
a
n
d
e
y
,
B
.
S
a
k
t
h
i
s
a
r
a
v
a
n
a
n
,
K
.
S
a
s
i
k
a
l
a
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
S
m
a
r
t
c
o
m
p
o
s
t
i
n
g
s
o
l
u
t
i
o
n
s
f
o
r
o
r
g
a
n
i
c
w
a
s
t
e
m
a
n
a
g
e
m
e
n
t
a
n
d
s
o
i
l
e
n
r
i
c
h
m
e
n
t
i
n
a
g
r
i
c
u
l
t
u
r
e
w
i
t
h
I
o
T
a
n
d
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
,
”
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
E
x
p
e
r
t
S
y
s
t
e
m
s
,
I
C
S
E
S
2
0
2
4
-
P
r
o
c
e
e
d
i
n
g
s
,
p
p
.
3
3
9
–
3
4
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
E
S
6
3
4
4
5
.
2
0
2
4
.
1
0
7
6
3
2
5
9
.
[
2
]
M
.
D
h
a
n
a
r
a
j
u
,
P
.
C
h
e
n
n
i
a
p
p
a
n
,
K
.
R
a
mal
i
n
g
a
m,
S
.
P
a
z
h
a
n
i
v
e
l
a
n
,
a
n
d
R
.
K
a
l
i
a
p
e
r
u
m
a
l
,
“
S
mar
t
f
a
r
mi
n
g
:
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
-
b
a
s
e
d
su
s
t
a
i
n
a
b
l
e
a
g
r
i
c
u
l
t
u
r
e
,
”
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
2
,
n
o
.
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
1
0
1
7
4
5
.
[
3
]
M
.
M
.
M
a
mo
u
d
a
n
,
A
.
J
a
f
a
r
i
,
Z.
M
o
h
a
mm
a
d
n
a
z
a
r
i
,
M
.
M
.
N
a
si
r
i
,
a
n
d
M
.
Y
a
z
d
a
n
i
,
“
H
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
me
t
a
h
e
u
r
i
st
i
c
mo
d
e
l
f
o
r
su
s
t
a
i
n
a
b
l
e
a
g
r
i
-
f
o
o
d
p
r
o
d
u
c
t
i
o
n
a
n
d
su
p
p
l
y
c
h
a
i
n
p
l
a
n
n
i
n
g
u
n
d
e
r
w
a
t
e
r
sca
r
c
i
t
y
,
”
Re
s
o
u
rc
e
s,
E
n
v
i
r
o
n
m
e
n
t
a
n
d
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
s
e
n
v
.
2
0
2
3
.
1
0
0
1
3
3
.
[
4
]
S
.
R
.
M
o
u
sa
v
i
,
V
.
A
.
J.
M
a
h
j
e
n
a
b
a
d
i
,
B
.
K
h
o
s
h
r
u
,
a
n
d
M
.
R
e
z
a
e
i
,
“
S
p
a
t
i
a
l
p
r
e
d
i
c
t
i
o
n
o
f
w
i
n
t
e
r
w
h
e
a
t
y
i
e
l
d
g
a
p
:
a
g
r
o
-
c
l
i
ma
t
i
c
mo
d
e
l
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
Fr
o
n
t
i
e
rs i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
3
.
1
3
0
9
1
7
1
.
[
5
]
C
.
C
.
S
.
B
a
sa
v
a
r
a
d
d
i
,
C
.
S
.
R
a
n
g
a
n
a
t
h
a
n
,
K
.
S
i
n
d
h
u
j
a
,
N
.
M
o
h
a
n
k
u
mar,
M
.
Ja
g
a
d
e
e
sw
a
r
a
n
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
R
e
a
l
-
t
i
m
e
i
n
c
i
d
e
n
t
d
e
t
e
c
t
i
o
n
a
n
d
r
e
s
p
o
n
se
w
i
t
h
i
so
l
a
t
i
o
n
f
o
r
e
st
a
l
g
o
r
i
t
h
m
a
n
d
c
l
o
u
d
i
n
f
r
a
s
t
r
u
c
t
u
r
e
,
”
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
-
S
MA
C
(
I
o
T
i
n
S
o
c
i
a
l
,
Mo
b
i
l
e
,
A
n
a
l
y
t
i
c
s
a
n
d
C
l
o
u
d
)
,
I
-
S
MA
C
2
0
2
4
-
Pr
o
c
e
e
d
i
n
g
s
,
p
p
.
1
0
2
4
–
1
0
2
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
-
S
M
A
C
6
1
8
5
8
.
2
0
2
4
.
1
0
7
1
4
5
9
3
.
[
6
]
C
.
S
.
R
a
n
g
a
n
a
t
h
a
n
,
A
.
A
.
M
.
A
.
R
i
a
z
u
l
h
a
me
e
d
,
G
.
B
r
i
n
d
h
a
,
N
.
M
o
h
a
n
k
u
mar,
S
.
Y
u
v
a
r
a
j
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
C
l
o
u
d
-
i
n
t
e
g
r
a
t
e
d
w
i
r
e
l
e
s
s
se
n
s
o
r
n
e
t
w
o
r
k
s
f
o
r
d
y
n
a
m
i
c
h
o
u
se
h
o
l
d
a
i
r
p
o
l
l
u
t
i
o
n
m
a
n
a
g
e
me
n
t
,
”
2
0
2
4
As
i
a
P
a
c
i
f
i
c
C
o
n
f
e
re
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
i
n
T
e
c
h
n
o
l
o
g
y
(
A
PC
I
T
)
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
P
C
I
T6
2
0
0
7
.
2
0
2
4
.
1
0
6
7
3
7
1
5
.
[
7
]
B
.
R
.
B
a
b
u
,
M
.
A
.
H
a
i
l
e
,
D
.
T.
H
a
i
l
e
,
a
n
d
D
.
Ze
r
i
h
u
n
,
“
R
e
a
l
-
t
i
me
se
n
so
r
d
a
t
a
a
n
a
l
y
t
i
c
s
a
n
d
v
i
su
a
l
i
z
a
t
i
o
n
i
n
c
l
o
u
d
-
b
a
se
d
sy
st
e
ms
f
o
r
f
o
r
e
st
e
n
v
i
r
o
n
me
n
t
m
o
n
i
t
o
r
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
i
n
S
i
g
n
a
l
a
n
d
I
m
a
g
e
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
2
9
–
3
9
,
2
0
2
3
,
d
o
i
:
1
0
.
2
9
2
8
4
/
i
j
a
si
s
.
9
.
1
.
2
0
2
3
.
2
9
-
3
9
.
[
8
]
S
.
S
h
a
r
a
f
a
t
e
t
a
l
.
,
“
A
n
I
o
T
-
e
n
a
b
l
e
d
A
I
sy
st
e
m
f
o
r
r
e
a
l
-
t
i
me
c
r
o
p
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
s
o
i
l
a
n
d
w
e
a
t
h
e
r
d
a
t
a
i
n
p
r
e
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
S
m
a
r
t
A
g
r
i
c
u
l
t
u
r
a
l
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
e
c
h
.
2
0
2
5
.
1
0
1
2
6
3
.
[
9
]
T.
M
a
h
mu
d
e
t
a
l
.
,
“
A
n
a
p
p
r
o
a
c
h
f
o
r
c
r
o
p
p
r
e
d
i
c
t
i
o
n
i
n
a
g
r
i
c
u
l
t
u
r
e
:
i
n
t
e
g
r
a
t
i
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
ms
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
E
E
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
7
3
5
8
3
–
1
7
3
5
9
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
7
8
7
3
9
.
[
1
0
]
Z.
A
l
s
a
l
a
mi
,
G
.
M
o
h
a
mm
e
d
,
a
n
d
T
.
S
r
i
n
i
v
a
s,
“
E
n
h
a
n
c
i
n
g
c
r
o
p
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
u
si
n
g
I
o
T
-
b
a
se
d
s
o
i
l
m
o
i
s
t
u
r
e
a
n
d
n
u
t
r
i
e
n
t
sen
s
o
r
s,”
S
H
S
We
b
o
f
C
o
n
f
e
r
e
n
c
e
s
,
v
o
l
.
2
1
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
5
1
/
s
h
sc
o
n
f
/
2
0
2
5
2
1
6
0
1
0
2
9
.
[
1
1
]
V
.
G
.
S
i
v
a
k
u
mar,
V
.
V
.
B
a
s
k
a
r
,
M
.
V
a
d
i
v
e
l
,
S
.
P
.
V
i
ma
l
,
a
n
d
S
.
M
u
r
u
g
a
n
,
“
I
o
T
a
n
d
G
I
S
i
n
t
e
g
r
a
t
i
o
n
f
o
r
r
e
a
l
-
t
i
me
m
o
n
i
t
o
r
i
n
g
o
f
so
i
l
h
e
a
l
t
h
a
n
d
n
u
t
r
i
e
n
t
st
a
t
u
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
e
l
f
S
u
st
a
i
n
a
b
l
e
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
y
st
e
m
s
,
I
C
S
S
AS
2
0
2
3
-
Pro
c
e
e
d
i
n
g
s
,
p
p
.
1
2
6
5
–
1
2
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
S
A
S
5
7
9
1
8
.
2
0
2
3
.
1
0
3
3
1
6
9
4
.
[
1
2
]
S
.
K
.
S
.
D
u
r
a
i
a
n
d
M
.
D
.
S
h
a
mi
l
i
,
“
S
mart
f
a
r
mi
n
g
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
D
e
c
i
s
i
o
n
A
n
a
l
y
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
3
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
2
.
1
0
0
0
4
1
.
[
1
3
]
D
.
Tr
i
p
a
t
h
i
,
S
.
K
.
B
i
sw
a
s,
a
n
d
B
.
P
u
r
k
a
y
a
s
t
h
a
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s o
f
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
c
r
o
p
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
:
C
Y
P
ELA
,
”
i
n
2
0
2
3
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
(
I
3
C
S
)
,
M
a
r
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
3
C
S
5
8
3
1
4
.
2
0
2
3
.
1
0
1
2
7
2
6
8
.
[
1
4
]
S
.
K
.
M
o
d
i
,
C
h
a
h
a
t
,
A
.
L.
Y
a
d
a
v
,
P
.
S
.
R
a
n
a
,
a
n
d
K
a
l
p
a
n
a
,
“
I
n
n
o
v
a
t
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
s
o
i
l
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
c
r
o
p
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s,
I
C
C
I
C
A
,
p
p
.
5
0
2
–
5
0
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
C
A
6
0
0
1
4
.
2
0
2
4
.
1
0
5
8
5
0
0
3
.
[
1
5
]
B
.
S
h
a
d
a
k
sh
a
r
a
p
p
a
,
“
Ef
f
i
c
i
e
n
t
se
q
u
e
n
t
i
a
l
p
a
t
t
e
r
n
d
i
sc
o
v
e
r
y
w
i
t
h
P
r
e
f
i
x
S
p
a
n
f
o
r
l
a
r
g
e
-
s
c
a
l
e
d
a
t
a
a
n
a
l
y
t
i
c
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
o
d
e
rn
C
o
m
p
u
t
a
t
i
o
n
,
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
3
3
–
4
0
,
2
0
2
5
,
d
o
i
:
1
0
.
6
5
0
0
0
/
s
2
h
9
v
g
3
9
.
[
1
6
]
P
.
S
.
R
a
m
a
p
r
a
b
a
e
t
a
l
.
,
“
I
mp
l
e
m
e
n
t
i
n
g
c
l
o
u
d
c
o
m
p
u
t
i
n
g
i
n
d
r
u
g
d
i
sc
o
v
e
r
y
a
n
d
t
e
l
e
me
d
i
c
i
n
e
f
o
r
q
u
a
n
t
i
t
a
t
i
v
e
st
r
u
c
t
u
r
e
-
a
c
t
i
v
i
t
y
r
e
l
a
t
i
o
n
s
h
i
p
a
n
a
l
y
si
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
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
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
1
3
2
–
1
1
4
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
5
i
1
.
p
p
1
1
3
2
-
1
1
4
1
.
[
1
7
]
G
.
S
.
P
r
a
v
a
l
l
i
k
a
,
L.
K
u
n
d
a
n
a
,
K
.
S
.
T
h
a
n
v
i
,
G
.
S
i
r
i
s
h
a
,
a
n
d
C
.
R
u
p
a
,
“
P
r
o
f
i
c
i
e
n
t
smar
t
so
i
l
b
a
s
e
d
I
o
T
sy
s
t
e
m
f
o
r
c
r
o
p
p
r
e
d
i
c
t
i
o
n
,
”
Pro
c
e
e
d
i
n
g
s o
f
t
h
e
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
v
e
n
t
i
v
e
Re
s
e
a
rc
h
i
n
C
o
m
p
u
t
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s (I
C
I
RC
A)
,
p
p
.
7
5
2
–
7
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
R
C
A
4
8
9
0
5
.
2
0
2
0
.
9
1
8
3
0
5
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.