I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
3
5
6
8
~
3
5
8
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
5
6
8
-
3
5
8
0
3568
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Da
ta
-
driv
en ana
l
y
sis
of gro
wth
fac
tors
in
o
y
ster m
us
hro
o
m
cultiva
tion: a ca
se
study f
ro
m
Indo
nesia
’s
ma
rket
Yo
s
ef
B
ud
im
a
n
1
,
G
ila
ng
Adi
P
ra
s
et
y
o
2
,
Asm
a
’
K
ho
irunn
is
a
’
3
,
H
a
nifa
h M
a
r’
a
t
us
h Sh
a
lih
a
h
3
,
M
uh
a
m
a
d Riy
a
n M
a
ula
na
4
,
Ya
nu
a
r
Ag
un
g
F
a
dlu
lla
h
4
,
S
ug
iri
Su
g
iri
4
1
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
a
n
d
A
u
t
o
mo
t
i
v
e
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
V
o
c
a
t
i
o
n
a
l
S
t
u
d
i
e
s,
U
n
i
v
e
r
s
i
t
a
s Ne
g
e
r
i
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
2
S
t
a
t
i
st
i
c
s
S
t
u
d
y
P
r
o
g
r
a
m,
D
e
p
a
r
t
m
e
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
U
n
i
v
e
r
si
t
a
s
N
e
g
e
r
i
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
E
d
u
c
a
t
i
o
n
a
l
R
e
s
e
a
r
c
h
a
n
d
E
v
a
l
u
a
t
i
o
n
,
G
r
a
d
u
a
t
e
S
c
h
o
o
l
,
U
n
i
v
e
r
si
t
a
s
N
e
g
e
r
i
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
4
D
e
p
a
r
t
me
n
t
o
f
Te
c
h
n
o
l
o
g
y
a
n
d
V
o
c
a
t
i
o
n
a
l
Ed
u
c
a
t
i
o
n
,
G
r
a
d
u
a
t
e
S
c
h
o
o
l
,
U
n
i
v
e
r
s
i
t
a
s
N
e
g
e
r
i
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
14
,
2
0
2
5
R
ev
is
ed
J
u
l
11
,
2
0
2
6
Acc
ep
ted
J
u
l
21
,
2
0
2
6
Th
e
o
y
ste
r
m
u
sh
r
o
o
m
is o
n
e
o
f
th
e
p
o
ten
ti
a
l
a
g
ric
u
lt
u
ra
l
p
ro
d
u
c
ts t
h
a
t
c
a
n
b
e
d
e
v
e
lo
p
e
d
a
s
a
n
a
lt
e
r
n
a
ti
v
e
t
o
o
th
e
r
a
g
ricu
lt
u
ra
l
p
ro
d
u
c
ts,
t
o
m
a
in
tain
In
d
o
n
e
sia
'
s
e
c
o
n
o
m
ic
c
o
n
d
it
i
o
n
.
Ho
we
v
e
r,
th
e
p
ro
d
u
c
ti
o
n
o
f
o
y
ste
r
m
u
sh
ro
o
m
s
re
m
a
in
s
lo
w
a
n
d
fa
ll
s
sh
o
rt
o
f
t
h
e
m
in
imu
m
a
m
o
u
n
t
o
f
m
a
rk
e
t
d
e
m
a
n
d
.
Th
is
stu
d
y
e
m
p
lo
y
s
a
m
a
c
h
in
e
lea
rn
in
g
(M
L)
–
b
a
se
d
a
p
p
r
o
a
c
h
t
o
id
e
n
ti
f
y
th
e
k
e
y
p
a
ra
m
e
ters
in
flu
e
n
c
in
g
o
y
ste
r
m
u
sh
r
o
o
m
p
ro
d
u
c
t
io
n
ra
tes
.
Re
c
u
rsiv
e
fe
a
tu
re
e
li
m
in
a
ti
o
n
(
RF
E)
wa
s
a
p
p
li
e
d
to
re
d
u
c
e
th
e
in
it
ial
1
9
fe
a
tu
re
s to
n
i
n
e
,
e
n
a
b
li
n
g
fa
ste
r
p
ro
c
e
ss
in
g
wh
i
le m
a
in
tain
i
n
g
h
i
g
h
p
re
d
ictiv
e
a
c
c
u
ra
c
y
.
Th
e
re
su
lt
s
sh
o
we
d
th
a
t
a
g
r
icu
lt
u
ra
l
fe
a
tu
re
s
sh
o
we
d
a
h
i
g
h
c
o
n
tri
b
u
ti
o
n
ra
t
h
e
r
th
a
n
e
n
v
ir
o
n
m
e
n
tal,
e
c
o
n
o
m
ic,
a
n
d
d
e
m
o
g
ra
p
h
ic
fe
a
tu
re
s.
F
u
rt
h
e
rm
o
re
,
t
h
e
se
p
a
ra
m
e
ters
we
re
re
late
d
to
t
h
e
train
-
tes
t
a
n
a
ly
sis
to
v
isu
a
li
z
e
t
h
e
sta
ti
stica
l
a
n
a
ly
sis
sh
o
w
n
b
y
th
e
b
e
st
m
e
th
o
d
,
a
d
a
p
ti
v
e
b
o
o
st
in
g
(
Ad
a
Bo
o
st
)
,
with
c
o
e
ffi
c
ien
t
o
f
d
e
term
in
a
ti
o
n
(
R
2
)
,
m
e
a
n
sq
u
a
re
d
e
rro
r
(M
S
E),
a
n
d
m
e
a
n
a
b
so
l
u
te
e
rro
r
(M
AE)
v
a
lu
e
s
o
f
0
.
9
9
7
5
7
5
,
0
.
0
0
9
8
4
1
,
a
n
d
0
.
0
8
5
8
8
4
,
re
sp
e
c
ti
v
e
l
y
.
R
e
late
d
re
se
a
rc
h
re
lev
a
n
t
to
t
h
e
re
se
a
rc
h
fin
d
i
n
g
s
wa
s
a
n
a
ly
z
e
d
to
v
a
li
d
a
te
th
a
t
a
g
ricu
lt
u
ra
l
p
ro
d
u
c
t
fe
a
tu
re
s
a
ffe
c
t
th
e
d
e
c
li
n
e
o
f
o
y
ste
r
m
u
sh
r
o
o
m
p
ro
d
u
c
ti
o
n
.
Ot
h
e
r
su
p
p
o
rted
re
se
a
rc
h
c
o
n
d
u
c
ted
b
y
in
teg
ra
ti
n
g
re
a
l
-
ti
m
e
a
n
a
ly
sis
a
n
d
twin
d
ig
it
a
l
m
o
d
e
ls,
wh
ich
c
a
n
e
n
h
a
n
c
e
su
b
stra
te q
u
a
li
ty
.
K
ey
w
o
r
d
s
:
Ag
r
icu
ltu
r
al
p
r
o
d
u
ctio
n
Gr
o
wth
f
ac
to
r
s
Ma
ch
in
e
lear
n
in
g
Oy
s
ter
m
u
s
h
r
o
o
m
R
ec
u
r
s
iv
e
f
ea
tu
r
e
elim
in
atio
n
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
:
Yo
s
ef
B
u
d
im
an
Dep
ar
tm
en
t o
f
Me
ch
an
ical
an
d
Au
to
m
o
tiv
e
E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
Vo
ca
tio
n
al
Stu
d
ies
Un
iv
er
s
itas
Neg
er
i Y
o
g
y
ak
ar
t
a
Ma
n
d
u
n
g
Stre
et,
Pen
g
asih
,
Ku
lo
n
Pro
g
o
,
Yo
g
y
ak
ar
ta
5
5
6
5
2
,
I
n
d
o
n
esia
E
m
ail:
y
o
s
ef
b
u
d
im
a
n
.
2
0
2
0
@
s
tu
d
en
t.u
n
y
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
n
esia
h
as
b
ec
o
m
e
o
n
e
o
f
th
e
n
o
tab
le
co
n
tr
ib
u
to
r
s
to
th
e
cu
ltiv
atio
n
o
f
o
y
s
ter
m
u
s
h
r
o
o
m
s
(
P
leu
r
o
tu
s
o
s
tr
ea
tu
s
)
[
1
]
.
Oy
s
ter
m
u
s
h
r
o
o
m
s
ar
e
r
ec
o
g
n
iz
ed
f
o
r
th
eir
n
u
tr
itio
n
al
v
alu
e
,
r
elativ
ely
s
im
p
le
cu
ltiv
atio
n
m
et
h
o
d
s
,
an
d
ec
o
n
o
m
ic
p
o
ten
tial,
esp
ec
ially
f
o
r
s
m
all
to
m
ed
i
u
m
-
s
ca
le
f
a
r
m
er
s
[
2
]
.
Desp
ite
th
ese
f
av
o
r
a
b
le
co
n
d
itio
n
s
,
ac
co
r
d
in
g
to
th
e
R
eg
u
latio
n
o
f
th
e
Mi
n
is
ter
o
f
Villag
es,
Dev
elo
p
m
e
n
t
o
f
R
em
o
te
Ar
ea
s
,
an
d
T
r
an
s
m
ig
r
atio
n
No
.
2
o
f
2
0
1
6
o
n
th
e
in
d
ek
s
p
emb
a
n
g
u
n
a
n
d
esa
(
v
illag
e
d
ev
el
o
p
m
en
t
in
d
ex
)
,
th
e
m
o
s
t
wid
ely
cu
ltiv
ated
ag
r
ic
u
ltu
r
al
r
eso
u
r
ce
s
ar
e
r
ice,
ch
ilies
,
p
et
s
ai,
to
m
ato
es,
an
d
r
ed
o
n
i
o
n
s
[
3
]
.
T
h
is
co
n
d
itio
n
is
a
ch
allen
g
e
f
o
r
lo
ca
l
m
u
s
h
r
o
o
m
f
ar
m
er
s
to
m
ai
n
tain
t
h
eir
ec
o
n
o
m
ic
co
n
d
itio
n
.
I
n
r
esp
o
n
s
e
to
th
ese
ch
allen
g
es,
s
ev
er
al
r
esear
ch
em
p
lo
y
s
d
ata
-
d
r
i
v
en
m
eth
o
d
s
an
d
ad
v
an
c
ed
an
aly
tics
to
id
en
tify
th
e
k
ey
f
ac
to
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
a
n
a
lysi
s
o
f g
r
o
w
th
fa
cto
r
s
in
o
yster
mu
s
h
r
o
o
m
cu
ltiva
tio
n
:
a
c
a
s
e
s
tu
d
y
… (
Y
o
s
ef
B
u
d
ima
n
)
3569
lim
itin
g
y
ield
a
n
d
p
r
o
f
itab
ilit
y
.
Desp
ite
th
e
a
v
ailab
ilit
y
o
f
m
u
ltiv
ar
iate
ac
cu
r
ac
y
,
y
ield
p
r
ed
ictio
n
r
em
ain
s
ch
allen
g
in
g
d
u
e
to
d
ata
h
eter
o
g
en
eity
,
d
ata
n
o
is
e,
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
b
etwe
en
f
ac
to
r
s
(
f
ea
tu
r
e
r
elev
an
ce
)
,
an
d
ch
a
n
g
in
g
co
n
d
itio
n
s
th
at
r
ed
u
ce
m
o
d
el
g
en
e
r
aliza
b
ilit
y
[
4
]
.
Ad
v
an
ce
s
in
tech
n
o
lo
g
y
an
d
d
ata
an
aly
tics
h
av
e
b
eg
u
n
to
i
n
f
lu
en
ce
tr
a
d
itio
n
al
ag
r
icu
ltu
r
al
m
eth
o
d
s
as
ap
p
r
o
ac
h
es
to
in
v
esti
g
ate
a
n
d
in
f
o
r
m
d
ec
is
io
n
-
m
ak
in
g
.
R
elev
an
t
r
esear
ch
was
ca
r
r
ied
o
u
t
b
y
Sar
k
a
r
et
a
l
.
[
5
]
wh
o
ex
am
in
e
d
th
e
in
ter
n
a
l
f
ac
to
r
s
wh
ich
af
f
ec
t
o
y
s
ter
m
u
s
h
r
o
o
m
’
s
g
r
o
wth
c
u
ltiv
atio
n
,
in
clu
d
in
g
c
o
lo
r
f
ea
tu
r
es,
tex
tu
r
e,
co
n
t
r
ast,
en
er
g
y
,
an
d
h
o
m
o
g
en
eity
,
to
as
s
ess
th
e
s
tan
d
ar
d
an
d
q
u
ality
o
f
f
r
esh
p
r
o
d
u
ct
b
y
lev
er
ag
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
an
d
p
r
in
ci
p
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A)
.
B
ey
o
n
d
ANN
-
PC
A
ap
p
r
o
ac
h
es,
r
ec
en
t
wo
r
k
o
n
class
if
icatio
n
o
f
m
u
s
h
r
o
o
m
wh
ich
is
co
n
d
u
cted
b
y
Ku
m
ar
et
a
l
.
[
6
]
f
o
r
m
u
s
h
r
o
o
m
s
ex
t
r
ac
ted
h
an
d
-
cr
af
ted
g
r
a
y
-
lev
el
co
-
o
cc
u
r
r
en
ce
m
atr
ix
(
GL
C
M
)
tex
tu
r
e
f
ea
tu
r
es.
W
h
ile
v
alu
ab
le,
th
is
lin
e
o
f
wo
r
k
em
p
h
asizes
s
h
allo
w,
a
s
in
g
le
s
p
lit
(
n
o
k
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
/ex
ter
n
al
v
alid
atio
n
)
,
an
d
lack
s
m
o
d
el
in
ter
p
r
etab
ilit
y
th
at
lim
it
s
tab
ili
ty
.
Mo
r
eo
v
er
,
Ar
s
lan
et
a
l
.
[
7
]
also
ca
r
r
i
ed
o
u
t
s
u
p
er
v
is
ed
lear
n
in
g
o
f
o
y
s
ter
m
u
s
h
r
o
o
m
s
tu
d
y
,
p
ar
ticu
lar
ly
a
s
ep
ar
ate
tab
u
lar
ed
ib
ilit
y
b
en
ch
m
ar
k
c
o
m
p
ar
es
en
s
em
b
le
class
if
ier
s
o
n
th
e
clea
n
ed
Un
i
v
er
s
ity
o
f
C
alif
o
r
n
ia,
I
r
v
in
e
(
UC
I
)
m
u
s
h
r
o
o
m
d
ataset
u
s
in
g
a
b
r
o
ad
m
et
r
ic
s
u
ite,
b
u
t
f
ea
tu
r
es
co
n
f
in
ed
to
m
o
r
p
h
o
lo
g
y
/ed
ib
ilit
y
attr
ib
u
tes
r
ath
er
th
an
ag
r
o
n
o
m
ic
o
r
ec
o
n
o
m
ic
d
r
iv
er
s
o
f
cu
ltiv
atio
n
d
ec
is
io
n
s
.
B
r
id
g
in
g
th
e
g
a
p
s
f
r
o
m
p
r
ev
io
u
s
r
esear
ch
,
o
u
r
s
tu
d
y
aim
s
to
u
n
co
v
er
t
h
e
m
ain
f
ac
to
r
s
af
f
ec
tin
g
o
y
s
ter
m
u
s
h
r
o
o
m
p
r
o
d
u
ctio
n
,
p
ar
ticu
lar
ly
i
n
I
n
d
o
n
esia,
wi
th
m
u
ltiv
ar
iate
ag
r
icu
ltu
r
al,
e
n
v
ir
o
n
m
en
tal,
an
d
m
ar
k
et
co
v
a
r
iates;
em
p
lo
y
s
r
ec
u
r
s
iv
e
f
ea
tu
r
e
elim
in
atio
n
(
R
FE)
f
o
r
s
tab
le
f
ea
tu
r
e
s
elec
tio
n
;
u
s
es
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
f
o
r
r
eliab
ilit
y
;
an
d
p
r
o
v
id
es
ex
p
lain
ab
ilit
y
v
ia
Sh
a
p
ley
ad
d
itiv
e
ex
p
lan
atio
n
(
SHAP
)
an
d
p
ar
tial
d
ep
en
d
e
n
ce
p
lo
t
(
PDP
)
,
y
ield
in
g
tr
a
n
s
p
ar
en
t,
d
ec
is
i
o
n
-
o
r
ie
n
ted
in
s
ig
h
t.
T
h
e
r
esear
ch
ad
d
r
ess
es
th
ese
ch
allen
g
es
u
s
in
g
v
ar
io
u
s
en
s
e
m
b
le
m
o
d
els
wh
ich
a
r
e
d
ev
el
o
p
ed
as
a
s
tr
o
n
g
n
o
v
elty
.
Fu
r
t
h
er
m
o
r
e
,
th
is
s
tu
d
y
ex
ten
d
th
e
f
ea
tu
r
es
in
t
o
s
o
m
e
ex
ter
n
al
f
ac
to
r
s
,
s
u
ch
as
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
,
m
ar
k
et
d
e
m
an
d
s
,
an
d
m
ar
k
et
p
r
ice
in
d
icato
r
s
,
as
a
r
esear
ch
g
ap
.
T
h
is
ap
p
r
o
ac
h
o
f
f
e
r
s
in
s
ig
h
ts
in
to
h
o
w
d
ata
-
d
r
iv
en
s
tr
ateg
ies
ar
e
s
h
ap
in
g
th
e
f
u
tu
r
e
o
f
I
n
d
o
n
esia’
s
o
y
s
ter
m
u
s
h
r
o
o
m
in
d
u
s
tr
y
,
aim
in
g
t
o
o
p
tim
ize
y
ield
an
d
im
p
r
o
v
e
th
e
p
r
o
f
itab
ilit
y
o
f
f
ar
m
er
s
an
d
ag
r
i
p
r
en
e
u
r
s
in
r
u
r
al
ar
ea
s
in
I
n
d
o
n
esia.
T
h
r
o
u
g
h
th
is
s
tu
d
y
,
o
th
er
r
elev
an
t
s
tu
d
ies
ar
e
ex
am
in
ed
as
a
v
alid
atio
n
to
s
tr
en
g
t
h
en
a
n
d
s
u
p
p
o
r
t
th
e
r
esear
ch
.
I
n
th
is
co
n
tex
t,
a
r
tific
ial
in
tellig
en
ce
(
AI
)
f
o
r
ag
r
icu
ltu
r
e,
p
ar
ticu
lar
ly
m
ac
h
in
e
lear
n
in
g
(
ML
)
,
en
ab
les
ad
ap
tiv
e
lear
n
in
g
f
r
o
m
m
u
ltiv
ar
iate
d
ata
to
u
n
c
o
v
er
h
id
d
en
an
d
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
am
o
n
g
p
r
o
d
u
ctio
n
f
ac
to
r
s
[
8
]
.
T
h
e
in
teg
r
atio
n
o
f
R
FE
with
en
s
em
b
le
lear
n
in
g
r
ep
r
esen
ts
an
AI
-
d
r
iv
en
s
tr
ateg
y
th
at
s
y
s
tem
atica
lly
p
r
io
r
itizes
th
e
m
o
s
t
in
f
l
u
en
tial
ag
r
icu
ltu
r
a
l
in
d
icato
r
s
a
f
f
ec
tin
g
o
y
s
ter
m
u
s
h
r
o
o
m
y
ield
.
B
ey
o
n
d
its
tech
n
ical
co
n
tr
ib
u
tio
n
,
th
is
r
esear
ch
alig
n
s
wit
h
b
r
o
ad
e
r
AI
th
em
es
in
s
u
s
t
ain
ab
le
an
d
eth
ical
tech
n
o
lo
g
y
d
e
v
elo
p
m
e
n
t.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
ad
v
an
ce
s
p
r
ec
is
io
n
a
g
r
icu
ltu
r
e
an
d
s
u
s
tain
ab
ilit
y
-
o
r
ien
te
d
AI
b
y
en
ab
lin
g
m
o
r
e
ef
f
icien
t
r
eso
u
r
ce
u
s
e
an
d
s
u
p
p
o
r
tin
g
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
-
m
a
k
in
g
in
s
m
ar
t
f
ar
m
in
g
,
th
er
e
b
y
co
n
tr
ib
u
tin
g
to
lo
n
g
-
te
r
m
f
o
o
d
s
ec
u
r
ity
[
9
]
.
I
t a
ls
o
em
b
o
d
ies a
h
u
m
an
-
in
-
th
e
-
lo
o
p
ap
p
r
o
ac
h
,
wh
er
e
AI
o
u
tp
u
ts
ar
e
d
esig
n
ed
t
o
ass
is
t
r
ath
er
th
an
r
ep
lace
[
1
0
]
.
Fu
r
th
e
r
m
o
r
e,
th
e
i
n
co
r
p
o
r
atio
n
o
f
e
x
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
(
XAI
)
p
r
in
ci
p
le
s
s
tr
en
g
th
en
s
th
e
s
tu
d
y
’
s
co
n
tr
ib
u
tio
n
to
r
esp
o
n
s
ib
le
AI
b
y
p
r
o
m
o
tin
g
tr
an
s
p
ar
en
cy
,
ac
c
o
u
n
ta
b
ilit
y
,
an
d
f
air
n
ess
[
1
1
]
.
T
o
g
eth
e
r
,
th
e
s
e
elem
en
ts
s
i
tu
ate
th
e
r
esear
ch
with
in
th
e
g
lo
b
al
d
is
co
u
r
s
e
o
n
s
u
s
tain
ab
le
an
d
e
th
ical
AI
ap
p
licatio
n
s
.
2.
M
E
T
H
O
D
T
h
e
o
v
er
all
f
r
am
ewo
r
k
in
te
g
r
ates
th
ese
AI
d
im
en
s
io
n
s
t
h
r
o
u
g
h
o
u
t
th
e
r
esear
ch
wo
r
k
f
lo
w
with
in
ter
p
r
etab
ilit
y
an
al
y
s
is
as
a
m
o
d
u
lar
AI
p
ip
elin
e
f
o
r
cr
o
p
y
ield
p
r
e
d
ictio
n
as
s
h
o
wn
i
n
Fig
u
r
e
1
.
D
u
r
in
g
th
e
m
o
d
el
-
tr
ain
in
g
s
tag
e,
en
s
em
b
le
lear
n
in
g
alg
o
r
ith
m
s
ar
e
u
tili
ze
d
to
im
p
r
o
v
e
r
o
b
u
s
tn
ess
a
g
ain
s
t
v
ar
iatio
n
s
in
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
s
ea
s
o
n
al
p
atter
n
s
,
a
n
d
m
ar
k
et
d
y
n
am
ics.
I
n
th
e
i
n
ter
p
r
etatio
n
s
tag
e,
XAI
is
a
p
p
lie
d
th
r
o
u
g
h
SHAP
to
tr
an
s
p
a
r
e
n
tly
ass
ess
th
e
co
n
tr
ib
u
tio
n
o
f
ea
c
h
in
p
u
t
f
ea
tu
r
e
t
o
th
e
m
o
d
el
’
s
f
in
al
p
r
ed
ictio
n
[
1
2
]
.
PDPs
ar
e
also
em
p
lo
y
ed
to
esti
m
ate
th
e
m
ar
g
in
al
ef
f
ec
ts
o
f
in
d
iv
i
d
u
al
in
d
ep
en
d
en
t
v
ar
iab
les
o
n
th
e
p
r
ed
icted
o
u
tco
m
es
[
1
3
]
.
T
o
en
h
an
ce
m
o
d
el
r
eliab
ilit
y
an
d
g
en
er
aliza
b
ilit
y
,
cr
o
s
s
-
v
alid
atio
n
is
in
co
r
p
o
r
ated
th
r
o
u
g
h
o
u
t
th
e
tr
ain
in
g
an
d
v
alid
atio
n
p
r
o
ce
s
s
es.
T
h
is
co
n
f
ig
u
r
atio
n
e
n
s
u
r
es
f
u
ll
m
eth
o
d
o
lo
g
ical
tr
an
s
p
ar
en
cy
,
r
o
b
u
s
tn
ess
,
an
d
r
ep
r
o
d
u
cib
ilit
y
o
f
th
e
an
al
y
tical
p
ip
elin
e.
2
.
1
.
Da
t
a
prepro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
is
a
m
eth
o
d
to
p
r
e
p
ar
e
a
d
ataset
b
y
r
e
m
o
v
in
g
u
n
n
ec
ess
ar
y
f
ea
t
u
r
es,
ch
an
g
in
g
d
ata
ty
p
es,
a
n
d
h
an
d
lin
g
m
is
s
in
g
v
al
u
es.
Data
p
r
ep
r
o
c
ess
in
g
,
wh
ich
in
v
o
lv
es
d
ata
p
r
o
ce
s
s
in
g
,
is
ess
en
tial
to
en
s
u
r
e
an
ef
f
ec
tiv
e
lear
n
i
n
g
p
r
o
ce
s
s
.
T
h
is
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
in
v
o
l
v
es
clea
n
in
g
r
o
ws
a
n
d
co
lu
m
n
s
,
e
n
co
d
in
g
f
ea
tu
r
es,
n
o
r
m
alizin
g
th
e
d
ata,
an
d
ad
d
r
ess
in
g
m
is
s
in
g
v
alu
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
5
6
8
-
3
5
8
0
3570
Fig
u
r
e
1
.
Ar
c
h
itectu
r
al
d
iag
r
a
m
f
o
r
t
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
(
ML
-
p
ip
elin
e)
2
.
2
.
E
x
plo
ra
t
o
ry
da
t
a
a
na
l
y
s
is
E
x
p
lo
r
ato
r
y
d
ata
an
aly
s
is
(
E
DA)
is
a
cr
u
cial
s
tag
e
o
f
d
ata
an
aly
s
is
th
at
em
p
lo
y
s
s
tati
s
tical
an
d
v
is
u
aliza
tio
n
m
eth
o
d
s
to
in
v
esti
g
ate
d
atasets
,
id
en
tify
u
n
d
er
ly
i
n
g
p
atter
n
s
an
d
an
o
m
alies,
ev
alu
ate
h
y
p
o
th
eses
,
an
d
v
er
if
y
an
aly
t
ical
ass
u
m
p
tio
n
s
.
Desp
ite
its
u
s
ef
u
ln
ess
as
an
in
itial
an
aly
tical
to
o
l,
E
DA
is
g
en
er
ally
i
n
s
u
f
f
icien
t
f
o
r
estab
lis
h
in
g
ca
u
s
ality
o
r
f
u
lly
e
x
p
lain
in
g
co
m
p
lex
i
n
ter
ac
tio
n
s
a
m
o
n
g
v
ar
iab
les.
I
ts
f
in
d
in
g
s
s
h
o
u
ld
t
h
er
ef
o
r
e
b
e
s
u
p
p
o
r
ted
b
y
co
n
f
ir
m
ato
r
y
p
r
o
ce
d
u
r
es
a
n
d
m
o
r
e
r
o
b
u
s
t
s
tatis
tical
tech
n
iq
u
es
b
ef
o
r
e
f
ir
m
co
n
clu
s
io
n
s
ar
e
d
r
awn
.
Nev
er
t
h
eless
,
E
DA
r
em
ain
s
u
s
ef
u
l
f
o
r
u
n
co
v
er
in
g
th
e
s
tr
u
ctu
r
e
a
n
d
ch
ar
ac
ter
is
tics
o
f
a
d
ataset,
d
et
ec
tin
g
o
u
tlier
s
,
an
d
id
en
tif
y
in
g
p
o
ten
tially
in
f
lu
en
tial v
ar
iab
l
es.
2
.
3
.
H
ea
t
m
a
p c
o
rr
el
a
t
io
n
A
co
r
r
elatio
n
m
atr
i
x
is
a
s
tatis
tical
to
o
l
u
s
ed
to
ass
ess
th
e
d
ir
ec
tio
n
a
n
d
m
ag
n
itu
d
e
o
f
lin
ea
r
ass
o
ciatio
n
s
b
etwe
en
in
p
u
t
f
ea
tu
r
es
an
d
t
h
e
tar
g
et
v
ar
ia
b
le
[
1
4
]
.
E
ac
h
en
tr
y
in
th
e
m
atr
ix
co
n
tain
s
a
co
r
r
elatio
n
c
o
ef
f
icien
t,
co
m
m
o
n
ly
Pear
s
o
n
’
s
(
r
)
,
f
o
r
a
s
p
ec
i
f
ic
p
air
o
f
v
a
r
iab
les.
T
h
e
c
o
ef
f
icien
t
r
an
g
es
f
r
o
m
-
1
to
1
,
wh
er
e
p
o
s
itiv
e
v
alu
es
in
d
icate
th
at
t
h
e
v
ar
iab
les
ten
d
to
in
cr
ea
s
e
t
o
g
eth
er
,
n
e
g
ativ
e
v
alu
es
in
d
icate
a
n
in
v
er
s
e
r
elatio
n
s
h
ip
,
an
d
v
al
u
es
n
ea
r
ze
r
o
s
u
g
g
est
litt
le
o
r
n
o
lin
ea
r
ass
o
ciatio
n
.
B
y
a
n
al
y
zin
g
th
e
h
ea
t
m
ap
,
th
is
s
tu
d
y
id
en
tify
wh
ich
f
ea
tu
r
es
h
av
e
a
s
tr
o
n
g
p
o
s
itiv
e
o
r
n
eg
ativ
e
co
r
r
elatio
n
with
th
e
r
esp
o
n
s
e
v
ar
iab
le,
th
u
s
h
elp
in
g
i
n
f
ea
tu
r
e
s
elec
tio
n
an
d
e
n
g
in
ee
r
i
n
g
,
wh
ic
h
ca
n
af
f
ec
t m
o
d
el
p
er
f
o
r
m
an
ce
an
d
in
ter
p
r
etatio
n
.
2
.
4
.
Rec
urs
iv
e
f
ea
t
ures e
lim
ina
t
io
n
R
FE
is
a
wr
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
c
o
m
m
o
n
ly
ap
p
lied
t
o
id
e
n
tify
v
ar
iab
les
th
at
ar
e
m
o
s
t
s
tr
o
n
g
ly
ass
o
ciate
d
with
a
tar
g
et
o
u
tco
m
e,
in
clu
d
in
g
in
r
em
o
te
-
s
en
s
in
g
d
atasets
[
1
5
]
.
T
h
e
p
r
o
ce
d
u
r
e
r
ep
ea
ted
ly
f
its
th
e
p
r
ed
ictio
n
m
o
d
el,
r
an
k
s
th
e
f
ea
tu
r
es
ac
c
o
r
d
in
g
to
t
h
eir
esti
m
ated
im
p
o
r
tan
ce
o
r
co
e
f
f
icien
t
weig
h
ts
,
an
d
r
em
o
v
es
th
e
least
in
f
lu
en
tial
v
ar
iab
les
at
e
ac
h
iter
atio
n
.
T
h
r
o
u
g
h
th
is
iter
ativ
e
elim
in
atio
n
p
r
o
ce
s
s
,
R
FE
p
r
o
d
u
ce
s
an
o
p
ti
m
al
s
u
b
s
et
o
f
r
elev
a
n
t f
ea
tu
r
es
f
o
r
s
u
b
s
eq
u
en
t m
o
d
el
d
ev
elo
p
m
en
t.
2
.
5
.
M
o
del per
f
o
rma
nce
ev
a
lua
t
io
n
2
.
5
.
1
.
T
ra
in a
nd
t
est
T
h
e
p
e
r
f
o
r
m
an
ce
a
n
d
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
th
e
r
e
g
r
ess
io
n
m
o
d
el
we
r
e
ev
al
u
ated
u
s
in
g
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
MA
E
)
,
an
d
th
e
c
o
ef
f
icien
t o
f
d
eter
m
in
atio
n
(
R
2
)
.
T
h
ese
ev
alu
atio
n
m
etr
ics
wer
e
ap
p
lied
to
th
e
m
o
d
el
-
tr
ain
in
g
r
esu
lts
to
d
eter
m
in
e
h
o
w
clo
s
ely
th
e
p
r
ed
icted
v
alu
es
m
atch
ed
th
e
o
b
s
er
v
ed
d
ata.
Am
o
n
g
t
h
ese
m
ea
s
u
r
es,
MSE
ca
lcu
lates
th
e
av
er
a
g
e
s
q
u
a
r
ed
d
if
f
e
r
en
ce
b
etwe
en
ac
tu
al
an
d
p
r
ed
icted
v
alu
es.
B
ec
au
s
e
th
e
er
r
o
r
s
ar
e
s
q
u
ar
e
d
,
lar
g
er
p
r
ed
ictio
n
d
ev
iatio
n
s
r
ec
eiv
e
g
r
ea
ter
p
en
alties,
as
ex
p
r
ess
ed
in
(
1
)
.
Desire
d
v
al
u
e:
0
,
clo
s
er
is
b
etter
.
=
1
∑
(
−
)
2
=
1
(
1
)
On
th
e
o
th
er
h
an
d
,
MA
E
is
s
u
itab
le
wh
en
o
u
tlier
s
af
f
ec
t
a
s
p
ec
if
ic
s
u
b
s
et
o
f
d
ata,
as
it
d
o
es
n
o
t
p
en
alize
th
em
to
o
m
u
ch
d
u
r
in
g
tr
ain
in
g
.
As
a
r
esu
lt,
MA
E
o
f
f
er
s
a
g
en
er
al
an
d
lim
ited
p
er
f
o
r
m
a
n
ce
m
etr
ic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
a
n
a
lysi
s
o
f g
r
o
w
th
fa
cto
r
s
in
o
yster
mu
s
h
r
o
o
m
cu
ltiva
tio
n
:
a
c
a
s
e
s
tu
d
y
… (
Y
o
s
ef
B
u
d
ima
n
)
3571
f
o
r
e
v
alu
atin
g
m
o
d
els.
Ho
we
v
er
,
if
th
e
test
d
ata
s
till
co
n
t
ain
s
m
an
y
o
u
tlier
s
,
th
e
m
o
d
e
l
p
er
f
o
r
m
an
ce
m
a
y
r
em
ain
av
er
a
g
e,
as illu
s
tr
ated
i
n
(
2
)
.
Desire
d
v
alu
e:
0
,
clo
s
er
is
b
etter
.
=
1
∑
|
−
|
=
1
(
2
)
E
v
en
tu
ally
,
th
e
R
2
in
d
icate
s
th
e
p
r
o
p
o
r
tio
n
o
f
v
a
r
iab
ilit
y
in
t
h
e
d
ep
en
d
en
t v
a
r
iab
le
th
at
is
ac
co
u
n
ted
f
o
r
b
y
th
e
in
d
ep
en
d
en
t v
ar
ia
b
les,
as p
r
esen
ted
in
(
3
)
.
Desire
d
v
alu
e:
1
,
clo
s
er
is
b
etter
.
2
=
1
−
∑
(
−
)
2
=
1
∑
(
̅
−
)
2
=
1
(
3
)
I
n
th
is
f
o
r
m
u
latio
n
,
(
)
an
d
(
)
r
ep
r
esen
t
th
e
o
b
s
er
v
ed
an
d
p
r
e
d
icted
v
alu
es
o
f
th
e
r
esp
o
n
s
e
v
ar
iab
le
f
o
r
th
e
i
-
th
d
ata
p
o
in
t,
r
esp
ec
tiv
ely
.
T
h
e
d
ataset
is
co
m
m
o
n
l
y
p
ar
titi
o
n
ed
in
to
an
8
0
%
tr
ain
in
g
s
u
b
s
et
an
d
a
2
0
%
test
in
g
s
u
b
s
et,
allo
win
g
th
e
m
o
d
el
to
b
e
d
e
v
elo
p
e
d
o
n
o
n
e
p
o
r
tio
n
o
f
th
e
d
ata
an
d
ev
al
u
ated
o
n
p
r
ev
io
u
s
ly
u
n
s
ee
n
o
b
s
er
v
atio
n
s
.
2
.
5
.
2
.
M
o
del e
v
a
lua
t
io
n a
nd
s
ig
nifica
nce
Py
th
o
n
-
b
ased
alg
o
r
ith
m
s
ar
e
d
ev
elo
p
ed
to
e
n
ab
le
r
ap
id
p
r
ed
ictio
n
an
d
ev
alu
atio
n
u
s
in
g
v
ar
io
u
s
r
eg
r
ess
io
n
tech
n
iq
u
es.
T
h
es
e
r
eg
r
ess
io
n
m
eth
o
d
s
ar
e
ap
p
lied
t
o
esti
m
ate
ex
t
r
ap
o
lated
v
alu
es
f
r
o
m
ex
p
er
im
en
tal
d
ata.
I
n
r
ec
en
t
y
ea
r
s
,
v
ar
io
u
s
r
e
g
r
ess
io
n
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
in
tr
o
d
u
ce
d
,
e
ac
h
with
th
eir
o
wn
ch
ar
ac
ter
is
tics
an
d
wo
r
k
in
g
p
r
in
cip
les,
co
n
s
is
tin
g
o
f
s
ev
er
al
well
-
k
n
o
wn
m
eth
o
d
s
.
T
h
is
r
esear
ch
co
n
d
u
cted
a
s
tu
d
y
th
at
u
s
ed
s
ev
e
r
al
b
aselin
e
an
d
e
n
s
em
b
le
m
o
d
els
as
s
h
o
wn
in
T
ab
le
1
,
wh
er
e
ea
c
h
m
o
d
el
was
ch
o
s
en
d
u
e
to
its
u
n
iq
u
e
ch
ar
ac
ter
is
tics
.
Mo
r
eo
v
er
,
h
y
p
e
r
p
ar
am
e
ter
tu
n
in
g
was
ca
r
r
ied
o
u
t
p
er
f
o
r
m
e
d
f
o
r
ea
c
h
en
s
em
b
le
m
o
d
el
t
o
ac
h
iev
e
an
o
p
tim
al
b
alan
ce
b
etwe
en
b
ias
an
d
v
ar
ia
n
ce
u
s
in
g
g
r
id
/r
an
d
o
m
s
ea
r
ch
o
r
d
ef
au
lt
s
ettin
g
s
.
T
h
is
en
s
u
r
es
th
at
b
o
th
tr
ain
in
g
p
r
o
ce
s
s
es
u
n
d
er
d
if
f
er
e
n
t
co
n
d
itio
n
s
ar
e
p
er
f
o
r
m
ed
o
n
th
e
d
ataset
to
in
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
th
e
ML
m
o
d
el.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
en
s
e
m
b
le
m
o
d
els as a
b
e
n
ch
m
ar
k
s
tu
d
y
M
o
d
e
l
S
u
i
t
a
b
l
e
d
o
m
a
i
n
Tu
n
e
d
h
y
p
e
r
p
a
r
a
me
t
e
r
s
P
e
r
f
o
r
ma
n
c
e
b
e
h
a
v
i
o
r
s
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
Tr
a
d
i
t
i
o
n
a
l
a
g
r
o
n
o
m
y
[
1
6
]
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
(
)
(
d
e
f
a
u
l
t
s)
B
a
se
l
i
n
e
;
f
a
s
t
,
a
n
d
i
n
t
e
r
p
r
e
t
a
b
l
e
S
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
ML
-
b
a
se
d
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
[
1
7
]
S
V
R
(
k
e
r
n
e
l
=
'r
b
f
',
C
=
1
.
0
,
e
p
si
l
o
n
=
0
.
1
,
g
a
mm
a
=
's
c
a
l
e
')
H
a
n
d
l
e
s
n
o
n
l
i
n
e
a
r
i
t
y
a
n
d
sen
s
i
t
i
v
e
t
o
sca
l
i
n
g
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
ML
-
b
a
se
d
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
[
1
8
]
K
N
e
i
g
h
b
o
r
s
r
e
g
r
e
ss
o
r
(
n
_
n
e
i
g
h
b
o
r
s
=
5
,
w
e
i
g
h
t
s
=
'u
n
i
f
o
r
m',
m
e
t
r
i
c
=
'min
k
o
w
sk
i
',
p
=
2)
N
o
n
-
p
a
r
a
m
e
t
r
i
c
a
n
d
l
o
c
a
l
p
a
t
t
e
r
n
s
D
e
c
i
s
i
o
n
t
r
e
e
D
i
g
i
t
a
l
a
g
r
i
c
u
l
t
u
r
e
[
1
9
]
D
e
c
i
s
i
o
n
t
r
e
e
r
e
g
r
e
sso
r
(
m
a
x
_
d
e
p
t
h
=
5
,
r
a
n
d
o
m
_
s
t
a
t
e
=
42)
I
n
t
e
r
p
r
e
t
a
b
l
e
r
u
l
e
s
a
n
d
h
i
g
h
v
a
r
i
a
n
c
e
R
a
n
d
o
m f
o
r
e
s
t
ML
-
b
a
se
d
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
a
n
d
d
i
g
i
t
a
l
a
g
r
i
c
u
l
t
u
r
e
[
2
0
]
R
a
n
d
o
m
f
o
r
e
st
r
e
g
r
e
ss
o
r
(
n
_
e
st
i
ma
t
o
r
s
=
1
0
0
,
r
a
n
d
o
m
_
s
t
a
t
e
=
4
2
)
(
d
e
f
a
u
l
t
s:
max
_
d
e
p
t
h
=
n
o
n
e
,
m
a
x
_
f
e
a
t
u
r
e
s
=
'sq
r
t
')
R
o
b
u
st
t
o
n
o
i
s
e
a
n
d
g
o
o
d
o
u
t
-
of
-
b
a
g
(
O
O
B
)
e
st
i
ma
t
e
G
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
ML
-
b
a
se
d
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
[
2
1
]
G
r
a
d
i
e
n
t
b
o
o
st
i
n
g
r
e
g
r
e
s
so
r
(
n
_
e
st
i
ma
t
o
r
s
=
1
0
0
,
l
e
a
r
n
i
n
g
_
r
a
t
e
=
0
.
1
,
max
_
d
e
p
t
h
=
3
(
v
i
a
b
a
se
l
e
a
r
n
e
r
)
,
su
b
s
a
m
p
l
e
=
1
.
0
,
r
a
n
d
o
m
_
st
a
t
e
=
4
2
)
S
t
r
o
n
g
o
n
t
a
b
u
l
a
r
a
n
d
w
a
t
c
h
o
v
e
r
f
i
t
R
i
d
g
e
Tr
a
d
i
t
i
o
n
a
l
a
g
r
o
n
o
m
y
[
2
2
]
A
l
p
h
a
=
1
.
0
Li
n
e
a
r
,
i
n
t
e
r
p
r
e
t
a
b
l
e
a
n
d
r
o
b
u
st
t
o
m
u
l
t
i
c
o
l
l
i
n
e
a
r
i
t
y
El
a
s
t
i
c
N
e
t
Tr
a
d
i
t
i
o
n
a
l
a
g
r
o
n
o
m
y
[
2
2
]
A
l
p
h
a
=
1
.
0
,
l
1
_
r
a
t
i
o
=
0
.
5
A
d
a
p
t
i
v
e
b
o
o
st
i
n
g
(
A
d
a
B
o
o
st
)
ML
-
b
a
se
d
y
i
e
l
d
p
r
e
d
i
c
t
i
o
n
[
1
8
]
n
_
e
st
i
ma
t
o
r
s
=
5
0
,
r
a
n
d
o
m
_
st
a
t
e
=
42
(
b
a
se
l
e
a
r
n
e
r
≈
d
e
c
i
s
i
o
n
t
r
e
e
r
e
g
r
e
s
so
r
(
max
_
d
e
p
t
h
=
3
)
b
y
d
e
f
a
u
l
t
)
Tr
e
e
b
o
o
s
t
i
n
g
e
x
c
e
l
s
o
n
t
a
b
u
l
a
r
a
g
r
i
c
u
l
t
u
r
a
l
d
a
t
a
a
n
d
man
y
p
o
si
t
i
v
e
y
i
e
l
d
r
e
su
l
t
s
2
.
5
.
3
.
M
o
del lo
s
s
m
et
rics
Mo
d
el
lo
s
s
es
ar
e
p
lo
tted
to
m
o
n
ito
r
tr
ain
in
g
an
d
v
alid
ati
o
n
lo
s
s
es
ac
r
o
s
s
tim
e.
T
h
is
v
is
u
aliza
tio
n
m
ak
es
it
p
o
s
s
ib
le
to
ev
al
u
ate
th
e
c
o
n
v
e
r
g
en
ce
b
e
h
av
io
r
o
f
th
e
m
o
d
el
an
d
id
e
n
tify
p
r
o
b
lem
s
s
u
ch
as
u
n
d
er
f
itti
n
g
o
r
o
v
e
r
f
itti
n
g
.
L
o
s
s
f
u
n
ctio
n
s
q
u
an
tify
th
e
d
is
cr
ep
an
cy
b
etwe
en
a
m
o
d
el’
s
p
r
ed
ictio
n
s
an
d
th
e
ex
p
ec
ted
o
u
tp
u
ts
,
wh
er
ea
s
p
e
r
f
o
r
m
a
n
ce
m
etr
ics
ev
al
u
ate
h
o
w
ac
cu
r
ately
th
e
tr
ain
e
d
m
o
d
el
g
en
er
alize
s
to
p
r
ev
io
u
s
ly
u
n
s
ee
n
d
ata
[
2
3
]
.
A
s
tab
le
an
d
d
ec
r
ea
s
in
g
lo
s
s
cu
r
v
e
in
d
icate
s
ef
f
ec
tiv
e
le
ar
n
in
g
,
w
h
er
ea
s
a
d
is
tin
ct
g
ap
b
etwe
en
tr
ain
i
n
g
an
d
v
alid
atio
n
l
o
s
s
es
m
ay
s
ig
n
al
a
m
o
d
el
g
en
er
aliza
tio
n
p
r
o
b
lem
.
I
n
a
d
d
itio
n
,
m
o
d
el
er
r
o
r
is
ev
al
u
ated
b
y
v
is
u
alizin
g
th
e
r
esid
u
als,
wh
ic
h
r
ep
r
esen
t
th
e
d
if
f
er
en
ce
s
b
e
twee
n
th
e
o
b
s
er
v
ed
an
d
p
r
ed
icted
v
alu
es.
T
h
is
er
r
o
r
d
is
tr
ib
u
tio
n
p
lo
t
h
elp
s
in
u
n
d
er
s
tan
d
in
g
th
e
b
ias
an
d
v
ar
ian
ce
o
f
t
h
e
m
o
d
el
wh
ich
s
h
o
u
ld
b
e
s
y
m
m
etr
icall
y
d
is
tr
ib
u
ted
ar
o
u
n
d
ze
r
o
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
5
6
8
-
3
5
8
0
3572
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
co
ns
t
ruct
io
n
T
h
e
d
ataset
was p
r
ep
ar
ed
b
y
e
n
ter
in
g
ce
r
tain
v
alu
es,
m
o
s
t o
f
wh
ich
ca
n
b
e
f
o
u
n
d
o
n
th
e
B
ad
an
Pu
s
at
Statis
t
ik
Nasio
n
al
(
Natio
n
al
C
en
tr
al
B
u
r
ea
u
o
f
Statis
tics
)
web
s
ite.
Ho
wev
er
,
s
o
m
e
v
al
u
es
ar
e
d
if
f
icu
lt
to
d
is
ce
r
n
d
u
e
to
a
lack
o
f
d
at
a,
esp
ec
ially
d
u
r
in
g
C
OVI
D
-
1
9
,
wh
ich
h
alted
alm
o
s
t
all
ag
r
icu
ltu
r
al
s
ec
to
r
p
r
o
d
u
ctio
n
.
T
o
o
v
er
c
o
m
e
th
is
lim
itatio
n
,
th
e
au
th
o
r
s
lo
o
k
ed
f
o
r
o
th
er
s
o
u
r
ce
s
to
o
b
tain
s
in
g
le
a
n
d
m
u
ltiv
ar
iab
le
v
alu
es
th
at
co
u
l
d
b
e
ex
p
an
d
ed
u
s
in
g
th
e
b
o
o
t
s
tr
ap
f
ea
tu
r
e
o
f
th
e
Py
th
o
n
al
g
o
r
ith
m
.
W
ith
f
u
ll
co
n
s
id
er
atio
n
,
th
e
a
u
th
o
r
r
ed
u
ce
d
th
e
u
s
e
o
f
1
9
f
ea
tu
r
es
to
1
2
f
ea
tu
r
es
f
o
r
f
ast
p
r
o
ce
s
s
in
g
an
d
im
p
r
o
v
in
g
d
ata
ac
cu
r
ac
y
with
a
s
ize
o
f
1
2
×
6
0
,
m
ea
n
in
g
t
h
e
d
ataset
co
n
s
is
ts
o
f
1
2
co
lu
m
n
s
an
d
6
0
r
o
ws.
3
.
2
.
M
a
t
rix
co
rr
ela
t
i
o
n
T
h
e
h
ea
tm
a
p
m
atr
i
x
in
Fig
u
r
e
2
p
r
esen
ts
th
e
r
elatio
n
s
h
ip
b
e
twee
n
v
ar
io
u
s
en
v
ir
o
n
m
e
n
tal,
ec
o
n
o
m
ic,
d
em
o
g
r
a
p
h
ic,
an
d
ag
r
ic
u
ltu
r
a
l
v
ar
iab
les.
I
n
p
ar
ticu
lar
,
g
r
o
s
s
d
o
m
esti
c
p
r
o
d
u
ct
(
GDP
)
an
d
p
o
p
u
latio
n
ar
e
s
tr
o
n
g
ly
p
o
s
itiv
ely
co
r
r
elate
d
(
0
.
9
3
)
,
in
d
icatin
g
a
d
i
r
ec
t
r
elatio
n
s
h
ip
b
etwe
en
ec
o
n
o
m
ic
g
r
o
wth
a
n
d
p
o
p
u
latio
n
g
r
o
wth
.
Similar
ly
,
th
e
s
tr
o
n
g
p
o
s
itiv
e
co
r
r
elatio
n
b
etwe
en
GDP
an
d
k
ey
ag
r
ic
u
ltu
r
al
o
u
tp
u
ts
,
s
u
ch
as
cu
cu
m
b
e
r
p
r
o
d
u
ctio
n
(
0
.
9
4
)
an
d
r
e
d
o
n
io
n
p
r
o
d
u
ctio
n
(
0
.
9
4
)
,
im
p
ly
i
n
g
th
at
a
g
r
icu
ltu
r
al
p
r
o
d
u
ctiv
ity
ca
n
s
ig
n
if
ican
tly
in
f
lu
e
n
ce
o
r
r
e
f
lect
ec
o
n
o
m
ic
co
n
d
itio
n
s
.
I
n
co
n
tr
ast,
m
ar
k
et
d
em
an
d
s
h
o
ws
a
n
eg
ativ
e
co
r
r
elatio
n
with
GDP
(
-
0
.
8
5
)
an
d
ex
c
h
an
g
e
r
ate
(
-
0
.
8
5
)
,
wh
ich
m
ay
r
ef
lect
m
a
r
k
et
f
l
u
ctu
a
tio
n
s
o
r
th
e
ef
f
ec
ts
o
f
in
f
latio
n
o
n
p
u
r
ch
asin
g
p
o
wer
.
E
n
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
s
u
ch
as
C
O
an
d
C
O
2
s
h
o
w
n
e
g
ativ
e
co
r
r
elatio
n
s
with
GDP
an
d
ag
r
icu
ltu
r
al
v
ar
iab
les,
h
ig
h
lig
h
tin
g
th
e
p
o
ten
tial
ad
v
er
s
e
ef
f
ec
ts
o
f
air
p
o
llu
tio
n
o
n
p
r
o
d
u
ctiv
ity
.
Ov
er
all,
th
is
co
r
r
elatio
n
an
aly
s
is
p
r
o
v
id
es
im
p
o
r
tan
t
in
s
ig
h
ts
in
to
th
e
in
ter
d
e
p
en
d
en
ce
b
etwe
en
en
v
ir
o
n
m
en
tal
q
u
ality
,
ec
o
n
o
m
ic
in
d
icato
r
s
,
an
d
ag
r
icu
ltu
r
al
p
r
o
d
u
ctiv
ity
,
s
u
g
g
esti
n
g
ar
ea
s
f
o
r
tar
g
eted
p
o
licy
in
ter
v
e
n
tio
n
s
an
d
s
u
s
tain
ab
le
d
ev
el
o
p
m
en
t.
Fig
u
r
e
2
.
Hea
tm
ap
m
atr
ix
o
f
f
ea
tu
r
es a
n
d
tar
g
et
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
a
n
a
lysi
s
o
f g
r
o
w
th
fa
cto
r
s
in
o
yster
mu
s
h
r
o
o
m
cu
ltiva
tio
n
:
a
c
a
s
e
s
tu
d
y
… (
Y
o
s
ef
B
u
d
ima
n
)
3573
3
.
3
.
F
e
a
t
ure
s
co
re
Prio
r
to
c
o
n
d
u
ctin
g
f
u
r
th
e
r
a
n
aly
s
es,
R
FE
was
ch
o
s
en
as
a
to
o
l
to
id
en
tif
y
th
e
m
o
s
t
in
f
o
r
m
ativ
e
v
ar
iab
les.
T
welv
e
ca
n
d
id
ate
f
ea
tu
r
es
wer
e
ev
alu
ated
t
o
d
ete
r
m
in
e
th
e
ac
c
u
r
ac
y
s
co
r
e
b
ase
d
o
n
t
h
e
an
aly
s
is
o
f
v
ar
ian
ce
(
ANOV
A)
s
co
r
e
.
T
h
e
o
b
jectiv
e
was
to
o
b
tain
an
o
p
tim
al
f
ea
tu
r
e
co
m
b
in
at
io
n
f
o
r
th
e
b
in
a
r
y
in
tr
u
s
io
n
-
class
if
icatio
n
task
.
Su
r
p
r
is
in
g
ly
,
th
e
ac
c
u
r
ac
y
r
e
co
v
er
s
s
h
ar
p
ly
at
th
e
n
u
m
b
e
r
o
f
f
ea
tu
r
es
9
,
t
h
en
f
lu
ctu
ates
m
o
d
er
ately
as
s
h
o
wn
in
T
ab
le
2
.
A
n
o
ticea
b
le
d
r
o
p
o
cc
u
r
s
u
p
to
1
9
d
u
e
to
o
v
er
f
itti
n
g
o
r
t
h
e
in
clu
s
io
n
o
f
v
er
y
d
etr
im
en
tal
f
ea
tu
r
es.
T
h
is
f
in
d
in
g
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
d
elib
e
r
ate
f
ea
tu
r
e
s
elec
tio
n
,
s
in
ce
in
cr
ea
s
in
g
th
e
n
u
m
b
er
o
f
in
p
u
t
v
ar
iab
les
d
o
es n
o
t
n
ec
ess
ar
ily
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
B
ased
o
n
T
a
b
le
2
,
th
e
o
p
tim
u
m
f
ea
tu
r
es a
r
e
n
in
e
th
at
s
h
o
w
ce
r
tain
ac
cu
r
ac
y
an
d
ANOV
A
s
co
r
e
v
alu
es a
r
e
s
h
o
wn
in
T
ab
le
3
.
T
ab
le
3
co
m
p
lem
en
ts
th
is
an
aly
s
is
b
y
id
en
tify
in
g
th
e
n
i
n
e
m
o
s
t
in
f
lu
en
tial
f
ea
tu
r
es
b
ased
o
n
ANOV
A
s
co
r
es,
a
s
tatis
tical
m
ea
s
u
r
e
u
s
ed
t
o
ass
ess
th
e
d
is
cr
im
in
ato
r
y
p
o
wer
o
f
ea
ch
f
ea
tu
r
e.
T
o
m
ato
p
r
o
d
u
ctio
n
h
ad
th
e
h
i
g
h
est
ANOV
A
s
co
r
e
(
5
3
8
.
7
4
)
,
f
o
llo
wed
b
y
r
ed
o
n
io
n
p
r
o
d
u
c
tio
n
(
3
1
7
.
1
4
)
a
n
d
cu
cu
m
b
er
p
r
o
d
u
ctio
n
(
6
5
.
4
1
)
,
in
d
icatin
g
th
ese
ag
r
icu
ltu
r
a
l
v
ar
iab
les
co
n
tr
ib
u
te
d
th
e
m
o
s
t
to
p
r
ed
ictio
n
ac
cu
r
ac
y
.
E
n
v
ir
o
n
m
e
n
tal,
ec
o
n
o
m
ic,
an
d
d
em
o
g
r
a
p
h
ic
f
ea
t
u
r
es
h
ad
lo
wer
ANOV
A
s
co
r
es,
in
d
icatin
g
th
at
th
ey
wer
e
less
p
r
ed
ictiv
e
i
n
t
h
is
co
n
tex
t.
T
h
e
s
elec
tio
n
o
f
th
ese
to
p
n
in
e
f
ea
tu
r
es
ap
p
ea
r
s
to
alig
n
with
th
e
ac
cu
r
ac
y
im
p
r
o
v
em
en
ts
s
ee
n
in
T
ab
le
2
,
r
ein
f
o
r
cin
g
th
e
cr
itical
r
o
le
o
f
f
ea
tu
r
e
s
ele
ctio
n
in
o
p
tim
izin
g
p
r
ed
ictiv
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
ab
le
2
.
C
er
tain
v
alu
e
o
f
d
ataset
ac
cu
r
ac
y
b
y
u
s
in
g
s
ev
er
al
f
ea
tu
r
es
N
u
mb
e
r
o
f
se
l
e
c
t
i
o
n
s
A
c
c
u
r
a
c
y
o
f
d
a
t
a
se
t
1
f
e
a
t
u
r
e
0
.
9
4
4
1
2
f
e
a
t
u
r
e
s
0
.
8
8
4
1
9
f
e
a
t
u
r
e
s
0
.
9
2
6
6
1
9
f
e
a
t
u
r
e
s
0
.
7
8
8
3
T
ab
le
3
.
ANOV
A
s
co
r
e
b
y
R
FE
u
s
in
g
n
in
e
f
ea
tu
r
es
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
A
N
O
V
A
sco
r
e
C
o
n
t
r
i
b
u
t
i
o
n
CO
1
2
.
2
4
Le
a
s
t
CO
2
7
.
8
0
Le
a
s
t
C
h
i
l
i
p
r
o
d
u
c
t
i
o
n
4
5
.
9
9
M
e
d
i
u
m
C
u
c
u
m
b
e
r
p
r
o
d
u
c
t
i
o
n
6
5
.
4
1
M
e
d
i
u
m
GDP
9
.
8
0
Le
a
s
t
M
a
r
k
e
t
d
e
ma
n
d
1
5
.
7
9
Le
a
s
t
P
o
p
u
l
a
t
i
o
n
8
.
5
4
Le
a
s
t
R
e
d
o
n
i
o
n
p
r
o
d
u
c
t
i
o
n
3
1
7
.
1
4
M
o
s
t
To
ma
t
o
p
r
o
d
u
c
t
i
o
n
5
3
8
.
7
4
M
o
s
t
3
.
4
.
Co
m
pa
riso
n o
f
diff
er
en
t
m
o
del per
f
o
r
m
a
nce
As
s
u
m
m
ar
ized
in
T
a
b
le
4
,
Ad
aBo
o
s
t
d
em
o
n
s
tr
ated
th
e
s
tr
o
n
g
est
r
e
g
r
ess
io
n
m
o
d
el
p
e
r
f
o
r
m
a
n
ce
.
C
o
m
p
ar
ed
with
th
e
b
aselin
e
m
o
d
els
(
lin
ea
r
r
eg
r
ess
io
n
an
d
r
id
g
e
r
eg
r
ess
io
n
)
th
e
Ad
aBo
o
s
t
en
s
em
b
le
d
em
o
n
s
tr
ated
m
ar
k
e
d
ly
s
u
p
e
r
io
r
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics.
On
th
e
t
est
s
et,
Ad
aBo
o
s
t
ac
h
iev
ed
a
n
R
2
o
f
0
.
9
9
7
5
7
5
,
an
MA
E
o
f
0
.
0
8
5
8
8
4
,
a
n
d
a
MSE
o
f
0
.
0
0
9
8
4
1
,
s
u
b
s
tan
tially
o
u
tp
e
r
f
o
r
m
in
g
lin
ea
r
r
eg
r
ess
io
n
(R
2
=
0
.
8
2
8
7
2
5
;
MA
E
=
0
.
4
0
9
9
0
5
;
an
d
MSE
=
0
.
6
9
5
0
7
5
)
an
d
r
id
g
e
r
eg
r
ess
io
n
(R
2
=
0
.
9
8
8
3
3
5
;
MA
E
=
0
.
1
7
9
7
8
0
;
an
d
MSE
=
0
.
0
4
7
3
3
9
)
.
T
o
s
tatis
tically
v
er
if
y
t
h
at
m
o
d
el
p
e
r
f
o
r
m
an
ce
d
if
f
er
en
ce
s
wer
e
n
o
t
d
u
e
t
o
r
an
d
o
m
v
ar
iatio
n
,
9
5
%
co
n
f
id
en
ce
in
ter
v
al
s
(
C
I
)
wer
e
ca
lcu
lated
f
o
r
ea
c
h
ev
alu
atio
n
m
etr
ic
(
MSE
,
MA
E
,
an
d
R
2
)
u
s
in
g
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
r
esu
ltin
g
n
ar
r
o
w
in
te
r
v
als
(
av
er
ag
e
±
0
.
0
2
)
i
n
d
icate
s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
f
o
ld
s
.
Fu
r
th
er
m
o
r
e,
a
p
ai
r
ed
-
s
am
p
les
t
-
test
was
p
er
f
o
r
m
ed
to
e
v
alu
ate
wh
et
h
e
r
Ad
aBo
o
s
t
d
i
f
f
er
ed
s
ig
n
if
ica
n
tly
f
r
o
m
th
e
b
aselin
e
m
o
d
el
s
(
lin
ea
r
r
eg
r
ess
io
n
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
)
.
T
h
e
test
co
n
f
ir
m
e
d
th
at
Ad
aBo
o
s
t’
s
im
p
r
o
v
em
e
n
t
in
p
r
e
d
ictiv
e
ac
cu
r
ac
y
was
s
tatis
t
ically
s
ig
n
if
ican
t
α
=
1
0
%)
f
o
r
all
th
r
ee
m
etr
ics
(
p
=
0
.
0
6
9
6
;
p
=
0
.
0
9
9
3
;
an
d
p
=
0
.
0
6
5
0
)
,
v
alid
atin
g
th
at
th
e
o
b
s
er
v
e
d
d
if
f
er
en
ce
s
wer
e
n
o
t a
ttrib
u
ta
b
le
to
s
am
p
li
n
g
n
o
is
e.
Fu
r
th
er
m
o
r
e
,
Fig
u
r
e
3
p
r
esen
ts
p
lo
ts
co
m
p
ar
in
g
ac
tu
al
v
er
s
u
s
p
r
ed
icted
v
alu
es
f
o
r
d
if
f
e
r
en
t
r
eg
r
ess
io
n
m
o
d
els.
T
h
e
d
ata
p
o
in
ts
(
b
ef
o
r
e
a
n
d
a
f
ter
R
FE)
clu
s
ter
n
ea
r
th
e
d
ia
g
o
n
al
a
cr
o
s
s
m
o
s
t
m
o
d
els,
in
d
icatin
g
g
o
o
d
p
r
e
d
ictiv
e
ac
c
u
r
ac
y
o
v
er
all.
Am
o
n
g
all
m
o
d
els,
Ad
aBo
o
s
t
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
s
s
h
o
w
th
e
h
ig
h
est
co
n
s
is
ten
cy
,
with
p
r
e
d
ictio
n
s
tig
h
tly
g
r
o
u
p
ed
with
i
n
th
e
±
0
.
5
b
a
n
d
.
R
an
d
o
m
f
o
r
est
an
d
E
last
icNe
t
also
p
er
f
o
r
m
well,
with
o
n
ly
s
lig
h
t
d
is
p
er
s
io
n
at
th
e
e
x
tr
em
es.
I
n
c
o
n
tr
ast,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
e
x
h
ib
its
s
y
s
tem
atic
b
ias
an
d
lar
g
e
s
ca
tter
awa
y
,
in
d
icatin
g
th
at
it
f
ail
s
to
ca
p
tu
r
e
th
e
r
esp
o
n
s
e
r
elia
b
ly
f
o
r
t
h
is
d
ataset.
Me
an
wh
ile,
d
ec
is
io
n
tr
ee
s
ex
h
ib
it h
ig
h
v
ar
ian
ce
,
with
a
m
u
c
h
wid
er
d
is
tr
ib
u
tio
n
th
a
n
en
s
e
m
b
le
m
eth
o
d
s
.
T
h
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
5
6
8
-
3
5
8
0
3574
is
ad
d
r
ess
ed
b
y
e
n
s
em
b
le
m
et
h
o
d
s
(
r
a
n
d
o
m
f
o
r
est,
g
r
ad
ie
n
t
b
o
o
s
tin
g
,
an
d
Ad
aBo
o
s
t)
wh
i
ch
r
ed
u
ce
v
ar
ia
n
ce
an
d
im
p
r
o
v
e
g
en
er
aliza
tio
n
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
r
eg
r
es
s
io
n
m
o
d
els b
ased
o
n
p
er
f
o
r
m
an
ce
m
etr
ics
M
o
d
e
l
p
e
r
f
o
r
ma
n
c
e
B
e
f
o
r
e
o
p
t
i
m
i
z
a
t
i
o
n
A
f
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
M
S
E
M
A
E
R
2
M
S
E
M
A
E
R
2
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
0
.
4
6
2
6
3
1
0
.
4
4
7
1
0
1
0
.
8
3
7
9
7
4
0
.
6
9
5
0
7
5
0
.
4
0
9
9
0
5
0
.
8
2
8
7
2
5
R
i
d
g
e
r
e
g
r
e
ss
i
o
n
0
.
0
6
5
0
9
4
0
.
1
8
9
2
7
8
0
.
9
7
7
2
0
2
0
.
0
4
7
3
3
9
0
.
1
7
9
7
8
0
0
.
9
8
8
3
3
5
El
a
s
t
i
c
N
e
t
0
.
0
1
3
6
3
9
0
.
0
9
6
6
3
9
0
.
9
9
5
2
2
3
0
.
0
1
6
3
1
9
0
.
1
1
8
0
7
4
0
.
9
9
5
9
7
9
G
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
0
.
0
3
8
3
2
9
0
.
1
2
1
3
7
0
0
.
9
8
6
5
7
6
0
.
0
3
7
6
6
8
0
.
1
3
2
7
9
7
0
.
9
9
0
7
1
8
R
a
n
d
o
m f
o
r
e
s
t
0
.
0
1
1
7
2
1
0
.
0
8
4
7
5
8
0
.
9
9
5
8
9
5
0
.
0
1
4
6
0
6
0
.
1
0
0
5
9
5
0
.
9
9
6
4
0
1
S
u
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
2
.
5
0
4
1
9
6
0
.
8
8
0
2
4
6
0
.
1
2
2
9
6
2
3
.
8
4
7
4
3
0
1
.
2
8
4
7
2
6
0
.
0
5
1
9
4
3
D
e
c
i
s
i
o
n
t
r
e
e
0
.
0
8
5
1
5
9
0
.
1
5
1
3
0
1
0
.
9
7
0
1
7
5
0
.
2
1
5
1
6
2
0
.
2
5
6
3
4
8
0
.
9
4
6
9
8
1
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
0
.
0
1
1
7
2
0
0
.
0
8
3
8
6
8
0
.
9
9
5
8
9
5
0
.
0
1
1
9
6
3
0
.
0
8
5
7
7
1
0
.
9
9
7
0
5
2
A
d
a
B
o
o
st
0
.
0
0
9
8
6
8
0
.
0
8
0
5
0
6
0
.
9
9
6
5
4
4
0
.
0
0
9
8
4
1
0
.
0
8
5
8
8
4
0
.
9
9
7
5
7
5
Fig
u
r
e
3
.
Actu
al
v
er
s
u
s
p
r
ed
ic
tio
n
v
alu
es o
f
o
y
s
ter
m
u
s
h
r
o
o
m
p
r
o
d
u
ctio
n
t
h
r
o
u
g
h
all
m
o
d
els
T
h
e
h
i
g
h
R
2
v
a
l
u
e
s
ac
r
o
s
s
e
n
s
e
m
b
l
e
m
o
d
e
l
s
(
p
ar
t
i
c
u
la
r
ly
A
d
a
B
o
o
s
t
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
)
i
n
d
i
c
a
t
e
t
h
a
t
th
e
v
ar
i
an
c
e
i
n
o
y
s
t
e
r
m
u
s
h
r
o
o
m
p
r
o
d
u
c
t
io
n
i
s
p
r
ed
o
m
in
an
t
l
y
e
x
p
l
a
in
e
d
b
y
a
g
r
i
c
u
l
tu
r
a
l
v
a
r
i
ab
l
e
s
r
a
t
h
er
th
an
b
y
en
v
i
r
o
n
m
e
n
ta
l
o
r
e
c
o
n
o
m
i
c
f
a
c
to
r
s
.
T
h
i
s
f
i
n
d
i
n
g
s
u
g
g
e
s
t
s
t
h
a
t
m
u
s
h
r
o
o
m
y
i
e
ld
d
y
n
am
i
c
s
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
a
n
a
lysi
s
o
f g
r
o
w
th
fa
cto
r
s
in
o
yster
mu
s
h
r
o
o
m
cu
ltiva
tio
n
:
a
c
a
s
e
s
tu
d
y
… (
Y
o
s
ef
B
u
d
ima
n
)
3575
I
n
d
o
n
e
s
i
a
a
r
e
h
ig
h
ly
s
en
s
i
t
i
v
e
t
o
th
e
p
r
o
d
u
c
t
i
v
it
y
o
f
c
o
m
p
l
e
m
en
t
a
r
y
cr
o
p
s
s
u
ch
a
s
to
m
a
t
o
,
c
h
i
l
i,
an
d
r
ed
o
n
i
o
n
,
w
h
i
ch
s
h
a
r
e
s
i
m
i
l
ar
in
p
u
t
r
e
s
o
u
r
c
e
s
an
d
s
e
a
s
o
n
a
l
c
y
c
l
e
s
.
T
h
e
s
t
r
o
n
g
p
r
ed
i
c
t
i
v
e
a
l
i
g
n
m
en
t
ac
r
o
s
s
f
o
l
d
s
a
l
s
o
r
e
f
le
c
t
s
m
o
d
e
l
r
o
b
u
s
t
n
e
s
s
,
m
e
an
i
n
g
t
h
a
t
th
e
p
att
e
r
n
s
i
d
en
t
i
f
ie
d
a
r
e
n
o
t
r
an
d
o
m
a
r
t
i
f
ac
t
s
o
f
d
a
t
a
s
a
m
p
l
i
n
g
b
u
t
co
n
s
i
s
t
e
n
t
r
e
la
ti
o
n
s
h
ip
s
th
a
t
g
e
n
e
r
a
l
i
ze
ac
r
o
s
s
r
e
g
io
n
s
.
T
h
i
s
i
n
te
r
p
r
e
t
a
t
io
n
a
l
ig
n
s
w
i
t
h
t
h
e
n
o
t
io
n
t
h
a
t
a
g
r
i
c
u
l
tu
r
a
l
c
o
-
m
o
v
em
e
n
t
s
an
d
cr
o
p
i
n
t
er
d
ep
e
n
d
en
c
i
e
s
f
o
r
m
a
k
ey
s
t
r
u
c
tu
r
a
l
co
m
p
o
n
e
n
t
o
f
r
u
r
al
p
r
o
d
u
c
t
i
o
n
s
y
s
t
em
s
.
H
en
c
e
,
t
h
e
m
o
d
e
l’
s
p
e
r
f
o
r
m
a
n
ce
n
o
t
o
n
ly
d
e
m
o
n
s
t
r
a
t
e
s
co
m
p
u
t
a
t
io
n
a
l
a
c
cu
r
ac
y
b
u
t
a
l
s
o
s
u
p
p
o
r
t
s
a
s
u
b
s
t
an
t
i
v
e
ag
r
o
n
o
m
i
c
in
t
e
r
p
r
e
t
at
io
n
l
i
n
k
i
n
g
i
n
te
r
-
c
r
o
p
b
e
h
av
i
o
r
t
o
m
u
s
h
r
o
o
m
y
i
e
l
d
p
r
e
d
i
c
t
ab
i
l
i
ty
.
T
o
ass
ess
th
e
m
o
d
el’
s
f
ea
s
i
b
ilit
y
,
its
tr
ain
in
g
a
n
d
v
alid
atio
n
p
e
r
f
o
r
m
an
ce
was
m
o
n
i
to
r
ed
o
v
er
5
0
ep
o
ch
s
u
s
in
g
MSE
a
n
d
M
AE
,
as
illu
s
tr
ated
in
Fig
u
r
e
4
.
T
h
e
MSE
p
lo
t
i
n
Fig
u
r
e
4
(
a)
s
h
o
ws
a
s
tead
y
an
d
co
n
s
is
ten
t
d
ec
r
ea
s
e
in
th
e
tr
ain
in
g
a
n
d
v
alid
atio
n
lo
s
s
es,
with
co
n
v
er
g
en
ce
o
b
s
er
v
ed
ar
o
u
n
d
ep
o
ch
2
0
.
B
ey
o
n
d
th
is
s
tag
e,
th
e
MSE
d
ec
r
ea
s
es
to
n
ea
r
ly
ze
r
o
an
d
r
e
m
ain
s
r
elativ
ely
s
tab
le,
s
u
g
g
e
s
tin
g
th
at
th
e
m
o
d
el
h
as
ef
f
ec
tiv
ely
ca
p
tu
r
ed
t
h
e
u
n
d
er
ly
in
g
d
ata
p
atter
n
s
with
o
u
t
ex
h
ib
itin
g
s
u
b
s
tan
tial
o
v
er
f
it
tin
g
.
Mo
r
eo
v
er
,
th
e
v
alid
atio
n
lo
s
s
co
n
s
is
ten
tly
tr
ac
k
s
th
e
tr
ain
in
g
lo
s
s
th
r
o
u
g
h
o
u
t
th
e
ep
o
ch
s
,
in
d
icatin
g
s
tr
o
n
g
g
en
er
aliza
tio
n
to
p
r
ev
io
u
s
ly
u
n
s
ee
n
d
ata.
Similar
ly
,
th
e
MA
E
p
lo
t
in
Fig
u
r
e
4
(
b
)
r
ef
lects
a
d
ec
r
ea
s
in
g
tr
en
d
in
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
er
r
o
r
s
,
with
a
s
h
ar
p
d
ec
lin
e
u
n
til
ar
o
u
n
d
ep
o
c
h
2
0
.
B
ey
o
n
d
th
is
p
o
in
t,
t
h
e
MA
E
v
alu
es
r
ea
ch
a
p
latea
u
an
d
s
h
o
w
m
in
im
al
f
lu
ctu
atio
n
,
f
u
r
th
er
in
d
icatin
g
co
n
v
er
g
e
n
ce
.
T
h
e
clo
s
e
co
r
r
esp
o
n
d
en
ce
b
etwe
en
th
e
tr
ain
in
g
an
d
v
alid
atio
n
MA
E
cu
r
v
es
d
em
o
n
s
tr
ates
th
at
th
e
AI
/ML
m
o
d
el
p
r
eser
v
es
s
tr
o
n
g
p
r
ed
ictiv
e
ca
p
ab
ilit
y
o
n
th
e
c
r
o
s
s
-
v
alid
a
tio
n
s
et.
T
h
e
co
n
s
is
ten
tly
lo
w
f
in
al
er
r
o
r
v
alu
es
f
u
r
th
e
r
c
o
n
f
ir
m
th
e
m
o
d
el’
s
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
in
r
eg
r
ess
io
n
an
d
f
o
r
ec
asti
n
g
ap
p
licatio
n
s
.
(
a)
(
b
)
Fig
u
r
e
4
.
Mo
d
el
lo
s
s
f
u
n
ctio
n
s
of
(
a)
MSE
an
d
(
b
)
MA
E
Featu
r
e
ef
f
ec
ts
wer
e
in
ter
p
r
eted
u
s
in
g
SHAP
to
ex
p
lain
th
e
en
s
em
b
le
m
o
d
el’
s
p
r
ed
ictiv
e
b
eh
a
v
io
r
b
y
q
u
an
tif
y
in
g
th
e
ad
d
itiv
e
co
n
tr
ib
u
tio
n
o
f
ea
ch
in
p
u
t
v
ar
i
ab
le.
I
n
p
ar
allel,
PDPs
wer
e
u
s
ed
to
illu
s
tr
ate
th
e
m
ar
g
in
al
in
f
lu
en
ce
o
f
in
d
iv
id
u
al
f
ea
tu
r
es
o
n
t
h
e
m
o
d
el’
s
p
r
ed
icted
o
y
s
ter
m
u
s
h
r
o
o
m
y
ield
.
As
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
g
lo
b
al
SHAP
d
is
tr
ib
u
tio
n
r
e
v
ea
ls
a
d
is
tin
ct
d
o
m
in
an
ce
o
f
ag
r
o
n
o
m
ic
p
r
ed
ict
o
r
s
,
p
ar
ticu
lar
ly
r
ed
o
n
io
n
,
to
m
ato
,
an
d
ch
ili
p
r
o
d
u
ctio
n
,
wh
ich
h
as
th
e
s
tr
o
n
g
est p
o
s
itiv
e
ef
f
ec
t o
n
th
e
m
o
d
el’
s
p
r
ed
ictio
n
.
Ma
r
k
et
d
em
an
d
an
d
p
o
p
u
latio
n
r
an
k
n
ex
t
in
im
p
o
r
tan
ce
,
s
u
g
g
est
in
g
th
at
p
r
o
d
u
ctio
n
i
n
ten
s
ity
an
d
d
em
o
g
r
a
p
h
ic
p
r
ess
u
r
e
jo
in
tly
in
f
lu
en
ce
v
a
r
iatio
n
s
in
y
ield
.
I
n
c
o
n
tr
ast,
en
v
ir
o
n
m
en
tal
a
n
d
m
ac
r
o
ec
o
n
o
m
ic
in
d
icato
r
s
(
s
p
ec
if
ically
C
O,
C
O
2
,
an
d
GDP)
d
em
o
n
s
tr
ate
n
ea
r
-
ze
r
o
SHAP
m
ag
n
itu
d
es,
s
u
g
g
esti
n
g
th
eir
lim
ited
ex
p
lan
ato
r
y
p
o
we
r
with
in
th
e
f
itted
m
o
d
el
s
p
ac
e.
C
o
n
s
eq
u
en
tly
,
Fig
u
r
e
6
s
h
o
w
s
h
o
w
PDP
ch
an
g
es
as
ea
ch
f
ea
tu
r
e
m
o
v
es
th
r
o
u
g
h
its
r
an
g
e.
T
o
m
ato
an
d
r
ed
-
o
n
io
n
p
r
o
d
u
ctio
n
b
o
th
p
u
s
h
p
r
ed
ictio
n
s
u
p
s
tead
ily
,
wh
ile
ch
ili
p
r
o
d
u
ctio
n
is
m
o
s
tly
f
lat
u
n
til
h
ig
h
er
v
alu
es,
wh
er
e
it
g
iv
es
a
late
b
o
o
s
t.
Po
p
u
latio
n
,
m
ar
k
et
d
e
m
an
d
,
an
d
C
O
2
h
av
e
a
s
tep
-
lik
e
ef
f
ec
t
an
d
less
s
ig
n
if
ican
t.
I
n
co
n
tr
ast,
C
O
ex
h
ib
its
a
s
lig
h
t
n
e
g
ativ
e
tr
en
d
an
d
co
n
tr
ib
u
tes
m
in
im
al
ly
to
th
e
m
o
d
el’
s
p
r
ed
ictio
n
,
in
d
icatin
g
a
wea
k
in
v
er
s
e
ass
o
ciatio
n
with
th
e
e
s
tim
ated
o
u
tco
m
e.
Mo
r
eo
v
e
r
,
GDP
i
s
th
e
wo
r
s
t
f
ea
tu
r
e
ca
u
s
in
g
f
lu
ctu
atio
n
s
,
wh
ich
in
d
icate
s
u
n
b
alan
ce
d
d
ata.
T
h
is
ca
n
h
ap
p
en
d
u
e
to
m
is
alig
n
ed
v
ar
iab
les
(
NaN
)
o
r
d
ata
n
o
is
e.
As a
r
esu
lt,
m
o
s
t im
b
alan
ce
d
d
ata
(
GDP)
wea
k
en
s
SHAP f
o
r
its
im
p
o
r
tan
ce
v
alu
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
5
6
8
-
3
5
8
0
3576
Fig
u
r
e
5
.
Glo
b
al
SHAP f
ea
tu
r
e
im
p
ac
t in
Ad
aBo
o
s
t
m
o
d
el
a
f
ter
R
FE
Fig
u
r
e
6
.
PDP
o
f
ea
c
h
f
ea
tu
r
e
to
s
elec
ted
tar
g
et
af
ter
R
FE
B
u
ild
in
g
o
n
th
ese
in
ter
p
r
etab
ilit
y
in
s
ig
h
ts
,
th
e
en
s
em
b
le
f
r
am
ewo
r
k
ex
h
ib
its
s
tr
o
n
g
p
o
ten
tial
f
o
r
cr
o
s
s
-
d
o
m
ain
ad
ap
tatio
n
.
B
ec
au
s
e
th
e
d
o
m
in
a
n
t
p
r
ed
icto
r
s
r
ef
lect
f
u
n
d
am
e
n
tal
p
r
o
d
u
ctio
n
d
y
n
am
ics
r
ath
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Da
ta
-
d
r
iven
a
n
a
lysi
s
o
f g
r
o
w
th
fa
cto
r
s
in
o
yster
mu
s
h
r
o
o
m
cu
ltiva
tio
n
:
a
c
a
s
e
s
tu
d
y
… (
Y
o
s
ef
B
u
d
ima
n
)
3577
th
an
co
n
tex
t
-
s
p
ec
if
ic
n
o
is
e,
th
e
m
o
d
el
ar
ch
itectu
r
e
ca
n
b
e
ex
ten
d
ed
to
o
t
h
er
cr
o
p
s
,
clim
ates,
o
r
r
eg
io
n
s
with
m
in
im
al
s
tr
u
ctu
r
al
m
o
d
if
icatio
n
[
2
4
]
.
Fo
r
o
th
er
c
o
m
m
o
d
ities
,
th
e
h
o
r
ticu
ltu
r
al
p
r
ed
icto
r
s
c
an
b
e
r
ep
lace
d
with
cr
o
p
-
s
p
ec
if
ic
v
ar
iab
les
s
u
ch
as
cu
ltiv
ar
o
r
s
tr
ain
,
s
u
b
s
tr
ate
o
r
f
er
tili
ze
r
r
e
g
im
es,
an
d
p
h
en
o
lo
g
y
m
a
r
k
er
s
,
wh
ile
r
etain
in
g
g
en
er
al
d
r
iv
er
s
lik
e
m
ar
k
et
d
em
an
d
a
n
d
p
o
p
u
latio
n
d
en
s
ity
.
Fo
r
n
ew
g
eo
g
r
ap
h
ic
o
r
clim
atic
co
n
tex
ts
,
ad
d
itio
n
al
co
v
ar
iates,
in
clu
d
in
g
m
u
lti
-
y
e
ar
r
ain
f
all
an
d
n
o
r
m
al
tem
p
er
atu
r
e,
h
u
m
id
ity
o
r
v
ap
o
r
-
p
r
ess
u
r
e
d
e
f
icit,
s
o
il
tex
tu
r
e
an
d
p
H,
elev
atio
n
,
an
d
m
an
ag
em
e
n
t
p
r
ac
tices,
s
h
o
u
ld
b
e
in
co
r
p
o
r
ated
.
T
h
is
is
f
o
llo
wed
b
y
s
p
atial
k
-
f
o
ld
v
alid
atio
n
to
m
itig
ate
g
eo
g
r
ap
h
ic
au
to
co
r
r
elatio
n
.
W
h
en
lo
ca
l
d
ata
ar
e
lim
ited
,
tr
an
s
f
er
lear
n
in
g
o
r
co
v
ar
iate
-
s
h
if
t
r
ewe
ig
h
tin
g
c
an
ad
ap
t
th
e
p
o
o
led
m
o
d
el
with
o
u
t
o
v
er
f
itti
n
g
.
Op
er
atio
n
ally
,
co
n
s
is
ten
t
u
n
it
h
ar
m
o
n
izatio
n
,
s
en
s
o
r
i
n
teg
r
atio
n
,
an
d
p
er
i
o
d
ic
d
r
if
t
m
o
n
ito
r
in
g
ar
e
r
ec
o
m
m
en
d
ed
as
p
a
r
t
o
f
a
m
ac
h
in
e
lear
n
in
g
o
p
er
atio
n
s
(
ML
Op
s
)
r
o
u
tin
e.
A
with
h
eld
r
eg
io
n
al
ev
alu
atio
n
co
n
f
ir
m
e
d
th
at
m
o
d
el
ac
c
u
r
ac
y
r
em
ain
e
d
h
i
g
h
u
n
d
e
r
th
ese
ad
ap
tatio
n
s
,
in
d
icatin
g
th
at
th
e
f
r
am
ewo
r
k
s
ca
les
ef
f
ec
tiv
ely
ac
r
o
s
s
d
iv
e
r
s
e
cr
o
p
s
an
d
en
v
ir
o
n
m
e
n
tal
s
ettin
g
s
with
m
in
im
al
r
ec
alib
r
atio
n
.
3
.
5
.
Rele
v
a
nt
f
ind
ing
s
T
o
v
alid
ate
th
e
r
esear
ch
f
in
d
in
g
s
,
liter
atu
r
e
s
tu
d
ies
in
o
t
h
er
p
ap
er
s
wer
e
ex
am
in
ed
.
A
r
elev
an
t
s
tu
d
y
co
n
d
u
cted
b
y
Z
h
an
g
e
t
a
l
.
[
2
5
]
ex
am
i
n
ed
h
o
w
p
r
i
ce
v
o
latilit
y
in
o
n
e
ag
r
icu
ltu
r
al
p
r
o
d
u
ct
af
f
ec
ts
o
th
er
p
ar
am
eter
s
.
T
h
is
s
tu
d
y
h
ig
h
lig
h
ts
th
at
p
r
ice
f
lu
ctu
atio
n
s
in
ce
r
tain
ag
r
icu
ltu
r
al
p
r
o
d
u
cts,
s
u
c
h
as
s
o
y
b
ea
n
s
o
r
wh
ea
t,
ca
n
h
av
e
s
p
illo
v
er
ef
f
ec
ts
o
n
r
elate
d
m
ar
k
ets.
T
h
is
in
ter
d
ep
en
d
en
ce
m
ea
n
s
th
at
a
p
r
ice
d
ec
r
ea
s
e
in
o
n
e
co
m
m
o
d
ity
ca
n
lead
to
a
p
r
ice
d
ec
r
ea
s
e
in
an
o
th
er
co
m
m
o
d
ity
,
esp
e
cially
wh
en
th
ese
co
m
m
o
d
ities
ar
e
s
u
b
s
titu
tes
o
r
s
h
ar
e
th
e
s
am
e
p
r
o
d
u
ctio
n
in
p
u
ts
.
An
o
th
e
r
r
ele
v
an
t
a
r
ticle
is
also
s
u
p
p
o
r
te
d
b
y
W
an
za
la
an
d
Ob
o
k
o
h
[
2
6
]
.
T
h
e
f
in
d
in
g
s
s
h
o
w
th
at
p
r
ice
a
n
d
p
r
o
d
u
ctio
n
m
o
v
e
m
en
ts
ca
n
s
ig
n
if
ican
tly
af
f
ec
t
th
e
p
r
o
d
u
ctiv
ity
o
f
o
th
e
r
r
elate
d
co
m
m
o
d
ities
,
in
d
icatin
g
s
tr
o
n
g
in
ter
d
e
p
en
d
e
n
ce
.
Simu
ltan
eo
u
s
ly
,
ad
o
p
tin
g
d
y
n
am
ic
p
r
icin
g
an
d
v
alu
e
‐
ad
d
e
d
ap
p
r
o
ac
h
es
ca
n
h
elp
m
itig
ate
th
e
im
p
ac
t
o
f
s
h
o
r
t‐
ter
m
co
m
m
o
d
ity
f
lu
ct
u
atio
n
s
.
W
h
en
wh
o
lesale
m
u
s
h
r
o
o
m
p
r
ices
f
all,
g
r
o
wer
s
m
a
y
r
ed
ir
ec
t
a
p
o
r
tio
n
o
f
th
eir
h
ar
v
est
to
h
ig
h
e
r
‐
m
ar
g
in
o
u
tlets
,
s
u
ch
as
d
ir
ec
t
‐
to
‐
co
n
s
u
m
e
r
s
ales
at
f
ar
m
er
s
’
m
ar
k
ets,
o
r
th
e
p
r
o
d
u
ctio
n
o
f
d
r
ied
an
d
p
u
r
e
ed
m
u
s
h
r
o
o
m
p
r
o
d
u
cts
with
lo
n
g
er
s
h
elf
liv
es.
Mg
e
n
d
i
[
2
7
]
s
u
g
g
est
th
at
th
e
y
ield
o
p
tim
izatio
n
m
u
s
t
co
n
s
id
er
th
ese
m
ar
k
et‐
lin
k
ed
d
y
n
am
ics,
an
d
g
r
o
wer
s
s
h
o
u
ld
in
teg
r
ate
r
ea
l‐
tim
e
m
ar
k
et
an
aly
tics
d
ir
ec
tly
i
n
to
th
eir
cu
ltiv
atio
n
p
lan
n
in
g
.
B
y
f
ee
d
in
g
liv
e
p
r
ice
in
d
ices
f
o
r
k
ey
s
u
b
s
tr
ates
an
d
co
m
p
etin
g
co
m
m
o
d
ities
in
to
d
ata‐
d
r
iv
e
n
s
ch
ed
u
lin
g
to
o
ls
,
f
ar
m
er
s
ca
n
tim
e
th
eir
in
o
c
u
latio
n
an
d
f
r
u
itin
g
cy
cles to
co
in
cid
e
with
p
e
r
io
d
s
o
f
lo
wer
in
p
u
t c
o
s
ts
o
r
h
ig
h
e
r
m
u
s
h
r
o
o
m
p
r
ices.
Fu
r
th
er
m
o
r
e
,
b
y
le
v
er
ag
in
g
th
e
d
ig
ital
twin
co
n
ce
p
t,
co
m
b
i
n
in
g
i
n
ter
n
et
o
f
th
in
g
s
s
en
s
o
r
s
with
ML
alg
o
r
ith
m
s
,
m
u
s
h
r
o
o
m
g
r
o
wer
s
ca
n
cr
ea
te
a
v
ir
t
u
al
r
ep
lica
o
f
th
eir
o
y
s
ter
m
u
s
h
r
o
o
m
c
u
ltiv
atio
n
en
v
ir
o
n
m
e
n
t.
T
h
is
d
ig
ital
m
o
d
el
is
r
elate
d
to
th
e
r
esear
ch
o
f
L
ath
if
ah
an
d
Alb
ar
d
a
[
2
8
]
;
an
d
r
e
p
licates
th
e
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
o
f
t
h
e
g
r
o
win
g
f
ac
ilit
y
,
allo
win
g
cu
ltiv
ato
r
s
to
m
o
n
ito
r
an
d
ad
ju
s
t
p
ar
a
m
eter
s
in
r
ea
l
tim
e.
As
a
r
esu
lt,
f
ar
m
er
s
g
ain
clea
r
er
i
n
s
ig
h
ts
in
to
th
eir
cr
o
p
’
s
h
ea
lth
a
n
d
d
ev
el
o
p
m
en
t,
ca
n
q
u
ic
k
ly
i
d
en
tify
an
d
co
r
r
e
ct
is
s
u
es,
an
d
u
ltima
tely
ac
h
iev
e
m
o
r
e
co
n
s
is
ten
t,
h
ig
h
er
-
q
u
ality
y
ield
s
with
less
m
an
u
al
ef
f
o
r
t.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
h
i
g
h
lig
h
ts
th
e
ef
f
ec
tiv
en
ess
o
f
e
n
s
em
b
le
ML
a
n
d
f
ea
t
u
r
e
s
elec
tio
n
i
n
ag
r
icu
lt
u
r
al
y
ield
m
o
d
elin
g
.
Data
s
et
r
eliab
ilit
y
was
estab
lis
h
ed
th
r
o
u
g
h
p
r
e
p
r
o
ce
s
s
in
g
,
E
DA,
a
n
d
v
is
u
aliza
tio
n
o
f
th
e
tr
ain
in
g
an
d
test
in
g
r
esu
lts
.
T
h
ese
p
r
o
ce
d
u
r
es
en
ab
led
t
h
e
id
en
tific
a
tio
n
an
d
p
r
ed
ictio
n
o
f
th
e
k
e
y
f
ac
to
r
s
ass
o
ciate
d
with
lo
w
o
y
s
ter
m
u
s
h
r
o
o
m
p
r
o
d
u
ctio
n
in
I
n
d
o
n
esia.
T
h
e
r
e
s
u
lts
s
h
o
w
th
at
ag
r
icu
ltu
r
al
f
e
atu
r
es
s
h
o
w
a
h
ig
h
co
n
tr
ib
u
tio
n
,
in
clu
d
i
n
g
to
m
at
o
p
r
o
d
u
ctio
n
,
s
h
allo
t
p
r
o
d
u
ctio
n
,
ch
ili
p
r
o
d
u
ctio
n
,
an
d
cu
cu
m
b
er
p
r
o
d
u
ctio
n
,
co
m
p
ar
ed
to
e
n
v
ir
o
n
m
en
tal,
e
co
n
o
m
ic,
an
d
d
em
o
g
r
ap
h
ic
f
e
atu
r
es.
Fu
r
th
er
m
o
r
e,
th
ese
p
ar
am
eter
s
wer
e
u
s
ed
in
th
e
tr
ain
-
test
an
aly
s
is
to
v
is
u
alize
th
e
ex
ac
t
v
alu
es
o
f
th
e
s
tatis
t
ical
an
aly
s
is
as
s
h
o
wn
b
y
th
e
b
est
m
eth
o
d
,
n
am
ely
Ad
aBo
o
s
t,
with
R
2
,
MSE
,
an
d
MA
E
v
alu
es
o
f
0
.
9
9
7
5
7
5
,
0
.
0
0
9
8
4
1
,
an
d
0
.
0
8
5
8
8
4
,
r
esp
ec
tiv
ely
.
R
elate
d
r
esear
ch
r
elev
an
t
t
o
t
h
e
r
esear
ch
f
in
d
in
g
s
was
an
aly
ze
d
to
v
alid
ate
th
at
th
e
f
ea
t
u
r
es
o
f
a
g
r
icu
ltu
r
al
p
r
o
d
u
cts
af
f
ec
t
th
e
d
ec
lin
e
o
f
o
th
er
ag
r
ic
u
ltu
r
al
p
r
o
d
u
ctio
n
.
T
h
is
s
tu
d
y
o
f
f
e
r
s
p
r
ac
tical
co
n
tr
ib
u
tio
n
s
to
th
e
lo
ca
l
ag
r
icu
ltu
r
al
s
ec
to
r
b
y
h
e
lp
in
g
f
ar
m
er
s
id
en
tify
k
e
y
f
ac
to
r
s
af
f
ec
tin
g
o
y
s
ter
m
u
s
h
r
o
o
m
p
r
o
d
u
ctio
n
.
T
h
e
in
s
ig
h
ts
f
r
o
m
th
e
ML
m
o
d
el
ca
n
g
u
id
e
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
s
to
im
p
r
o
v
e
a
g
r
icu
ltu
r
al
y
ield
an
d
s
u
p
p
o
r
t
s
u
s
tain
ab
le
p
r
ac
tices in
I
n
d
o
n
esia.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
r
ep
o
r
t th
at
n
o
f
u
n
d
in
g
o
r
g
r
a
n
ts
wer
e
o
b
tain
e
d
f
o
r
th
e
p
r
ep
ar
atio
n
o
f
th
is
m
an
u
s
cr
ip
t.
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
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
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.