I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
14
, N
o.
5
,
O
c
to
be
r
20
25
, pp.
3879
~
3886
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
5
.pp
3879
-
3886
3879
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
O
p
t
i
m
i
z
e
d
e
n
se
m
b
l
e
f
r
am
e
w
or
k
f
or
p
r
e
d
i
c
t
i
n
g h
yd
r
op
on
i
c
st
oc
k
an
d
sal
e
s u
si
n
g m
ac
h
i
n
e
l
e
ar
n
i
n
g
V
ik
t
or
H
an
d
r
ia
n
u
s
P
r
an
a
t
aw
ij
aya, Re
s
s
a P
r
is
k
il
a, P
u
t
u
B
a
gu
s
A
d
id
yan
a A
n
u
gr
ah
P
u
t
r
a,
N
ova Noor
K
am
al
a S
ar
i,
E
f
r
an
s
C
h
r
i
s
t
ia
n
, S
e
p
t
ia
n
G
e
ge
s
,
N
ove
r
a K
r
is
t
ia
n
t
i
D
e
pa
r
t
m
e
nt
of
I
nf
or
m
a
t
i
c
s
E
ngi
ne
e
r
i
ng,
F
a
c
ul
t
y of
E
ngi
ne
e
r
i
ng, U
ni
ve
r
s
i
t
y of
P
a
l
a
ngka
R
a
ya
, P
a
l
a
ngka
R
a
ya
, I
ndone
s
i
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
M
a
y
27
,
2024
R
e
vi
s
e
d
J
un
10
,
2025
A
c
c
e
pt
e
d
J
ul
13
,
2025
The
increasing
global
demand
for
food
necessitates
the
adopti
on
of
sustainable
agricultural
practices.
Hydroponic
farming,
while
efficient
in
resource
utilizati
on,
faces
challenges
in
accurately
predicting
stock
levels
and
sales
due
to
dynamic,
ever
-
changing
factors.
This
research
prese
nts
an
optimized
ensemble
framework
for
forecasting
hydroponic
stock
levels
and
sales
by
integrating
linear
regression
(LR),
random
forest
(RF
),
and
XGBoost,
further
enhanced
through
an
evoluti
onary
algorit
hm
(EA).
The
propos
ed
framework
is
evaluated
using
root
mean
square
error
(RMS
E)
and
mean
absolute
error
(MAE),
demonstrating
significant
ac
curacy
improvements
over
individual
models.
The
ensemble
model
achie
ves
an
RMSE
reduction
of
43.82%
for
stock
pr
ediction
and
55.3%
for
sales
forecasting
compared
to
the
best
-
performing
individual
model.
Additionally,
local
interpretable
model
-
agnosti
c
explanati
ons
(LIME)
are
emplo
yed
to
offer
stakeholders
clear
insights
into
decision
-
making
processes,
s
uch
as
identifying
"
number
of
harves
ted
crops"
and
"
sales
data"
as
key
dri
vers
of
prediction
outcomes.
This
framework
supports
sustainable
develo
pment
goals (SDGs) 9.3, 12.3, and 12.C by promoting
resource eff
iciency, re
ducing
food
waste,
and
improving
small
-
scale
farmer
market
access.
Future
research
will
explore
real
-
time
data
integration
for
dynami
c
adaptati
on
and
further model
enhancements.
K
e
y
w
o
r
d
s
:
E
vol
ut
io
na
r
y a
lg
or
it
hm
H
ydr
oponic
f
a
r
m
in
g
O
pt
im
iz
e
d e
ns
e
m
bl
e
m
ode
l
P
r
e
di
c
ti
ve
a
na
ly
ti
c
s
S
us
ta
in
a
bl
e
a
gr
ic
ul
tu
r
e
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
R
e
s
s
a
P
r
is
ki
la
D
e
pa
r
tm
e
nt
of
I
nf
or
m
a
ti
c
s
E
ngi
ne
e
r
in
g, F
a
c
ul
ty
of
E
ngi
ne
e
r
in
g
, U
ni
ve
r
s
it
y of
P
a
la
ngka
R
a
ya
Y
os
S
uda
r
s
o
s
t.
, P
a
la
ngka
R
a
ya
, I
ndone
s
ia
E
m
a
il
:
r
e
s
s
a
@
it
.upr
.a
c
.i
d
1.
I
N
T
R
O
D
U
C
T
I
O
N
T
he
in
c
r
e
a
s
in
g
d
e
m
a
nd
f
or
s
us
ta
in
a
bl
e
a
gr
ic
ul
tu
r
e
ha
s
l
e
d
to
th
e
r
is
e
of
hydr
oponic
f
a
r
m
in
g,
a
r
e
s
our
c
e
-
e
f
f
ic
ie
nt
c
ul
ti
va
ti
on
m
e
th
od.
H
ow
e
ve
r
,
hydr
oponic
f
a
r
m
s
f
a
c
e
s
ig
ni
f
ic
a
nt
c
ha
ll
e
nge
s
in
s
to
c
k
m
a
na
ge
m
e
nt
,
in
c
lu
di
ng
ove
r
s
to
c
ki
ng,
unde
r
s
to
c
ki
ng,
a
nd
f
ood
w
a
s
te
[
1]
.
S
tu
di
e
s
in
di
c
a
te
th
a
t
im
pr
ope
r
f
or
e
c
a
s
ti
ng
le
a
ds
to
up
to
30%
of
pr
oduc
e
s
poi
la
ge
in
ur
ba
n
hydr
oponic
f
a
r
m
s
due
to
in
a
c
c
ur
a
te
d
e
m
a
nd
pr
e
di
c
ti
on
a
nd
s
uppl
y
c
ha
in
in
e
f
f
ic
ie
nc
ie
s
[
2]
.
T
he
s
e
in
e
f
f
ic
ie
nc
ie
s
hi
ghl
ig
ht
th
e
c
r
it
ic
a
l
ne
e
d
f
or
a
dva
nc
e
d
pr
e
di
c
ti
ve
a
na
ly
ti
c
s
t
o opti
m
iz
e
pr
oduc
ti
on a
nd r
e
duc
e
l
o
s
s
e
s
.
E
xi
s
ti
ng
f
or
e
c
a
s
ti
ng
m
ode
ls
of
te
n
s
tr
uggl
e
w
it
h
th
e
uni
que
c
om
pl
e
xi
ti
e
s
of
hydr
oponic
f
a
r
m
in
g,
s
uc
h
a
s
dyna
m
ic
pl
a
nt
gr
ow
th
c
yc
le
s
,
f
lu
c
tu
a
ti
ng
w
e
a
th
e
r
c
ondi
ti
ons
,
a
nd
r
e
s
our
c
e
c
ons
tr
a
in
ts
[
3]
,
[
4]
.
T
he
s
e
c
ha
ll
e
nge
s
m
a
ke
it
di
f
f
ic
ul
t
to
m
a
in
ta
in
opt
im
a
l
s
to
c
k
l
e
ve
ls
,
of
te
n
r
e
s
ul
ti
ng
in
in
e
f
f
ic
ie
nc
ie
s
a
nd
f
in
a
nc
ia
l
lo
s
s
e
s
.
T
r
a
di
ti
ona
l
s
t
a
ti
s
ti
c
a
l
m
ode
ls
a
nd
s
in
gl
e
-
m
a
c
hi
n
e
le
a
r
ni
ng
a
ppr
oa
c
he
s
f
a
il
to
c
a
pt
ur
e
th
e
in
tr
ic
a
te
,
nonl
in
e
a
r
r
e
la
ti
ons
hi
ps
i
n hydr
oponic
da
ta
, l
e
a
di
ng t
o i
na
c
c
ur
a
t
e
pr
e
di
c
ti
ons
[
5]
, [
6]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
5
,
O
c
to
be
r
2025
:
3879
-
3886
3880
T
o
a
d
d
r
e
s
s
t
hi
s
r
e
s
e
a
r
c
h
g
a
p,
t
hi
s
s
t
u
dy
pr
o
p
o
s
e
s
a
n
o
p
ti
m
i
z
e
d e
n
s
e
m
b
l
e
f
r
a
m
e
w
o
r
k
t
h
a
t
i
nt
e
g
r
a
t
e
s
l
in
e
a
r
r
e
g
r
e
s
s
i
o
n
(
L
R
)
,
r
a
nd
o
m
f
or
e
s
t
(
R
F
)
,
a
n
d
X
G
B
oo
s
t
.
T
h
e
s
e
m
ode
l
s
c
o
m
p
l
e
m
e
n
t
e
a
c
h
o
t
h
e
r
b
y
l
e
v
e
r
a
g
i
n
g
t
h
e
ir
u
n
i
q
u
e
s
t
r
e
n
g
t
h
s
:
L
R
c
a
pt
u
r
e
s
l
in
e
a
r
t
r
e
n
d
s
i
n s
t
o
c
k m
o
v
e
m
e
n
t
[
7
]
.
R
F
e
n
h
a
n
c
e
s
r
ob
u
s
t
n
e
s
s
b
y
h
a
n
d
li
n
g n
o
nl
i
n
e
a
r
i
n
t
e
r
a
c
t
i
o
n
s
a
nd
f
e
a
t
u
r
e
i
m
p
or
t
a
n
c
e
[
8]
.
X
G
B
oo
s
t
im
p
r
ov
e
s
a
c
c
u
r
a
c
y
t
h
r
o
u
g
h
g
r
a
di
e
n
t
bo
o
s
t
i
ng
t
e
c
h
ni
q
u
e
s
[
6
]
.
T
he
in
te
gr
a
ti
on
of
a
n
e
vol
ut
io
na
r
y
a
lg
or
it
hm
(
E
A
)
opt
im
iz
e
s
m
ode
l
w
e
ig
ht
in
g
to
e
nha
nc
e
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
[
9]
.
T
hi
s
m
e
th
od
dyna
m
ic
a
ll
y
a
dj
us
ts
m
ode
l
c
ont
r
ib
ut
io
ns
,
r
e
duc
in
g
f
or
e
c
a
s
ti
ng
e
r
r
or
s
a
nd
im
pr
ovi
ng a
da
pt
a
bi
li
ty
. A
ddi
ti
ona
ll
y, t
he
a
dopt
io
n
of
l
oc
a
l
in
te
r
pr
e
ta
bl
e
m
ode
l
-
a
gnos
ti
c
e
xpl
a
na
ti
ons
(
L
I
M
E
)
e
nha
nc
e
s
tr
a
n
s
pa
r
e
nc
y
by
id
e
nt
if
yi
ng
ke
y
pr
e
di
c
ti
ve
f
a
c
to
r
s
,
e
na
bl
in
g
s
ta
k
e
hol
de
r
s
to
m
a
ke
in
f
or
m
e
d
de
c
is
io
ns
r
e
ga
r
di
ng
in
ve
nt
or
y
c
ont
r
ol
a
nd
de
m
a
nd
f
or
e
c
a
s
ti
ng
[
10]
,
[
11]
.
T
hi
s
r
e
s
e
a
r
c
h
a
li
gns
w
it
h
s
us
ta
in
a
bl
e
de
v
e
lo
pm
e
nt
goa
ls
(
S
D
G
s
)
by
s
uppor
ti
ng
S
D
G
12.
3
(
r
e
duc
in
g
f
ood
w
a
s
te
)
,
S
D
G
9.3
(
e
nha
nc
in
g
m
a
r
ke
t
a
c
c
e
s
s
f
or
s
m
a
ll
-
s
c
a
le
f
a
r
m
e
r
s
)
,
a
nd
S
D
G
12.C
(
op
ti
m
iz
in
g
r
e
s
our
c
e
a
ll
oc
a
ti
on)
.
T
he
pr
opos
e
d
e
ns
e
m
bl
e
f
r
a
m
e
w
or
k
e
nh
a
nc
e
s
pr
e
di
c
ti
on
a
c
c
ur
a
c
y,
h
e
lp
in
g
f
a
r
m
e
r
s
m
a
ke
d
a
ta
-
dr
iv
e
n
de
c
is
io
n
s
to
m
in
im
iz
e
w
a
s
te
a
nd
opt
im
iz
e
r
e
s
our
c
e
s
.
A
ddi
ti
ona
ll
y,
th
e
in
te
r
pr
e
ta
bi
li
ty
pr
ovi
de
d
by
L
I
M
E
im
p
r
ove
s
tr
a
ns
pa
r
e
nc
y,
e
ns
ur
in
g
th
a
t
s
ta
ke
hol
de
r
s
c
a
n
e
f
f
e
c
ti
ve
ly
m
a
na
g
e
pr
oduc
ti
on
c
yc
le
s
f
or
a
m
or
e
s
u
s
ta
in
a
bl
e
a
nd
e
f
f
ic
ie
nt
hydr
oponic
f
a
r
m
in
g e
c
os
ys
te
m
.
T
he
r
e
m
a
in
de
r
of
th
is
pa
pe
r
is
or
ga
ni
z
e
d
a
s
:
s
e
c
ti
on
2
out
li
ne
s
t
he
pr
opos
e
d
m
e
th
odol
ogy,
in
c
lu
di
ng
da
ta
a
c
qui
s
it
io
n,
pr
e
pr
oc
e
s
s
in
g,
a
nd
m
ode
l
de
ve
lo
pm
e
nt
.
S
e
c
ti
on
3
pr
e
s
e
nt
s
th
e
r
e
s
ul
t
s
a
nd
di
s
c
u
s
s
io
n,
e
va
lu
a
ti
ng
th
e
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
f
r
a
m
e
w
or
k.
S
e
c
ti
o
n
4
c
onc
lu
de
s
w
it
h
k
e
y
in
s
ig
ht
s
,
im
pl
ic
a
ti
on
s
,
a
nd pote
nt
ia
l
f
ut
ur
e
r
e
s
e
a
r
c
h di
r
e
c
ti
ons
.
2.
M
E
T
H
O
D
T
hi
s
r
e
s
e
a
r
c
h
c
on
s
is
ts
of
f
our
m
a
in
s
te
p
s
:
da
ta
a
c
qui
s
it
io
n,
m
ode
l
de
ve
lo
pm
e
nt
,
m
ode
l
e
va
lu
a
ti
on,
a
nd
in
te
r
pr
e
ta
bi
li
ty
.
F
ig
ur
e
1
pr
ovi
de
s
a
ddi
ti
ona
l
de
ta
il
s
on
th
e
pr
oc
e
s
s
.
F
ur
th
e
r
e
xpl
a
na
ti
ons
a
r
e
a
v
a
il
a
bl
e
in
th
e
s
ubs
e
que
nt
s
ubs
e
c
ti
ons
.
F
ig
ur
e
1. T
he
de
ve
lo
pm
e
nt
of
a
n e
ns
e
m
bl
e
f
r
a
m
e
w
or
k
2.1.
D
at
a
a
c
q
u
is
it
io
n
T
he
d
a
ta
s
e
t
us
e
d
in
th
is
s
tu
dy
w
a
s
c
ol
le
c
te
d
f
r
om
a
hydr
opon
ic
f
a
r
m
ove
r
a
s
pa
n
of
28
w
e
e
ks
.
I
t
in
c
lu
de
s
ke
y
va
r
ia
bl
e
s
s
u
c
h
a
s
th
e
num
be
r
of
c
r
op
s
pl
a
nt
e
d,
th
e
num
be
r
of
c
r
ops
ha
r
ve
s
te
d,
a
nd
s
a
le
s
r
e
c
or
d
s
.
D
a
ta
pr
e
pr
oc
e
s
s
in
g
in
vol
ve
d
ha
ndl
in
g
m
is
s
in
g
va
lu
e
s
by
c
a
lc
u
la
ti
ng
th
e
r
e
m
a
in
in
g
s
to
c
k
ba
s
e
d
on
a
va
il
a
bl
e
da
ta
,
s
uc
h
a
s
ha
r
ve
s
t
a
nd
s
a
le
s
qua
nt
it
ie
s
,
a
nd
a
ddi
ng
it
to
th
e
s
to
c
k
f
or
th
e
f
ol
lo
w
in
g
w
e
e
k
,
a
nd
s
pl
it
ti
ng
th
e
da
ta
s
e
t
in
to
a
n 80%
t
r
a
in
in
g s
e
t
a
nd a
20%
t
e
s
ti
ng s
e
t
to
e
ns
ur
e
th
e
r
e
li
a
bi
li
ty
of
t
he
m
ode
l
[
12]
,
[
13]
.
2.2.
M
od
e
l
d
e
ve
lo
p
m
e
n
t
T
he
E
A
us
e
d
in
th
is
s
tu
dy
a
dj
us
t
s
th
e
w
e
ig
ht
s
of
in
di
vi
dua
l
m
ode
ls
-
L
R
[
14]
,
R
F
[
15]
,
a
nd
X
G
B
oos
t
[
16]
to
m
in
im
iz
e
pr
e
di
c
ti
on
e
r
r
or
s
.
R
a
th
e
r
th
a
n
a
s
s
ig
ni
ng
e
qua
l
w
e
ig
ht
s
to
th
e
s
e
m
ode
ls
,
th
e
E
A
dyna
m
ic
a
ll
y
opt
im
iz
e
s
th
e
ir
c
ont
r
ib
ut
io
ns
ba
s
e
d
on
th
e
ir
pe
r
f
or
m
a
nc
e
.
T
h
e
goa
l
i
s
to
f
in
d
th
e
opt
im
a
l
w
e
ig
ht
f
or
e
a
c
h
m
ode
l
by
m
in
im
iz
in
g
pr
e
di
c
ti
on
e
r
r
or
s
us
in
g
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
s
uc
h
a
s
r
oot
m
e
a
n
s
qua
r
e
e
r
r
or
(
R
M
S
E
)
a
nd
m
e
a
n
a
b
s
ol
ut
e
e
r
r
or
(
M
A
E
)
.
T
hi
s
a
ppr
oa
c
h
e
ns
ur
e
s
th
a
t
m
ode
ls
w
it
h
hi
ghe
r
in
di
vi
dua
l
a
c
c
ur
a
c
y
ha
ve
a
gr
e
a
te
r
i
nf
lu
e
nc
e
on t
he
f
in
a
l
pr
e
di
c
ti
on w
hi
le
m
a
in
ta
in
in
g t
he
r
obus
tn
e
s
s
of
t
he
e
n
s
e
m
bl
e
.
T
he
opt
im
iz
a
ti
on
pr
oc
e
s
s
b
e
gi
ns
by
in
it
ia
li
z
in
g
a
popula
ti
on
of
100
in
di
vi
dua
ls
,
e
a
c
h
r
e
pr
e
s
e
nt
in
g
a
uni
que
c
om
bi
na
ti
on
of
w
e
ig
ht
s
.
F
it
ne
s
s
e
va
lu
a
ti
on
is
c
ondu
c
te
d
to
a
s
s
e
s
s
e
a
c
h
in
di
vi
dua
l’
s
pe
r
f
or
m
a
nc
e
ba
s
e
d
on
R
M
S
E
a
nd
M
A
E
,
a
ll
ow
in
g
th
e
a
lg
or
it
hm
to
id
e
nt
if
y
th
e
m
os
t
e
f
f
e
c
ti
ve
w
e
ig
ht
a
s
s
ig
nm
e
nt
s
.
O
nc
e
th
e
opt
im
a
l
w
e
ig
ht
c
om
bi
na
ti
on
is
f
ound,
th
e
e
ns
e
m
bl
e
m
ode
l
is
e
va
lu
a
te
d
us
in
g
va
r
io
us
p
e
r
f
or
m
a
nc
e
m
e
tr
ic
s
.
A
ddi
ti
ona
ll
y,
L
I
M
E
is
a
ppl
ie
d
to
e
xpl
a
in
th
e
m
ode
l'
s
pr
e
di
c
ti
ons
,
pr
ovi
di
ng
s
ta
ke
hol
de
r
s
w
it
h
a
c
ti
ona
bl
e
i
ns
ig
ht
s
i
nt
o t
he
f
a
c
to
r
s
dr
iv
in
g s
to
c
k
a
nd s
a
le
s
f
or
e
c
a
s
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
e
d e
ns
e
m
bl
e
f
r
am
e
w
or
k
f
o
r
pr
e
di
c
ti
ng hy
dr
oponic
s
to
c
k
and
…
(
V
ik
to
r
H
andr
ia
nus
P
r
anat
aw
ij
ay
a
)
3881
T
h
e
s
e
l
e
c
ti
on
m
e
c
h
a
ni
s
m
r
e
t
a
i
n
s
th
e
t
op
5
0%
of
i
nd
iv
id
u
a
l
s
w
i
t
h
t
h
e
b
e
s
t
p
e
r
f
or
m
a
n
c
e
f
o
r
th
e
n
e
x
t
g
e
n
e
r
a
ti
on
.
T
o
m
a
in
t
a
i
n
di
v
e
r
s
it
y
a
nd
a
vo
id
pr
e
m
a
t
ur
e
c
o
n
ve
r
g
e
n
c
e
,
c
r
o
s
s
o
v
e
r
a
n
d
m
ut
a
t
io
n
o
p
e
r
a
t
io
n
s
a
r
e
e
m
pl
o
ye
d
t
o
i
nt
r
od
u
c
e
g
e
n
e
ti
c
v
a
r
i
a
t
io
n
s
.
C
r
o
s
s
ov
e
r
oc
c
ur
s
w
i
th
a
pr
ob
a
bi
li
ty
of
5
0%
,
a
ll
ow
i
ng
w
e
ig
h
t
c
o
m
bi
na
ti
o
n
s
t
o s
h
a
r
e
i
nf
or
m
a
ti
on
,
w
h
il
e
m
ut
a
ti
on
oc
c
ur
s
w
i
th
a
2
0%
pr
ob
a
bi
li
ty
,
i
nt
r
o
du
c
in
g
s
m
a
l
l
v
a
r
i
a
t
io
n
s
t
o
e
x
p
lo
r
e
n
e
w
p
ot
e
nt
ia
l
s
ol
u
ti
on
s
.
T
h
e
o
pt
im
iz
a
ti
on
pr
o
c
e
s
s
r
un
s
i
te
r
a
t
i
ve
ly
f
or
5
0
g
e
n
e
r
a
ti
o
n
s
,
g
r
a
d
ua
ll
y
r
e
f
i
ni
n
g
w
e
i
gh
t
di
s
tr
ib
ut
io
n
s
u
nt
il
c
o
n
ve
r
g
e
n
c
e
i
s
a
c
h
i
e
v
e
d.
T
hr
ou
gh
th
i
s
i
t
e
r
a
t
iv
e
a
p
pr
oa
c
h,
th
e
m
od
e
l
dy
n
a
m
i
c
a
ll
y
a
d
j
u
s
t
s
th
e
c
on
tr
ib
ut
i
on
s
of
e
a
c
h
a
l
go
r
i
th
m
t
o
m
i
ni
m
i
z
e
pr
e
di
c
ti
o
n
e
r
r
or
s
[
9]
,
[
1
7]
.
T
he
o
pt
im
i
z
e
d
w
e
i
gh
t
a
s
s
i
g
nm
e
nt
s
e
n
h
a
n
c
e
t
he
m
o
de
l’
s
a
d
a
pt
a
bi
li
ty
,
im
pr
o
vi
ng
f
or
e
c
a
s
ti
n
g
a
c
c
u
r
a
c
y
a
n
d
d
e
c
i
s
io
n
-
m
a
ki
n
g
e
f
f
i
c
i
e
n
c
y
.
2.3.
M
od
e
l
e
val
u
at
io
n
T
he
m
ode
ls
w
e
r
e
e
v
a
lu
a
te
d
us
in
g
R
M
S
E
a
nd
M
A
E
s
c
or
e
s
.
A
c
om
pa
r
a
ti
ve
a
na
ly
s
is
w
a
s
c
onduc
te
d
to
m
e
a
s
ur
e
th
e
di
f
f
e
r
e
nc
e
s
in
pe
r
f
or
m
a
nc
e
be
twe
e
n
in
di
vi
dua
l
m
ode
ls
a
nd
th
e
opt
im
iz
e
d
e
ns
e
m
bl
e
.
T
hi
s
a
na
ly
s
is
a
im
e
d t
o
a
s
s
e
s
s
i
m
pr
ove
m
e
nt
s
i
n pr
e
di
c
ti
ve
a
c
c
ur
a
c
y a
nd
r
e
li
a
bi
li
ty
[
18]
–
[
20
]
.
2.4.
I
n
t
e
r
p
r
e
t
ab
il
it
y w
it
h
lo
c
al
i
n
t
e
r
p
r
e
t
ab
le
m
od
e
l
-
agn
os
t
i
c
e
xp
la
n
at
io
n
s
T
o
e
n
s
ur
e
tr
a
ns
pa
r
e
n
c
y,
L
I
M
E
w
a
s
e
m
pl
oye
d
to
a
na
ly
z
e
f
e
a
tu
r
e
im
por
ta
nc
e
s
uc
h
a
s
num
be
r
ha
r
ve
s
te
d,
s
a
le
s
da
ta
,
r
e
m
a
in
in
g
s
to
c
k,
a
nd
num
be
r
of
pl
a
nt
s
pl
a
nt
e
d
.
T
hi
s
m
e
th
od
he
lp
s
e
xpl
a
in
pr
e
di
c
ti
on
out
c
om
e
s
by
il
lu
s
tr
a
ti
ng
th
e
in
f
lu
e
nc
e
of
k
e
y
va
r
ia
bl
e
s
.
B
y
pr
ovi
di
ng
c
le
a
r
e
r
in
s
ig
ht
s
,
L
I
M
E
e
nha
nc
e
s
s
ta
ke
hol
de
r
t
r
us
t
in
s
to
c
k a
nd
s
a
le
s
pr
e
di
c
ti
ons
[
21]
, [
22]
.
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
T
hi
s
s
e
c
ti
on
pr
e
s
e
nt
s
th
e
pe
r
f
or
m
a
nc
e
e
va
lu
a
ti
on
of
th
e
pr
opos
e
d
e
ns
e
m
bl
e
f
r
a
m
e
w
or
k,
it
s
in
te
r
pr
e
ta
bi
li
ty
,
c
om
pa
r
is
ons
w
it
h
pr
io
r
r
e
s
e
a
r
c
h,
a
nd
it
s
im
pl
ic
a
ti
ons
f
or
s
us
t
a
in
a
bl
e
a
gr
ic
ul
tu
r
a
l
pr
a
c
ti
c
e
s
.
T
he
f
in
di
ngs
de
m
ons
tr
a
te
t
he
e
f
f
e
c
ti
ve
ne
s
s
of
E
A
-
ba
s
e
d opti
m
i
z
a
ti
on i
n i
m
pr
ovi
ng
t
he
p
r
e
di
c
ti
ve
a
c
c
ur
a
c
y of
hydr
oponic
s
to
c
k
a
nd
s
a
le
s
f
or
e
c
a
s
ti
ng.
A
ddi
ti
ona
ll
y,
th
e
in
te
gr
a
ti
on
of
L
I
M
E
e
nha
nc
e
s
th
e
m
ode
l’
s
tr
a
ns
pa
r
e
nc
y, m
a
ki
ng i
t
m
or
e
a
c
ti
ona
bl
e
f
or
s
ta
ke
hol
de
r
s
.
3.1.
M
od
e
l
p
e
r
f
or
m
an
c
e
e
val
u
at
io
n
M
ode
l
pe
r
f
or
m
a
nc
e
w
a
s
e
v
a
lu
a
te
d
us
in
g
R
M
S
E
a
nd
M
A
E
to
a
s
s
e
s
s
th
e
a
c
c
ur
a
c
y
of
s
to
c
k
a
nd
s
a
le
s
pr
e
di
c
ti
ons
.
T
a
bl
e
1
s
how
s
th
e
R
M
S
E
a
nd
M
A
E
va
lu
e
s
f
or
e
a
c
h
in
di
vi
dua
l
m
ode
l
a
nd
th
e
e
n
s
e
m
bl
e
m
od
e
l.
T
he
e
ns
e
m
bl
e
a
ppr
oa
c
h
c
ons
is
te
nt
ly
out
pe
r
f
or
m
s
L
R
,
R
F
,
a
nd
X
G
B
oos
t
in
bot
h
m
e
tr
ic
s
,
de
m
ons
tr
a
ti
ng
it
s
a
bi
li
ty
to
ha
ndl
e
th
e
c
om
pl
e
xi
ti
e
s
of
hydr
oponic
s
a
le
s
f
or
e
c
a
s
ti
ng.
F
ig
ur
e
2
vi
s
ua
li
z
e
s
th
e
pr
e
di
c
te
d
ve
r
s
us
a
c
tu
a
l
r
e
m
a
in
in
g
s
to
c
k
le
ve
l
s
,
hi
ghl
ig
ht
in
g
th
e
m
ode
l'
s
a
c
c
ur
a
c
y.
O
ve
r
a
ll
,
th
e
e
ns
e
m
bl
e
m
ode
l
pr
ovi
de
s
m
or
e
c
ons
is
te
nt
pr
e
di
c
ti
ons
t
ha
t
a
r
e
c
lo
s
e
r
t
o t
he
a
c
tu
a
l
va
lu
e
s
.
T
a
bl
e
1. M
od
e
l
pe
r
f
or
m
a
nc
e
c
om
pa
r
is
on
M
ode
l
R
e
m
a
i
ni
ng
s
t
oc
k
S
a
l
e
s
R
M
S
E
M
A
E
R
M
S
E
M
A
E
LR
1.78
1.04
5.39
2.17
RF
2.89
1.49
6.53
2.12
X
G
B
oos
t
4.27
1.19
16.60
3.32
E
ns
e
m
bl
e
m
ode
l
1.00
0.93
2.41
1.66
F
ig
ur
e
2.
T
he
p
r
e
di
c
te
d
v
e
r
s
us
a
c
tu
a
l
r
e
m
a
in
in
g s
to
c
k
l
e
v
e
ls
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
5
,
O
c
to
be
r
2025
:
3879
-
3886
3882
T
he
e
ns
e
m
bl
e
m
ode
l,
opt
im
iz
e
d
us
in
g
a
n
E
A
f
or
w
e
ig
ht
a
d
ju
s
tm
e
nt
,
s
ig
ni
f
ic
a
nt
ly
r
e
duc
e
s
bot
h
R
M
S
E
a
nd
M
A
E
va
lu
e
s
.
T
hi
s
im
pr
ove
m
e
nt
de
m
ons
tr
a
te
s
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
c
om
bi
ni
ng
m
ul
ti
pl
e
m
ode
ls
th
r
ough
opt
im
iz
e
d
w
e
ig
ht
in
g,
le
a
di
ng
to
m
or
e
r
e
li
a
bl
e
pr
e
di
c
ti
ons
.
T
he
s
e
e
nha
n
c
e
m
e
nt
s
a
r
e
pa
r
ti
c
ul
a
r
ly
va
lu
a
bl
e
f
or
s
m
a
ll
-
s
c
a
le
hydr
oponic
f
a
r
m
e
r
s
,
a
s
th
e
y
im
pr
ove
in
ve
nt
or
y
m
a
na
ge
m
e
nt
a
nd
s
a
le
s
f
or
e
c
a
s
ti
ng,
ul
ti
m
a
te
ly
m
in
im
iz
in
g
w
a
s
te
a
nd
opt
im
iz
in
g
r
e
s
our
c
e
s
[
23]
–
[
25]
.
F
or
s
to
c
k
pr
e
di
c
ti
on,
th
e
opt
im
iz
e
d
w
e
ig
ht
s
a
r
e
0.92
f
or
L
R
,
0.52
f
or
R
F
,
a
nd
-
0.26
f
or
X
G
B
oos
t.
F
or
s
a
l
e
s
pr
e
di
c
ti
on,
th
e
w
e
ig
ht
s
a
r
e
0.03
f
or
L
R
,
0.72
f
or
R
F
,
a
nd
0.26
f
or
X
G
B
oos
t.
T
he
w
e
ig
ht
opt
im
iz
a
ti
on
pr
oc
e
s
s
im
pr
ove
s
pr
e
di
c
ti
on
a
c
c
ur
a
c
y,
s
uppor
ti
ng
m
or
e
e
f
f
ic
ie
nt
s
to
c
k m
a
na
ge
m
e
nt
a
nd r
e
duc
in
g f
ood wa
s
te
.
T
he
e
n
s
e
m
bl
e
m
ode
l
ha
ndl
e
s
non
-
li
ne
a
r
it
y
a
nd
f
e
a
tu
r
e
in
te
r
a
c
t
io
ns
by
ut
il
iz
in
g
th
e
s
tr
e
ngt
hs
of
R
F
a
nd
X
G
B
oos
t.
W
hi
le
L
R
c
a
pt
ur
e
s
onl
y
li
ne
a
r
r
e
la
ti
ons
hi
ps
,
R
F
a
nd
X
G
B
oos
t
a
r
e
c
a
pa
bl
e
of
m
ode
li
ng
c
om
pl
e
x,
non
-
li
ne
a
r
pa
tt
e
r
ns
a
nd
in
te
r
a
c
ti
on
s
be
tw
e
e
n
f
e
a
tu
r
e
s
.
T
he
r
e
f
or
e
,
e
v
e
n
th
ough
L
R
doe
s
not
a
c
c
ount
f
or
f
e
a
tu
r
e
in
te
r
a
c
ti
ons
,
th
e
e
n
s
e
m
bl
e
m
ode
l
c
om
bi
ne
s
th
e
be
n
e
f
it
s
of
a
ll
th
r
e
e
m
ode
l
s
,
e
na
bl
in
g
it
to
c
a
pt
ur
e
bot
h non
-
li
ne
a
r
it
y a
nd f
e
a
tu
r
e
i
nt
e
r
a
c
ti
ons
e
f
f
e
c
ti
ve
ly
.
3.2.
I
n
t
e
r
p
r
e
t
ab
il
it
y of
p
r
e
d
ic
t
io
n
s
T
o
e
nha
nc
e
th
e
tr
a
ns
pa
r
e
nc
y
of
m
ode
l
de
c
is
io
ns
,
L
I
M
E
w
a
s
e
m
pl
oye
d
to
a
na
ly
z
e
th
e
i
m
pa
c
t
of
va
r
io
us
f
e
a
tu
r
e
s
on
pr
e
di
c
ti
on
out
c
om
e
s
a
s
s
how
n
in
F
ig
ur
e
3
.
T
he
r
e
s
ul
t
s
in
di
c
a
te
th
a
t
"
num
be
r
ha
r
ve
s
te
d"
a
nd
"
s
a
le
s
da
ta
"
a
r
e
th
e
m
os
t
in
f
lu
e
nt
ia
l
f
a
c
to
r
s
in
de
te
r
m
in
in
g
r
e
m
a
in
in
g
s
to
c
k
F
ig
ur
e
3
(
a
)
,
w
hi
le
"
num
be
r
ha
r
ve
s
te
d"
a
nd
"
r
e
m
a
in
in
g
s
to
c
k
"
pl
a
y
a
c
r
uc
ia
l
r
ol
e
in
pr
e
di
c
ti
ng
s
a
le
s
F
ig
ur
e
3
(
b
)
.
F
or
r
e
m
a
in
in
g
s
to
c
k
pr
e
di
c
ti
ons
F
ig
ur
e
3
(
a
)
,
if
th
e
num
be
r
of
ha
r
ve
s
t
s
is
le
s
s
th
a
n
o
r
e
qua
l
to
974.25,
th
e
pr
e
di
c
ti
on
de
c
r
e
a
s
e
s
by
5.68
uni
ts
,
in
di
c
a
ti
ng
a
s
tr
ong
ne
ga
ti
ve
im
pa
c
t.
C
onve
r
s
e
ly
,
if
s
a
le
s
d
a
ta
is
l
e
s
s
th
a
n
or
e
qua
l
to
975.00,
th
e
pr
e
di
c
te
d
s
to
c
k
in
c
r
e
a
s
e
s
by
4.30
uni
ts
,
s
ugge
s
ti
ng
th
a
t
s
to
c
k
le
ve
ls
a
r
e
e
xpe
c
te
d
to
be
hi
ghe
r
w
he
n
r
e
c
e
nt
s
a
le
s
s
ta
y w
it
hi
n t
hi
s
t
hr
e
s
hol
d. T
he
numbe
r
of
pl
a
nt
s
pl
a
nt
e
d h
a
s
a
ne
gl
ig
ib
le
e
f
f
e
c
t
on
th
is
pr
e
di
c
ti
on. T
he
s
e
f
in
di
ngs
hi
ghl
ig
ht
th
os
e
f
lu
c
tu
a
ti
ons
in
ha
r
ve
s
t
s
iz
e
a
nd
r
e
c
e
nt
s
a
le
s
tr
e
nds
s
ig
ni
f
ic
a
nt
ly
in
f
lu
e
nc
e
s
to
c
k
a
va
il
a
bi
li
ty
, a
ll
ow
in
g f
a
r
m
e
r
s
t
o be
tt
e
r
a
nt
ic
ip
a
te
i
nve
nt
or
y l
e
ve
ls
.
F
or
s
a
le
s
pr
e
di
c
ti
ons
F
ig
ur
e
3
(
b
)
,
w
he
n
th
e
num
be
r
o
f
ha
r
ve
s
ts
is
le
s
s
th
a
n
or
e
qua
l
to
974.25,
th
e
pr
e
di
c
te
d
s
a
le
s
d
e
c
r
e
a
s
e
by
10.50
uni
ts
,
c
onf
ir
m
in
g
th
e
di
r
e
c
t
c
or
r
e
la
ti
on
be
twe
e
n
ha
r
ve
s
t
s
i
z
e
a
nd
s
a
le
s
vol
um
e
.
A
ddi
ti
ona
ll
y,
i
f
r
e
m
a
in
in
g
s
to
c
k
e
xc
e
e
ds
6.00
uni
ts
,
th
e
pr
e
di
c
ti
on
dr
ops
by
1.77
uni
ts
,
in
di
c
a
ti
ng
th
a
t
s
ur
pl
us
in
ve
nt
or
y
doe
s
not
ne
c
e
s
s
a
r
il
y
tr
a
ns
la
te
to
hi
gh
e
r
s
a
le
s
.
S
im
il
a
r
to
th
e
s
to
c
k
pr
e
di
c
ti
on,
th
e
num
be
r
of
pl
a
nt
s
pl
a
nt
e
d
ha
s
a
n
in
s
ig
ni
f
ic
a
nt
in
f
lu
e
nc
e
on
th
e
s
a
le
s
f
or
e
c
a
s
t.
T
he
s
e
in
s
ig
ht
s
de
m
ons
tr
a
te
th
a
t
m
a
in
ta
in
in
g
a
n
opt
im
a
l
ha
r
ve
s
t
s
iz
e
a
nd
m
a
na
gi
ng
in
ve
nt
or
y
e
f
f
e
c
ti
ve
ly
a
r
e
c
r
it
ic
a
l
f
or
m
a
xi
m
iz
in
g
s
a
le
s
.
B
y
in
te
r
pr
e
ti
ng
pr
e
di
c
ti
ons
th
r
ough
L
I
M
E
,
th
e
f
r
a
m
e
w
or
k
pr
ov
id
e
s
a
c
ti
ona
bl
e
in
s
ig
ht
s
th
a
t
e
na
bl
e
f
a
r
m
e
r
s
to
m
a
ke
da
ta
-
dr
iv
e
n
a
dj
us
tm
e
nt
s
in
pr
oduc
ti
on
s
tr
a
te
gi
e
s
.
U
nd
e
r
s
ta
ndi
ng
th
e
s
e
f
e
a
tu
r
e
c
ont
r
ib
ut
io
ns
he
lp
s
opt
im
iz
e
in
ve
nt
or
y
c
ont
r
ol
,
im
p
r
ove
de
m
a
nd
f
or
e
c
a
s
ti
ng,
a
nd
e
nha
nc
e
r
e
s
our
c
e
a
ll
oc
a
ti
on,
le
a
di
ng
to
m
or
e
e
f
f
ic
ie
nt
a
nd s
us
ta
in
a
bl
e
hydr
oponic
f
a
r
m
in
g
[
26]
, [
27]
.
(
a
)
(
b)
F
ig
ur
e
3
.
L
I
M
E
a
na
ly
s
is
f
or
(
a
)
r
e
m
a
in
in
g s
to
c
k pr
e
di
c
ti
on a
nd
(
b)
s
a
le
s
pr
e
di
c
ti
on
3.3.
C
om
p
ar
is
on
w
it
h
p
r
e
vi
ou
s
s
t
u
d
ie
s
P
r
e
v
io
u
s
r
e
s
e
a
r
c
h
o
n
hy
dr
op
on
ic
f
or
e
c
a
s
t
in
g
h
a
s
pr
e
dom
in
a
n
tl
y
ut
i
li
z
e
d
s
i
ngl
e
m
a
c
h
in
e
l
e
a
r
n
in
g
m
od
e
l
s
or
s
ta
t
i
s
ti
c
a
l
m
e
th
od
s
,
w
h
ic
h
of
t
e
n
s
tr
u
ggl
e
t
o
a
da
pt
t
o
di
v
e
r
s
e
e
n
vi
r
onm
e
n
ta
l
c
ond
it
i
on
s
a
nd
m
a
r
ke
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
e
d e
ns
e
m
bl
e
f
r
am
e
w
or
k
f
o
r
pr
e
di
c
ti
ng hy
dr
oponic
s
to
c
k
and
…
(
V
ik
to
r
H
andr
ia
nus
P
r
anat
aw
ij
ay
a
)
3883
f
lu
c
tu
a
ti
on
s
.
T
h
e
s
e
m
e
th
od
s
of
t
e
n l
a
c
k
g
e
n
e
r
a
li
z
a
bi
l
it
y
a
nd
r
ob
u
s
t
ne
s
s
,
li
m
it
i
ng t
h
e
ir
e
f
f
e
c
ti
ve
ne
s
s
i
n
r
e
a
l
-
w
or
l
d
hydr
opo
ni
c
s
y
s
te
m
s
.
I
doj
e
e
t
al
.
[
28]
e
m
ph
a
s
i
z
e
t
he
li
m
it
a
ti
on
s
o
f
tr
a
di
t
io
na
l
m
a
c
hi
ne
l
e
a
r
ni
n
g a
l
gor
i
th
m
s
w
he
n
a
pp
li
e
d
to
hy
dr
o
pon
ic
d
a
t
a
,
hi
ghl
ig
h
ti
n
g t
h
e
n
e
e
d
f
or
m
or
e
a
d
a
p
ti
ve
a
n
d
opt
im
i
z
e
d
a
p
pr
o
a
c
h
e
s
.
I
n
c
ont
r
a
s
t,
our
pr
opo
s
e
d
E
A
-
opt
im
i
z
e
d
e
n
s
e
m
bl
e
f
r
a
m
e
w
or
k
ove
r
c
om
e
s
th
e
s
e
li
m
it
a
ti
on
s
by
dyna
m
i
c
a
ll
y
a
dj
us
ti
ng
m
o
de
l
w
e
ig
ht
s
,
r
e
s
ul
ti
n
g
in
hi
gh
e
r
pr
e
d
ic
ti
ve
a
c
c
ur
a
c
y,
r
ob
us
tn
e
s
s
,
a
nd
in
t
e
r
pr
e
ta
bi
li
ty
.
T
he
im
pr
ov
e
m
e
nt
s
a
r
e
s
uppor
t
e
d
b
y
th
e
lo
w
e
r
R
M
S
E
a
nd M
A
E
s
c
or
e
s
,
de
m
ons
tr
a
ti
ng
th
e
e
f
f
e
c
ti
ve
n
e
s
s
of
t
he
opt
im
iz
a
ti
on pr
oc
e
s
s
. C
om
pa
r
e
d t
o
c
onv
e
nt
io
na
l
a
ppr
o
a
c
h
e
s
,
ou
r
m
e
th
od o
pt
im
a
ll
y i
nt
e
gr
a
t
e
s
m
ul
ti
pl
e
m
od
e
ls
,
e
ns
ur
i
ng gr
e
a
t
e
r
s
t
a
bi
li
t
y a
n
d i
m
pr
ov
e
d g
e
n
e
r
a
li
z
a
ti
o
n a
c
r
os
s
di
v
e
r
s
e
da
t
a
s
e
t
s
[
29]
.
A
ddi
ti
ona
ll
y,
e
xpl
a
in
a
bi
li
ty
ha
s
be
e
n
la
r
ge
ly
ove
r
lo
oke
d
i
n
pr
e
vi
ous
hydr
oponic
f
or
e
c
a
s
ti
ng
r
e
s
e
a
r
c
h.
U
nl
ik
e
e
a
r
li
e
r
s
tu
di
e
s
th
a
t
f
oc
us
e
d
s
ol
e
ly
on
pr
e
di
c
ti
on
a
c
c
ur
a
c
y,
our
w
or
k
in
c
or
por
a
te
s
L
I
M
E
to
e
nha
nc
e
m
ode
l
tr
a
ns
pa
r
e
n
c
y.
R
a
z
a
k
e
t
al
.
[
30]
hi
ghl
ig
ht
e
d,
e
xpl
a
in
a
bl
e
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
(
X
A
I
)
is
c
r
uc
ia
l
f
or
a
gr
ic
ul
tu
r
a
l
de
c
is
io
n
-
m
a
ki
ng, a
s
i
t
a
ll
ow
s
s
ta
ke
hol
de
r
s
t
o un
de
r
s
ta
nd t
he
r
a
ti
ona
le
be
hi
nd pr
e
di
c
ti
ons
. O
u
r
f
r
a
m
e
w
or
k
e
ns
ur
e
s
th
a
t
m
ode
l
out
put
s
a
r
e
not
onl
y
a
c
c
ur
a
te
but
a
ls
o
in
te
r
pr
e
ta
bl
e
,
m
a
ki
ng
it
pr
a
c
ti
c
a
l
f
or
r
e
a
l
-
w
or
ld
i
m
pl
e
m
e
nt
a
ti
on.
3.4.
I
m
p
li
c
at
io
n
s
f
o
r
s
u
s
t
ai
n
ab
le
p
r
ac
t
ic
e
s
T
h
e
p
r
o
p
o
s
e
d
f
r
a
m
e
w
or
k
c
o
n
tr
i
b
ut
e
s
t
o
s
u
s
t
a
i
n
a
b
l
e
a
gr
i
c
ul
t
ur
a
l
p
r
a
c
t
i
c
e
s
b
y
u
t
i
li
z
i
n
g
a
d
v
a
n
c
e
d
p
r
e
di
c
t
i
ve
a
n
a
l
y
t
i
c
s
.
I
m
pr
o
v
e
d
f
or
e
c
a
s
t
i
ng
c
a
p
a
b
il
i
ti
e
s
e
n
a
b
l
e
b
e
t
t
e
r
s
t
o
c
k
m
a
n
a
g
e
m
e
n
t
,
w
a
s
t
e
r
e
du
c
t
i
on
,
a
n
d
s
up
p
o
r
t
s
m
a
ll
-
s
c
a
l
e
h
y
dr
o
p
on
i
c
f
a
r
m
e
r
s
i
n
m
a
ki
n
g
i
nf
or
m
e
d
d
e
c
i
s
i
on
s
.
B
y
i
nt
e
g
r
a
ti
n
g
m
a
c
hi
n
e
l
e
a
r
ni
n
g
a
n
d
E
A
-
b
a
s
e
d
o
p
t
i
m
i
z
a
t
i
on
,
t
h
e
f
r
a
m
e
w
o
r
k
e
n
h
a
n
c
e
s
e
f
f
i
c
i
e
n
c
y
a
n
d
a
d
a
pt
a
b
il
i
t
y
i
n
a
g
r
i
c
u
l
t
ur
a
l
o
p
e
r
a
t
io
n
s
.
A
k
e
y
c
o
nt
r
ib
u
t
io
n
o
f
t
h
i
s
f
r
a
m
e
w
or
k
i
s
it
s
a
l
i
g
nm
e
n
t
w
it
h
S
D
G
s
.
I
t
s
u
pp
o
r
t
s
S
D
G
12
.
3
(
r
e
d
u
c
i
ng
f
oo
d
w
a
s
t
e
)
by
o
p
ti
m
i
z
i
n
g
s
t
o
c
k
m
a
n
a
g
e
m
e
n
t,
w
hi
c
h
m
i
n
im
i
z
e
s
o
v
e
r
p
r
o
d
u
c
ti
o
n
a
n
d
s
p
oi
l
a
g
e
.
B
y
p
r
o
vi
d
in
g
m
o
r
e
a
c
c
u
r
a
t
e
p
r
e
d
i
c
t
io
n
s
of
s
u
p
pl
y
a
n
d
d
e
m
a
n
d,
t
h
e
s
y
s
t
e
m
h
e
lp
s
r
e
d
u
c
e
u
n
n
e
c
e
s
s
a
r
y
r
e
s
o
ur
c
e
c
o
n
s
um
p
t
i
on
a
n
d
f
i
n
a
n
c
i
a
l
l
o
s
s
e
s
.
F
ur
th
e
r
m
or
e
,
th
e
f
r
a
m
e
w
or
k
c
ont
r
ib
ut
e
s
to
S
D
G
9.3
(
s
uppor
ti
ng
s
m
a
ll
-
s
c
a
le
f
a
r
m
e
r
s
)
by
pr
ovi
di
ng
da
ta
-
dr
iv
e
n
de
c
is
io
n
-
m
a
ki
ng
to
ol
s
.
T
he
s
e
to
ol
s
e
m
pow
e
r
f
a
r
m
e
r
s
w
it
h
a
c
ti
ona
bl
e
in
s
ig
ht
s
,
a
ll
ow
in
g
th
e
m
to
m
a
ke
m
or
e
s
tr
a
te
gi
c
de
c
is
io
ns
a
nd
c
om
pe
te
m
or
e
e
f
f
e
c
ti
ve
ly
i
n
th
e
m
a
r
ke
t.
W
it
h
im
pr
ove
d
f
or
e
c
a
s
ti
ng
a
nd
in
ve
nt
or
y c
ont
r
ol
, s
m
a
ll
-
s
c
a
le
hydr
oponic
f
a
r
m
e
r
s
c
a
n e
nha
nc
e
pr
oduc
ti
vi
ty
a
nd r
e
duc
e
ope
r
a
ti
ona
l
r
is
ks
.
A
ddi
ti
ona
ll
y,
th
e
f
r
a
m
e
w
or
k
a
dva
nc
e
s
S
D
G
12.C
(
im
pr
ov
in
g
r
e
s
our
c
e
e
f
f
ic
ie
nc
y
)
by
f
os
te
r
in
g
e
f
f
ic
ie
nt
r
e
s
our
c
e
us
e
.
B
y
opt
im
iz
in
g
a
gr
ic
ul
tu
r
a
l
pr
oc
e
s
s
e
s
,
it
e
ns
ur
e
s
th
a
t
r
e
s
our
c
e
s
s
u
c
h
a
s
w
a
t
e
r
,
nut
r
ie
nt
s
,
a
nd
e
ne
r
gy
a
r
e
ut
il
iz
e
d
e
f
f
e
c
ti
ve
ly
.
T
hi
s
c
ont
r
ib
ut
e
s
to
a
m
o
r
e
s
us
ta
in
a
bl
e
a
ppr
oa
c
h
to
hydr
oponic
f
a
r
m
in
g,
r
e
duc
in
g
e
nvi
r
onm
e
nt
a
l
im
pa
c
t
w
hi
le
e
nha
nc
in
g
pr
oduc
ti
vi
ty
.
O
ve
r
a
ll
,
th
e
pr
opos
e
d
f
r
a
m
e
w
or
k
pr
om
ot
e
s
da
ta
-
dr
iv
e
n
a
gr
ic
ul
tu
r
e
by
im
p
r
ovi
ng
e
f
f
ic
ie
nc
y,
pr
oduc
ti
vi
ty
,
a
nd
s
us
ta
in
a
bi
li
ty
.
B
y
m
in
im
iz
in
g
in
e
f
f
ic
ie
nc
ie
s
a
nd f
a
c
il
it
a
ti
ng be
tt
e
r
de
c
is
io
n
-
m
a
ki
ng, i
t
be
ne
f
it
s
i
ndi
vi
dua
l
f
a
r
m
e
r
s
a
nd c
ont
r
ib
ut
e
s
t
o br
oa
de
r
s
us
ta
in
a
bi
li
ty
e
f
f
or
ts
i
n
a
gr
ic
ul
tu
r
a
l
pr
a
c
ti
c
e
s
[
31]
.
4.
C
O
N
C
L
U
S
I
O
N
T
h
is
s
t
ud
y
de
m
on
s
tr
a
te
s
th
e
e
f
f
e
c
ti
v
e
n
e
s
s
of
a
n
o
pt
i
m
i
z
e
d
e
n
s
e
m
bl
e
f
r
a
m
e
w
or
k
c
o
m
bi
ni
n
g
L
R
,
R
F
,
a
nd
X
G
B
oo
s
t
m
o
de
l
s
,
r
e
f
i
ne
d
t
hr
o
ugh
E
A
-
ba
s
e
d
w
e
ig
ht
opt
im
iz
a
ti
on,
f
or
a
c
c
ur
a
t
e
ly
f
or
e
c
a
s
ti
ng
hy
dr
o
pon
ic
s
t
oc
k
a
nd
s
a
le
s
.
B
y
in
te
gr
a
ti
n
g
L
I
M
E
,
t
he
f
r
a
m
e
w
or
k
a
l
s
o
e
nh
a
n
c
e
s
m
o
de
l
in
te
r
pr
e
ta
bi
l
it
y
,
e
m
po
w
e
r
in
g
in
f
or
m
e
d
d
e
c
i
s
io
n
-
m
a
ki
ng
.
T
h
e
i
m
pr
ov
e
d
pr
e
di
c
ti
ve
a
c
c
ur
a
c
y
ha
s
s
i
gn
if
i
c
a
nt
i
m
pl
ic
a
t
io
n
s
f
or
s
m
a
l
l
-
s
c
a
l
e
hydr
opo
ni
c
f
a
r
m
e
r
s
,
s
u
pp
or
ti
ng
b
e
tt
e
r
i
nv
e
nt
or
y
m
a
n
a
g
e
m
e
nt
,
w
a
s
t
e
r
e
d
uc
ti
o
n,
a
nd
r
e
s
ou
r
c
e
op
ti
m
i
z
a
ti
on
,
w
hi
c
h
a
li
g
n w
it
h s
u
s
ta
in
a
bl
e
a
g
r
ic
ul
t
ur
e
p
r
a
c
ti
c
e
s
a
nd
c
on
tr
ib
ut
e
t
o a
c
hi
e
vi
ng
th
e
S
D
G
s
.
F
ut
ur
e
w
or
k
w
il
l
f
o
c
u
s
on
i
n
c
or
p
or
a
ti
ng
r
e
a
l
-
t
im
e
d
a
t
a
a
n
d
a
d
a
p
ti
v
e
m
od
e
l
in
g
t
e
c
hn
iq
u
e
s
t
o
f
u
r
th
e
r
im
pr
ov
e
f
or
e
c
a
s
ti
ng
pe
r
f
or
m
a
n
c
e
,
r
e
s
po
n
s
iv
e
n
e
s
s
,
a
n
d
th
e
o
ve
r
a
l
l
e
f
f
e
c
ti
v
e
n
e
s
s
of
t
he
s
y
s
t
e
m
in
dy
na
m
ic
a
gr
i
c
ul
tu
r
a
l
e
nvi
r
onm
e
n
t
s
.
A
C
K
N
O
WL
E
D
G
M
E
N
T
S
T
he
a
ut
hor
s
gr
a
te
f
ul
ly
a
c
knowle
dge
th
e
va
lu
a
bl
e
f
e
e
dba
c
k
pr
ovi
de
d
by
c
ol
le
a
gue
s
dur
in
g
th
e
pr
e
pa
r
a
ti
on
of
th
is
m
a
nu
s
c
r
ip
t.
S
pe
c
ia
l
a
ppr
e
c
ia
ti
on
i
s
a
l
s
o
e
xt
e
nde
d
to
th
e
U
ni
ve
r
s
it
y
of
P
a
la
ngka
R
a
ya
f
or
it
s
a
c
a
de
m
ic
s
uppor
t
a
nd t
he
pr
ovi
s
io
n of
r
e
s
e
a
r
c
h f
a
c
il
it
ie
s
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
T
hi
s
r
e
s
e
a
r
c
h di
d not r
e
c
e
iv
e
a
ny
s
pe
c
if
ic
gr
a
nt
f
r
om
a
ny f
undi
ng a
ge
nc
y.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
5
,
O
c
to
be
r
2025
:
3879
-
3886
3884
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
V
ik
to
r
H
a
ndr
ia
nus
P
r
a
na
ta
w
ij
a
ya
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
e
s
s
a
P
r
is
ki
la
✓
✓
✓
✓
✓
✓
P
ut
u B
a
gus
A
di
dya
na
A
nugr
a
h P
ut
r
a
✓
✓
✓
✓
✓
✓
N
o
v
a
N
oo
r
K
a
m
a
la
S
a
r
i
✓
✓
✓
✓
✓
✓
E
f
r
a
ns
C
hr
is
ti
a
n
✓
✓
✓
✓
✓
✓
S
e
pt
ia
n G
e
ge
s
✓
✓
✓
✓
✓
✓
N
ove
r
a
K
r
is
ti
a
nt
i
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
T
he
a
ut
hor
s
s
t
a
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
I
N
F
O
R
M
E
D
C
O
N
S
E
N
T
T
he
r
e
w
e
r
e
no huma
n
s
ubj
e
c
ts
.
E
T
H
I
C
A
L
A
P
P
R
O
V
A
L
T
he
r
e
w
e
r
e
no a
ni
m
a
l
s
ubj
e
c
ts
.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
s
e
t
ut
il
iz
e
d
in
th
is
s
tu
dy
c
a
n
be
a
c
c
e
s
s
e
d
a
t
:
ht
tp
s
:/
/d
r
iv
e
.google
.c
om
/d
r
iv
e
/f
ol
de
r
s
/1
-
F
nI
bX
qm
kB
F
C
r
R
1S
L
lF
m
I
N
jDa
R
F
x04Od?
us
p=
s
h
a
r
in
g.
R
E
F
E
R
E
N
C
E
S
[
1]
Y
.
L
i
u,
X
.
P
a
n,
a
nd
J
.
L
i
,
“
C
ur
r
e
nt
a
gr
i
c
ul
t
ur
a
l
pr
a
c
t
i
c
e
s
t
hr
e
a
t
e
n
f
ut
ur
e
gl
oba
l
f
ood
pr
oduc
t
i
on
,”
J
our
nal
of
A
gr
i
c
ul
t
ur
al
and
E
nv
i
r
onm
e
nt
al
E
t
hi
c
s
, vol
. 28, no. 2, pp. 203
–
216, A
pr
. 2015, doi
:
10.1007/
s
10806
-
014
-
9527
-
6.
[
2]
A
.
W
e
z
e
l
a
nd
E
.
S
i
l
va
,
“
A
gr
oe
c
ol
ogy
a
nd
a
gr
oe
c
ol
ogi
c
a
l
c
r
oppi
ng
pr
a
c
t
i
c
e
s
,”
i
n
A
gr
oe
c
ol
ogi
c
al
P
r
ac
t
i
c
e
s
F
or
Sus
t
ai
nabl
e
A
gr
i
c
ul
t
ur
e
:
P
r
i
nc
i
pl
e
s
,
A
ppl
i
c
at
i
ons
,
A
nd
M
ak
i
ng
T
he
T
r
an
s
i
t
i
on
,
W
or
l
d
S
c
i
e
nt
i
f
i
c
(
E
ur
ope
)
,
2017,
pp.
19
–
51
,
doi
:
10.1142/
9781786343062_0002.
[
3]
T
. F
r
i
e
dr
i
c
h a
nd A
. K
a
s
s
a
m
,
“
F
ood s
e
c
ur
i
t
y a
s
a
f
unc
t
i
on of
s
us
t
a
i
na
bl
e
i
nt
e
n
s
i
f
i
c
a
t
i
on of
c
r
op pr
oduc
t
i
on
,”
A
I
M
S A
gr
i
c
ul
t
ur
e
and
F
ood
, vol
. 1, no. 2, pp. 227
–
238, 2016, doi
:
10.3934/
a
gr
f
ood.2016.2.227.
[
4]
A
.
R
e
hm
a
n
a
nd
M
.
F
a
r
ooq,
“
C
ha
l
l
e
nge
s
,
c
ons
t
r
a
i
nt
s
,
a
nd
oppor
t
uni
t
i
e
s
i
n
s
us
t
a
i
na
bl
e
a
gr
i
c
ul
t
ur
e
a
nd
e
nvi
r
onm
e
nt
,”
i
n
Sus
t
ai
nabl
e
A
gr
i
c
ul
t
ur
e
and t
he
E
nv
i
r
onm
e
nt
, E
l
s
e
vi
e
r
, 2023, pp. 487
–
501
,
doi
:
10.1016/
B
978
-
0
-
323
-
90500
-
8.00012
-
9.
[
5]
N
.
A.
T
ha
i
pa
r
a
m
bi
l
a
nd
V
.
R
a
dha
kr
i
s
hna
n,
“
C
h
a
l
l
e
nge
s
i
n
a
c
hi
e
vi
ng
a
n
e
c
on
om
i
c
a
l
l
y
s
us
t
a
i
n
a
bl
e
a
qu
a
poni
c
s
ys
t
e
m
:
a
r
e
vi
e
w
,
”
A
quac
ul
t
ur
e
I
nt
e
r
nat
i
onal
, vol
. 30, no. 6, pp. 3035
–
3066, D
e
c
. 2022, doi
:
10.1007/
s
10499
-
022
-
00946
-
z.
[
6]
K
.
J
.
W
a
l
t
e
r
s
,
B
.
K
.
B
e
h
e
,
C
.
J
.
C
ur
r
e
y,
a
nd
R
.
G
.
L
ope
z
,
“
H
i
s
t
or
i
c
a
l
,
c
ur
r
e
nt
,
a
nd
f
ut
ur
e
pe
r
s
pe
c
t
i
ve
s
f
or
c
ont
r
ol
l
e
d
e
nvi
r
o
nm
e
nt
hydr
oponi
c
f
ood
c
r
op
pr
oduc
t
i
on
i
n
t
he
U
ni
t
e
d
S
t
a
t
e
s
,”
H
or
t
Sc
i
e
nc
e
,
vol
.
55,
no.
6,
pp.
758
–
767,
J
un.
2020,
doi
:
10.21273/
H
O
R
T
S
C
I
14901
-
20.
[
7]
S
.
R
.
S
a
t
hya
na
r
a
ya
na
,
W
.
V
.
G
a
nga
dha
r
,
M
.
G
.
B
a
dr
i
na
t
h,
R
.
M
.
R
a
vi
ndr
a
,
a
nd
A
.
U
.
S
hr
i
r
a
m
r
a
o,
“
H
ydr
oponi
c
s
:
a
n
i
nt
e
ns
i
f
i
e
d
a
gr
i
c
ul
t
ur
e
pr
a
c
t
i
c
e
t
o
i
m
pr
ove
f
ood
pr
oduc
t
i
on
,”
R
e
v
i
e
w
s
i
n
A
gr
i
c
ul
t
ur
al
Sc
i
e
nc
e
,
vol
.
10,
pp.
101
–
114,
2022,
doi
:
10.7831/
r
a
s
.10.0_101.
[
8]
T
.
A
l
ka
dr
i
,
D
.
R
ukm
a
na
,
a
nd
N
.
H
a
m
i
d,
“
H
ydr
oponi
c
ve
ge
t
a
bl
e
a
gr
i
bus
i
ne
s
s
bus
i
ne
s
s
de
ve
l
opm
e
nt
s
t
r
a
t
e
gy
(
c
a
s
e
s
t
udy
i
n
C
V
.
A
ka
r
H
ydr
oponi
c
s
M
onc
ongl
oe
S
ubdi
s
t
r
i
c
t
,
M
a
r
os
D
i
s
t
r
i
c
t
)
,”
I
O
P
C
onf
e
r
e
n
c
e
Se
r
i
e
s
:
E
ar
t
h
and
E
nv
i
r
onm
e
nt
al
Sc
i
e
nc
e
,
vol
.
1230, no. 1, S
e
p. 2023, doi
:
10.1088/
1755
-
1315/
1230/
1/
012050.
[
9]
Y
.
Z
ha
ng,
B
.
L
i
u,
a
nd
J
.
Y
u,
“
A
s
e
l
e
c
t
i
ve
e
ns
e
m
bl
e
l
e
a
r
ni
ng
a
ppr
oa
c
h
ba
s
e
d
on
e
vol
ut
i
ona
r
y
a
l
gor
i
t
hm
,”
J
our
nal
of
I
n
t
e
l
l
i
ge
nt
and F
uz
z
y
Sy
s
t
e
m
s
, vol
. 32, no. 3, pp. 2365
–
2373, F
e
b. 2017, doi
:
10.3233/
J
I
F
S
-
16332.
[
10]
T
.
va
n
K
l
om
pe
nbur
g,
A
.
K
a
s
s
a
hun,
a
nd
C
.
C
a
t
a
l
,
“
C
r
op
yi
e
l
d
pr
e
di
c
t
i
on
u
s
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng:
a
s
ys
t
e
m
a
t
i
c
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
,
”
C
om
put
e
r
s
and E
l
e
c
t
r
oni
c
s
i
n A
gr
i
c
ul
t
ur
e
, vol
. 177
, O
c
t
. 2020, doi
:
10.1016/
j
.c
om
pa
g.2020.105709.
[
11]
M
. J
a
va
i
d, A
.
H
a
l
e
e
m
,
I
. H
. K
h
a
n, a
nd
R
. S
um
a
n,
“
U
nde
r
s
t
a
ndi
ng
t
he
pot
e
nt
i
a
l
a
ppl
i
c
a
t
i
ons
of
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
i
n
a
gr
i
c
ul
t
ur
e
s
e
c
t
o
r
,”
A
dv
anc
e
d A
gr
oc
he
m
, vol
. 2, no. 1, pp. 15
–
30,
M
a
r
. 2023, doi
:
10.1016/
j
.a
a
c
.2022.10.001.
[
12]
S
.
C
a
r
pi
t
e
l
l
a
,
M
.
I
nui
guc
hi
,
V
.
K
r
a
t
oc
hví
l
,
a
nd
M
.
P
i
š
t
ě
k,
“
M
ul
t
i
-
c
r
i
t
e
r
i
a
de
c
i
s
i
on
a
na
l
ys
i
s
w
i
t
hout
c
ons
i
s
t
e
n
c
y
i
n
pa
i
r
w
i
s
e
c
om
pa
r
i
s
ons
,”
C
om
put
e
r
s
and I
ndu
s
t
r
i
al
E
ngi
ne
e
r
i
ng
, vol
. 168, J
un. 2022, doi
:
10.1016/
j
.c
i
e
.2022.108089.
[
13]
S
.
B
a
r
a
t
,
T
.
C
l
a
r
k,
B
.
B
a
r
n,
a
nd
V
.
K
ul
ka
r
ni
,
“
A
s
i
m
ul
a
t
i
on
ba
s
e
d
a
i
d
f
o
r
c
om
pl
e
x
dyna
m
i
c
de
c
i
s
i
on
m
a
ki
ng,”
i
n
C
E
U
R
W
or
k
s
hop P
r
oc
e
e
di
ng
s
, 2016, vol
. 1765, pp. 22
–
31.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
O
pt
imi
z
e
d e
ns
e
m
bl
e
f
r
am
e
w
or
k
f
o
r
pr
e
di
c
ti
ng hy
dr
oponic
s
to
c
k
and
…
(
V
ik
to
r
H
andr
ia
nus
P
r
anat
aw
ij
ay
a
)
3885
[
14]
N
.
K
.
C
houdha
r
y,
S
.
S
.
L
.
C
hukka
pa
l
l
i
,
S
.
M
i
t
t
a
l
,
M
.
G
upt
a
,
M
.
A
bd
e
l
s
a
l
a
m
,
a
nd
A
.
J
os
hi
,
“
Y
i
e
l
dP
r
e
di
c
t
:
a
c
r
op
yi
e
l
d
pr
e
di
c
t
i
on
f
r
a
m
e
w
or
k
f
o
r
s
m
a
r
t
f
a
r
m
s
,”
i
n
P
r
oc
e
e
di
ngs
-
2020
I
E
E
E
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
B
i
g
D
at
a,
B
i
g
D
at
a
2020
,
D
e
c
.
2020,
pp.
2340
–
2349
,
doi
:
10.1109/
B
i
gD
a
t
a
50022.2020.9377832.
[
15]
E
.
S
a
be
e
h
a
nd
M
.
Z
.
A
l
-
T
a
i
e
,
“
E
nha
nc
i
ng
a
gr
i
c
ul
t
u
r
a
l
de
c
i
s
i
on
-
m
a
ki
ng
t
hr
oug
h
da
t
a
a
na
l
ys
i
s
:
pr
e
di
c
t
i
ng
c
r
op
he
a
l
t
h
out
c
om
e
s
,
”
B
I
O
W
e
b of
C
onf
e
r
e
nc
e
s
, vol
. 97, A
pr
. 2024, doi
:
10.1051/
bi
oc
onf
/
20249700013.
[
16]
V
.
M
a
n
e
,
A
.
G
a
j
b
h
i
ye
,
A
m
i
s
ha
,
C
.
D
e
s
h
m
u
kh
,
a
n
d
K
.
G
a
i
k
w
a
d
,
“
K
r
i
s
h
i
m
i
t
r
a
:
c
r
o
p
a
n
d
f
e
r
t
i
l
i
z
e
r
r
e
c
o
m
m
e
n
da
t
i
o
ns
s
ys
t
e
m
us
i
n
g
m
a
c
hi
ne
l
e
a
r
n
i
n
g
a
l
go
r
i
t
h
m
,
”
i
n
L
e
c
t
ur
e
N
o
t
e
s
i
n
N
e
t
w
or
k
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
7
5
,
2
0
2
3,
p
p
.
30
9
–
317
,
d
o
i
:
1
0
.
1
00
7
/
9
7
8
-
981
-
19
-
2
84
0
-
6
_
24
.
[
17]
J
.
R
a
j
put
e
t
al
.
,
“
A
s
s
e
s
s
m
e
nt
of
d
a
t
a
i
nt
e
l
l
i
ge
nc
e
a
l
gor
i
t
hm
s
i
n
m
ode
l
i
ng
da
i
l
y
r
e
f
e
r
e
nc
e
e
va
pot
r
a
ns
pi
r
a
t
i
on
unde
r
i
nput
da
t
a
l
i
m
i
t
a
t
i
on
s
c
e
na
r
i
os
i
n
s
e
m
i
-
a
r
i
d
c
l
i
m
a
t
i
c
c
ondi
t
i
on,”
W
at
e
r
Sc
i
e
nc
e
and
T
e
c
h
nol
ogy
,
vol
.
87,
no.
10,
pp.
2504
–
2528,
M
a
y
2023,
doi
:
10.2166/
w
s
t
.2023.137.
[
18]
M
.
S
ha
hhos
s
e
i
ni
,
G
.
H
u,
I
.
H
ube
r
,
a
nd
S
.
V
.
A
r
c
hont
oul
i
s
,
“
C
oupl
i
ng
m
a
c
hi
n
e
l
e
a
r
ni
ng
a
nd
c
r
op
m
ode
l
i
ng
i
m
pr
ove
s
c
r
op
yi
e
l
d
pr
e
di
c
t
i
on i
n t
he
U
S
C
or
n B
e
l
t
,”
Sc
i
e
nt
i
f
i
c
R
e
por
t
s
, vol
. 11, no. 1, J
a
n. 2021, doi
:
10.1038/
s
41598
-
020
-
80820
-
1.
[
19]
G
.
P
i
l
l
one
t
t
o, T
.
C
he
n,
A
.
C
hi
us
o,
G
.
D.
N
i
c
ol
a
o,
a
nd
L
.
L
j
ung,
“
R
e
gul
a
r
i
z
a
t
i
on
of
l
i
ne
a
r
r
e
gr
e
s
s
i
on
m
ode
l
s
,”
i
n
C
om
m
uni
c
at
i
ons
and C
ont
r
ol
E
ngi
ne
e
r
i
ng
, 2022, pp. 33
–
93
,
doi
:
10.1007/
978
-
3
-
030
-
95860
-
2_3.
[
20]
T
.
C
ha
i
a
nd
R
.
R
.
D
r
a
xl
e
r
,
“
R
oot
m
e
a
n
s
qua
r
e
e
r
r
or
(
R
M
S
E
)
or
m
e
a
n
a
bs
ol
ut
e
e
r
r
or
(
M
A
E
)
?
-
a
r
gum
e
nt
s
a
ga
i
ns
t
a
voi
di
ng
R
M
S
E
i
n t
he
l
i
t
e
r
a
t
ur
e
,”
G
e
os
c
i
e
nt
i
f
i
c
M
ode
l
D
e
v
e
l
opm
e
nt
, vol
. 7, no. 3, pp. 1247
–
125
0, J
un. 2014, doi
:
10.5194/
gm
d
-
7
-
1247
-
2014.
[
21]
T
.
O
.
H
ods
on,
“
R
oot
-
m
e
a
n
-
s
qua
r
e
e
r
r
or
(
R
M
S
E
)
o
r
m
e
a
n
a
bs
ol
ut
e
e
r
r
or
(
M
A
E
)
:
w
he
n
t
o
us
e
t
he
m
or
not
,”
G
e
os
c
i
e
nt
i
f
i
c
M
ode
l
D
e
v
e
l
opm
e
nt
, vol
. 15, no. 14, pp. 5481
–
5487, J
ul
. 2022, doi
:
10.5194/
gm
d
-
15
-
5481
-
2022.
[
22]
T
.
Z
hu,
“
A
na
l
ys
i
s
on
t
he
a
ppl
i
c
a
bi
l
i
t
y
of
t
he
r
a
ndom
f
or
e
s
t
,”
J
our
nal
of
P
hy
s
i
c
s
:
C
onf
e
r
e
n
c
e
Se
r
i
e
s
,
vol
.
1607,
no.
1,
A
ug.
2020
,
doi
:
10.1088/
1742
-
6596/
1607/
1/
012123.
[
23]
P
.
N
a
w
r
oc
ki
a
nd
M
.
S
m
e
ndow
s
ki
,
“
L
ong
-
t
e
r
m
pr
e
di
c
t
i
on
of
c
l
oud
r
e
s
our
c
e
u
s
a
ge
i
n
hi
gh
-
pe
r
f
or
m
a
nc
e
c
om
put
i
ng
,”
i
n
L
e
c
t
u
r
e
N
ot
e
s
i
n
C
om
put
e
r
Sc
i
e
n
c
e
(
i
nc
l
udi
ng
s
ubs
e
r
i
e
s
L
e
c
t
ur
e
N
ot
e
s
i
n
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
and L
e
c
t
u
r
e
N
ot
e
s
i
n B
i
oi
nf
or
m
at
i
c
s
)
, vol
.
14074 L
N
C
S
, 2023, pp. 532
–
546
,
doi
:
10.1007/
978
-
3
-
031
-
36021
-
3_53.
[
24]
A
.
A
l
s
uba
yhi
n,
M
.
S
.
R
a
m
z
a
n,
a
nd
B
.
A
l
z
a
hr
a
ni
,
“
C
r
i
m
e
pr
e
di
c
t
i
on
m
ode
l
us
i
ng
t
hr
e
e
c
l
a
s
s
i
f
i
c
a
t
i
on
t
e
c
hni
que
s
:
r
a
ndom
f
or
e
s
t
,
l
ogi
s
t
i
c
r
e
gr
e
s
s
i
on
,
a
nd
L
i
ght
G
B
M
,
”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
dv
anc
e
d
C
om
put
e
r
Sc
i
e
nc
e
and
A
ppl
i
c
at
i
ons
,
vol
.
15,
no.
1,
pp.
240
–
251, 2024, doi
:
10.14569/
I
J
A
C
S
A
.2024.0150123.
[
25]
R
. P
. E
t
hi
r
a
j
a
nd K
. P
a
r
a
nj
ot
hi
, “
A
de
e
p
l
e
a
r
ni
ng
-
ba
s
e
d
a
ppr
oa
c
h f
or
e
a
r
l
y de
t
e
c
t
i
on of
di
s
e
a
s
e
i
n s
ug
a
r
c
a
ne
pl
a
nt
s
:
a
n e
xpl
a
i
na
bl
e
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
m
ode
l
,”
I
A
E
S
I
nt
e
r
nat
i
onal
J
our
nal
of
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
g
e
nc
e
,
vol
.
13,
no.
1,
pp.
974
–
983,
M
a
r
.
2024,
doi
:
10.11591/
i
j
a
i
.v13.i
1.pp974
-
983.
[
26]
D
.
A
.
G
z
a
r
,
A
.
M
.
M
a
hm
ood,
a
nd
M
.
K
.
A
bba
s
,
“
A
c
om
pa
r
a
t
i
ve
s
t
udy
of
r
e
gr
e
s
s
i
on
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
:
t
r
a
de
of
f
be
t
w
e
e
n
a
c
c
ur
a
c
y
a
nd
c
om
put
a
t
i
ona
l
c
om
pl
e
xi
t
y
,”
M
at
he
m
at
i
c
al
M
ode
l
l
i
ng
o
f
E
ngi
ne
e
r
i
ng
P
r
obl
e
m
s
,
vol
.
9,
no.
5,
pp.
1217
–
1224, D
e
c
. 2022, doi
:
10.18280/
m
m
e
p.090508.
[
27]
K
.
W
e
i
e
t
al
.
,
“
E
xpl
a
i
na
bl
e
de
e
p
l
e
a
r
ni
ng
s
t
udy
f
o
r
l
e
a
f
di
s
e
a
s
e
c
l
a
s
s
i
f
i
c
a
t
i
on
,”
A
gr
onom
y
,
vol
.
12,
no.
5,
A
p
r
.
2022,
doi
:
10.3390/
a
gr
onom
y12051035.
[
28]
G
.
I
doj
e
,
C
.
M
our
out
ogl
ou,
T
.
D
a
gi
ukl
a
s
,
A
.
K
ot
s
i
r
a
s
,
I
.
M
udde
s
a
r
,
a
nd
P
.
A
l
e
f
r
a
gki
s
,
“
C
om
pa
r
a
t
i
ve
a
na
l
ys
i
s
of
da
t
a
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
a
l
gor
i
t
hm
s
:
a
hydr
oponi
c
s
s
ys
t
e
m
us
e
c
a
s
e
,”
Sm
ar
t
A
g
r
i
c
ul
t
ur
al
T
e
c
hnol
ogy
,
vol
.
4,
A
ug.
2023,
doi
:
10.1016/
j
.a
t
e
c
h.2023.100207.
[
29]
J
.
T
.
D
.
S
ouz
a
,
A
.
C
.
D
.
F
r
a
nc
i
s
c
o,
C
.
M
.
P
i
e
ka
r
s
ki
,
G
.
F
.
D
.
P
r
a
do,
a
nd
L
.
G
.
D
.
O
l
i
ve
i
r
a
,
“
D
a
t
a
m
i
ni
ng
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng
i
n
t
he
c
ont
e
xt
of
s
us
t
a
i
na
bl
e
e
va
l
ua
t
i
on:
a
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
,”
I
E
E
E
L
a
t
i
n
A
m
e
r
i
c
a
T
r
ans
ac
t
i
ons
,
vol
.
17,
no.
3,
pp.
372
–
382,
M
a
r
.
2019, doi
:
10.1109/
T
L
A
.2019.8863307.
[
30]
S
.
F
.
A
.
R
a
z
a
k,
S
.
Y
oga
r
a
ya
n,
M
.
S
.
S
a
ye
e
d,
a
nd
M
.
I
.
F
.
M
.
D
e
r
a
f
i
,
“
A
gr
i
c
ul
t
ur
e
5.0
a
nd
e
xpl
a
i
na
bl
e
A
I
f
or
s
m
a
r
t
a
gr
i
c
ul
t
ur
e
:
a
s
c
opi
ng r
e
vi
e
w
,”
E
m
e
r
gi
ng Sc
i
e
n
c
e
J
our
nal
, vol
. 8, no. 2, pp. 744
–
760, A
pr
. 20
24, doi
:
10.28991/
E
S
J
-
2024
-
08
-
02
-
024.
[
31]
S
.
A
hm
e
d,
S
.
M
a
da
ni
a
n,
F
.
M
i
r
z
a
,
a
nd
S
.
Z
a
i
m
,
“
P
r
e
di
c
t
i
on
of
na
t
ur
a
l
ga
s
c
ons
um
pt
i
on
i
n
B
a
h
ç
e
ş
e
hi
r
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
n
g
m
ode
l
s
,”
A
C
I
S 2020 P
r
oc
e
e
di
ngs
-
31s
t
A
us
t
r
al
a
s
i
an C
onf
e
r
e
nc
e
on I
nf
or
m
at
i
on
Sy
s
t
e
m
s
, 2020.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Viktor
Handrianus
Pranatawijaya
received
the
M.T.
degree
in
Informatics
Engineering
from
Atma
Jaya
Yogyakarta
University,
Indonesia,
in
2008.
He
is
currently
teaching
in
the
Informatic
s
Engineerin
g
D
epartment
at
Palangka
R
aya
Universi
ty.
He
is
a
member
of
the
Association
of
Higher
Education
in
Informati
cs
and
Computers
(APTIKOM).
His
current
research
interests
are
software
engineering
and
artificial
intelligence
.
He
can
be
contacted
at email
:
viktorhp@
it.upr.ac.id.
Ressa
Priskila
received
the
M.T.
degree
in
Informatics
Engineeri
ng
from
Atma
Jaya
Yogyakarta
University,
Indonesia.
She
is
currently
lecturing
with
the
D
epartment
of
Information
Engineering
at
University
of
Palangka
Raya.
Her
res
earch
areas
of
interest
include
software
engineering,
information
science,
and
artificial
i
ntelligence
.
She
can
be
contacted
at email
:
ressa@
it.upr.ac.id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
5
,
O
c
to
be
r
2025
:
3879
-
3886
3886
Putu
Bagus
Adidyana
Anugrah
Putra
holds
a
Master
of
Enginee
ring
(M.Eng.
)
in
Informatics
Engineering
from
University
of
Amikom
Yogyakarta,
I
ndonesia,
in
2013.
He
is
currently
lecturin
g
with
the
D
epartment
of
Informati
on
Engineeri
ng
at
Universi
ty
of
Palangka
Raya.
He
is
a
member
of
the
Association
of
Higher
Education
in
Inf
ormatics
and
Computers
(APTIKOM).
His
research
areas
of
interest
include
software
engineeri
ng,
information
science,
and artifi
cial int
elligence
. He can be contac
ted at email:
putubagus@
it.upr.ac.id
.
Nova
Noor
Kamala
Sari
holds
a
Master
of
Engineering
(M.Eng.)
in
Informatics
Engineering
from
University
of
Amikom
Yogyakarta,
Indonesia,
in
2013.
She
is
currentl
y
lecturing
with
the
D
epartment
of
Informati
on
Engineeri
ng
at
Unive
rsity
of
Palangka
Raya.
Her
research
areas
of
interest
include
software
engineering,
informati
on
science,
and
artificial
intelligence
. She can be contacted a
t email:
novanoorks@
it.upr.ac.id
.
Efrans
Christian
holds
a
Master
of
Technology
(M.T.)
degree
fr
om
Atma
Jay
a
Yogyakarta
University.
He
is
currently
a
lecturer
in
the
Dep
artment
of
Informatics
Engineering
at
Palangka
Raya
University.
His
research
interests
i
nclude
human
-
computer
interactio
n
(HCI),
software
engineering,
and
artificial
intelligence.
He
can
be
contacted
at
email:
efrans@i
t.upr.ac.id
.
Septian
Geges
holds
S.
Kom
.
and
M.
Kom
.
degree
s
from
Instu
tut
Teknologi
Sepuluh
Nopemb
er
Suraba
ya,
in
addition
to
several
professional
c
ertificates
and
skills
at
computer
network
s
.
He
is
currently
lecturing
with
the
D
epartment
of
Engineeri
ng
at
Palangka
Raya
University.
His
research
areas
of
interest
include
data
transmission
protocol
,
distributed
system,
blockchain
technology,
and
digital
signal
processing
.
He
ca
n
be
contacted
at
email:
septian.geges@it.upr.ac.id
.
Novera
Kristianti
is
a
lecturer
in
Informatics
Engineering
at
University
of
Palangk
a
Raya,
Indonesia.
She
received
her
M.T
.
degree
from
Atma
Jaya
Yogyakarta
University,
Indonesia.
Her
research
interests
are
visualization,
soft
c
omputing
,
and
artificial
intelligence
. She can
be contac
ted at ema
il:
noverakristianti@
eng.upr.ac.id
.
Evaluation Warning : The document was created with Spire.PDF for Python.