Although
composting
has
many
advantages
in
the
treatment
of
organic
waste,
there
are
still
problems
and
challenges
associated
with
emissions,
like
NH3,
VOCs,
H2S,
as
well
greenhouse
gases
such
CO2,
CH4,
N2O.
One
promising
approach
to
enhancing
conditions
is
used
novel
analytical
methods
bad
on
artificial
intelligence.
To
predict
optimize
emissions
(CO,
NH3)
during
process
kinetics
thought
mathematical
models
(MM)
machine
learning
(ML)
were
utilized.
Data
about
everyday
from
laboratory
compost’s
biochar
different
incubation
(50,
60,
70
°C)
doses
(0,
3,
6,
9,
12,
15%
d.m.)
for
MM
ML
selections
training.
not
been
very
effective
predicting
(R2
0.1
-
0.9),
while
acritical
neural
network
(ANN,
Bayesian
Regularized
Neural
Network;
R2
accuracy
CO:0,71,
CO2:0,81,
NH3:0,95,
H2S:0,72))
decision
tree
(DT,
RPART;
CO:0,693,
CO2:0,80,
NH3:0,93,
H2S:0,65)
have
demonstrated
satisfactory
results.
For
first
time
CO
H2S
demonstrated.
Further
research
a
semi-scale
field
study
needed
improve
developments
models.
New Biotechnology,
Год журнала:
2023,
Номер
77, С. 58 - 67
Опубликована: Июль 17, 2023
In
this
work,
a
model
for
the
characterization
of
microalgae
cultures
based
on
artificial
neural
networks
has
been
developed.
The
is
essential
to
guarantee
quality
biomass,
and
objective
work
achieve
simple
fast
method
address
issue.
Data
acquisition
was
performed
using
FlowCam,
device
capable
capturing
images
cells
detected
in
culture
sample,
which
are
used
as
inputs
by
model.
can
distinguish
between
6
different
genera
microalgae,
having
trained
with
several
species
each
genus.
It
further
complemented
classification
threshold
discard
unwanted
objects
while
improving
overall
accuracy
achieved
an
up
97.27%
when
classifying
culture.
results
demonstrate
effectiveness
Deep
Learning
models
cultures,
it
being
useful
tool
monitoring
large-scale
production
facilities
providing
accurate
over
wide
range
genera.
