Sustainability,
Год журнала:
2025,
Номер
17(9), С. 3828 - 3828
Опубликована: Апрель 24, 2025
Life
cycle
carbon
emissions
from
the
construction
industry
(CE)
have
a
profound
impact
on
China’s
“dual
carbon”
goals,
with
significant
posing
severe
challenges
to
environment.
In
this
paper,
four
prediction
models
were
trained
and
compared,
optimal
model,
Genetic
Algorithm
Optimized
BP
Neural
Network
(GA-BP),
was
finally
selected
for
multi-scenario
of
CE.
Firstly,
study
performs
comprehensive
accounting
indicator
analysis
CE
over
its
entire
life
cycle.
addition,
paper
further
conducts
spatial
differentiation
Subsequently,
parameter
conducted
using
an
improved
STIRPAT
followed
by
LMDI
factor
decomposition
based
model.
Finally,
model
performance
verified
three
evaluation
metrics:
coefficient
determination
(R2),
mean
absolute
error
(MAE),
percentage
(MAPE).
The
results
indicate
that
(1)
in
emission
assessment,
reached
peak
42.52
t
per
capita
annually
8.90
CO2/m2
unit
area;
(2)
year-end
resident
population
has
greatest
influence
CE,
other
related
variables
also
contributing
positively;
(3)
GA-BP
outperforms
models,
R2
increasing
0.0435
0.0981,
MAE
reducing
63%
76%,
MAPE
decreasing
23%
68%.
