medRxiv (Cold Spring Harbor Laboratory),
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 7, 2025
Abstract
Agricultural
injuries
remain
a
significant
occupational
hazard,
causing
substantial
human
and
economic
losses
worldwide.
This
study
investigates
the
prediction
of
agricultural
injury
severity
using
both
linear
ensemble
machine
learning
(ML)
models
applies
explainable
AI
(XAI)
techniques
to
understand
contribution
input
features.
Data
from
AgInjuryNews
(2015–2024)
was
preprocessed
extract
relevant
attributes
such
as
location,
time,
age,
safety
measures.
The
dataset
comprised
2,421
incidents
categorized
fatal
or
non-fatal.
Various
ML
models,
including
Naïve
Bayes
(NB),
Decision
Tree
(DT),
Support
Vector
Machine
(SVM),
Random
Forest
(RF),
Gradient
Boosting
(GB),
were
trained
evaluated
standard
performance
metrics.
Ensemble
demonstrated
superior
accuracy
recall
compared
with
XGBoost
achieving
100%
for
injuries.
However,
all
faced
challenges
in
predicting
non-fatal
due
class
imbalance.
SHAP
analysis
provided
insights
into
feature
importance,
gender,
time
emerging
most
influential
predictors
across
models.
research
highlights
effectiveness
while
emphasizing
need
balanced
datasets
XAI
actionable
insights.
findings
have
practical
implications
enhancing
guiding
policy
interventions.
Highlights
analyzed
(2015–
2024)
utilized
predict
severity,
focusing
on
outcomes.
Forest,
outperformed
recall,
especially
injuries,
although
predictions
imbalance
observed.
Key
identified
through
included
providing
interpretable
factors
influencing
severity.
integration
enhanced
transparency
predictions,
enabling
stakeholders
prioritize
targeted
interventions
effectively.
potential
combining
improve
practices
provides
foundation
addressing
data
future
studies.
Graphical
International Journal of River Basin Management,
Journal Year:
2023,
Volume and Issue:
23(1), P. 1 - 13
Published: May 24, 2023
Floods
affect
over
2.2
billion
people
worldwide,
and
their
frequency
is
increasing
at
an
alarming
rate
compared
to
other
disasters.
Presidential
disaster
declarations
have
issued
increasingly
almost
every
year
in
Iowa
for
the
past
30
years,
indicating
that
state
on
rise
of
flood
risk.
A
multi-disciplinary
approach
required,
which
underlying
hydrologic
processes
cause
floods
are
closely
linked
with
watershed-level
socio-economic
functions
using
effective
collaboration
tools
ensure
community
participation
co-production
mitigation
plans
while
paying
attention
socio-environmental
justice
principles.
Considering
existing
limitations
needs,
we
conducted
a
risk
assessment
by
utilizing
geophysical
datasets
case
study
Cedar
Rapids,
Iowa.
Flood
outputs
generated
based
three
main
groups:
geophysical-based
risk,
socioeconomic
combined
An
extensive
literature
review
determine
pairwise
comparison
matrices
parameters
used
analytical
hierarchy
process
(AHP)
fuzzy
AHP
methods.
Our
results
indicate
high-
very-high-risk
susceptibility
zones
primarily
located
central
urban
areas
lower
elevations,
regardless
method
type
(AHP
or
FAHP).
According
overall
results,
large
area
Rapids
consists
medium
level
according
map
method.
The
show
high
very
high-risk
16%
studied
region,
medium,
low
low-risk
correspond
84%.
Besides,
nearly
40%
population
lives
zones.
Urban Informatics,
Journal Year:
2024,
Volume and Issue:
3(1)
Published: March 8, 2024
Abstract
Transportation
systems
can
be
significantly
affected
by
flooding,
leading
to
physical
damage
and
hindering
accessibility.
Despite
flooding
being
a
frequent
occurrence,
there
are
limited
accessible
online
tools
available
for
supporting
routing
emergency
planning
decisions
during
flooding.
Existing
generally
based
on
complicated
models
not
easily
non-expert
users,
highlighting
the
need
efficient
communication
decision-making
analyzing
flood
impacts
transportation
networks
various
stakeholders,
including
public,
minimize
adverse
those
groups.
This
paper
presents
web
application
that
uses
graph
network
methods
latest
technologies
standards
assist
in
describing
events
terms
of
operational
constraints
provide
analytical
support
mobility
mitigation
these
events.
The
framework
is
designed
user-friendly,
enabling
users
access
information
about
road
status,
shortest
paths
critical
amenities,
location-allocation,
service
coverage.
study
area
includes
following
two
communities
State
Iowa,
Cedar
Rapids
Charles
City,
which
were
used
test
application's
functionality
explore
outcomes.
Our
research
demonstrates
affect
bridge
operation,
from
locations
arbitrary
point-to-point
routing,
facility
placement,
introduced
solve
complex
flood-related
decision
tasks
an
understandable
representation
vulnerability,
enhancing
strategies.
Therefore,
this
provides
valuable
tool
stakeholders
make
informed
Journal of Hydroinformatics,
Journal Year:
2023,
Volume and Issue:
25(2), P. 552 - 566
Published: March 1, 2023
Abstract
The
temporal
and
spatial
resolution
of
rainfall
data
is
crucial
for
environmental
modeling
studies
in
which
its
variability
space
time
considered
as
a
primary
factor.
Rainfall
products
from
different
remote
sensing
instruments
(e.g.,
radar,
satellite)
have
space-time
resolutions
because
the
differences
their
capabilities
post-processing
methods.
In
this
study,
we
developed
deep-learning
approach
that
augments
with
increased
to
complement
relatively
lower-resolution
products.
We
propose
neural
network
architecture
based
on
Convolutional
Neural
Networks
(CNNs),
namely
TempNet,
improve
radar-based
compare
proposed
model
an
optical
flow-based
interpolation
method
CNN-baseline
model.
While
TempNet
achieves
mean
absolute
error
0.332
mm/h,
comparison
methods
achieve
0.35
0.341,
respectively.
methodology
presented
study
could
be
used
enhancing
maps
better
imputation
missing
frames
sequences
2D
support
hydrological
flood
forecasting
studies.
Journal of Hydroinformatics,
Journal Year:
2023,
Volume and Issue:
25(4), P. 1171 - 1187
Published: July 1, 2023
Abstract
We
introduce
HydroLang
Markup
Language
(HL-ML),
a
programming
interface
that
uses
markup
language
to
perform
environmental
analyses
using
the
hydrological
and
framework
HydroLang.
The
software
acts
as
self-contained
HTML
tags
powered
by
web
component
specification
generate
simple
computations
enable
data
analysis,
visualization,
manipulation
via
semantically
driven
instructions.
It
enables
researchers
professionals
use
retrieve,
analyze,
visualize,
map
with
basic
skills.
components'
adaptability
users
run
analytical
routines
complex
on
client
side.
present
implementation
details
of
approach,
custom
elements
in
technologies
academia,
share
sample
usages
demonstrate
simplicity
human-readable
computer-executable
framework.
EarthArXiv (California Digital Library),
Journal Year:
2023,
Volume and Issue:
unknown
Published: Aug. 19, 2023
Hydrometeorological
disasters,
including
floods
and
droughts,
have
intensified
in
both
frequency
severity
recent
years.
This
trend
underscores
the
critical
role
of
timely
monitoring,
accurate
forecasting,
effective
warning
systems
facilitating
proactive
responses.
Today's
information
offer
a
vast
intricate
mesh
data,
encompassing
satellite
imagery,
meteorological
metrics,
predictive
modeling.
Easily
accessible
to
general
public,
these
cyberinfrastructures
simulate
potential
disaster
scenarios,
serving
as
invaluable
aids
decision-making
processes.
review
collates
key
literature
on
water-related
systems,
underscoring
transformative
impact
emerging
Internet
technologies.
These
advancements
promise
enhanced
flood
drought
timeliness
greater
preparedness
through
improved
management,
analysis,
visualization,
data
sharing.
Moreover,
aid
hydrometeorological
predictions,
foster
development
web-based
educational
platforms,
support
frameworks,
digital
twins,
metaverse
applications
contexts.
They
further
bolster
scientific
research
development,
enrich
climate
change
vulnerability
strengthen
associated
cyberinfrastructures.
article
delves
into
prospective
developments
realm
natural
pinpointing
primary
challenges
gaps
current
highlighting
intersections
with
future
artificial
intelligence
solutions.
