Home' Position : Position 84 Aug-Spt 2016 Contents With Australia’s population set
to soar to 30 million by 2031,
the pressure on authorities
and commercial enterprises to deliver
intelligent transport systems that are
reliable, efficient, safe, sustainable and
accessible has never been greater.
Beyond the rapid growth of our major
cities, the challenges that lie ahead for the
country’s transport networks are complex
and have far-reaching ramifications.
For example, traffic congestion – and
its impact on local business – is forecast
to cost AU$20 billion a year by 2020. Road
freight alone is projected to increase by 80
per cent by 2030. And CO2 emissions from
road transport will account for 14 per cent
of Australia’s total greenhouse emissions.
The answer to addressing these
challenges – and mitigating the associated
risks – doesn’t lie in traditional responses.
Rather, if you’re the CEO or COO of
one of Australia’s transport agencies,
the key to improving the performance
of existing infrastructure networks and
optimising new intelligent transport
strategies lies buried deep within your
department’s Big Data reservoirs.
Predicting the future
Utilising data sources to provide insights
into a city’s transport networks isn’t new;
in fact most traffic departments have been
using the approach for decades. To the
uninitiated, today’s traffic management
centres often resemble Star Trek sets as
information is streamed, in near-real-
time, to a gallery of interactive digital
maps and screens to provide a live picture
of a transport network, highlighting
blockages, upgrades and accidents.
But the truth is we have barely
scratched the surface in exploiting big
data to improve transport networks and
planning. While day-to-day, operational
tasks – such as optimising traffic signal
timing and responding to accidents – are
incredibly important to the smooth flow
of traffic, even greater value lies in being
able to predict what the networks of the
future could, and should, look like.
New developments in advanced
location-based analytics are now
providing us with the ability to move
beyond the historical views of traffic
patterns and real-time situational
awareness that is our current focus.
By combining advanced analytics
with the wide range of big data sources
that we can now consume, we are
better positioned to understand future
commuter behaviour and plan networks
that match and direct movement more
efficiently than ever before.
driven insights to inform
Central to this approach is supplementing
authoritative, government-sourced data
with “non-authoritative”, external data to
create a more comprehensive and holistic
view of our transport networks.
Australian transport agencies now
have the ability to mine data collected
through the ubiquitous smartphone, as
well as satellites and GNSS devices, and
combine this with information from
services and apps we use on a daily basis,
such as Uber and Twitter. And with global
telecommunications networks forecast
to connect with more than 50 billion
Internet of Things (IoT) sensors by the
year 2020, the amount of accessible big
data will increase exponentially.
Advanced location-based analytics
platforms – including GIS – can
rapidly probe these vast volumes of
data, translating raw information into
For example, planners looking to
relieve road congestion by encouraging
alternative transport could use
location-based analytics to leverage
the information collected by cycling
apps such as Strava. Strava reveals
routes taken by bike riders as well as
commentary about why these are used:
valuable information that could support
decision-making when designing new bike
paths for cyclists.
With GIS technology, data from these
disparate sources can be integrated and
analysed with ease to enable us to move
beyond simply identifying the ‘where’ and
‘when’ of transport, to start answering
crucial questions about ‘how’ and ‘why’
people are travelling. Why are commuters
selecting one mode of transport over
another? How can promoting the use of a
particular route over another during peak-
hour ease congestion?
By analysing data at an individual trip
level, as opposed to an aggregated level,
we can determine how individuals choose
their routes and arrive at decisions about
Armed with this knowledge, we can
understand how the different components
of our transport network – encompassing
infrastructure, vehicles and mobility
services – could be planned based on the
needs of commuters and the capacity of
the network as a whole.
Singapore’s Land Transport Authority
(LTA) is just one case of an agency that
has successfully leveraged this approach.
Their location-based analytics system
called Planning for Land Transport
Big data analytics has only just scratched the surface
on a future of smart transport networks.
Locating a smarter
20 position August/September 2016
Links Archive Position Jun Jul 2016 Position 85 Oct-Nov 2016 Navigation Previous Page Next Page