Content uploaded by Gary White
Author content
All content in this area was uploaded by Gary White on Jan 13, 2021
Content may be subject to copyright.
A Digital Twin Smart City for Citizen Feedback
Gary White∗
, Anna Zink, Lara Codec´
a, Siobh´
an Clarke
Trinity College Dublin, College Green, Dublin 2, Ireland
Abstract
A digital twin is a digital representation of a physical process, person, place, system or device. Digital twins were originally de-
signed to improve manufacturing processes using simulations that have highly accurate models of individual components. However,
with increasingly large and accurate building information models (BIM) combined with big data generated from IoT sensors in a
smart city, it is now possible to create digital twin smart cities. An accurate 3D model of a city can be published online and walked
around by the public to view proposed changes in urban planning and policy. This allows for easier dissemination and transparency
to the public before putting these decisions into practice. This open and public model allows for an additional virtual feedback loop
where citizens can interact and report feedback on planned changes in the city. Citizens can also interact with components to tag
and report problems in their area. The digital twin also allows for additional experimentation where 3D data is necessary, such as
flood evacuation planning. In this paper, we demonstrate a public and open digital twin of the Docklands area in Dublin, Ireland
and show how this model can be used for urban planning of skylines and green space allowing users to interact and report feedback
on planned changes.
Keywords: Digital Twin, Smart Cities, Internet of Things (IoT), Urban Planning, Urban Policy
1. Introduction
Cities have become increasing smarter in the last two decades
[1], using pervasive information and communications technol-
ogy (ICT) to monitor activities in the city [2]. Data can then
be generated from a wide variety of activities in the city, such
as traffic and transportation [3], power generation [4], utilities
provisioning [5], water supply [6] and waste management [7].
Smart cities can then use this data to improve the mobility, en-
vironment, living standards and governance of the city [8, 9].
A strong link has been shown between investing in smart city
policies and urban GDP growth [10].
The data generated by smart cities makes them exciting
testbeds for data mining and machine learning [11, 12]. The
services provided to citizens in a smart city can be personalised
using machine learning, internet of things and big data [13, 14].
These deep learning algorithms can be used to categorise and
perform analytics on a number of different data streams includ-
ing videos [15]. More recent neural network approaches, such
as generative adversarial network (GAN) can be used to opti-
mize crowd routing in a smart city [16]. In the digital twin layer
reinforcement learning algorithms can also be used to learn the
best action policies to improve performance in a number of ur-
ban intelligence tasks, such as managing traffic and power sys-
tems [17, 18].
∗Corresponding author
Email addresses: whiteg5@scss.tcd.ie (Gary White),
zinka@tcd.ie (Anna Zink), lara.codeca@tcd.ie (Lara Codec´
a),
siobhan.clarke@scss.tcd.ie (Siobh´
an Clarke)
The increased data available from smart cities, artificial intel-
ligence, data analytics and machine learning allows for the cre-
ation of a digital twin that can update and change as the phys-
ical equivalents change [19]. A digital twin is a pairing of the
virtual and physical worlds that allows for analysis of data and
monitoring of systems to head offproblems before they occur,
prevent downtime and can even be used to plan for the future us-
ing simulations [20]. Digital twins have primarily been used in
the manufacturing sector, but other areas of study and business
are beginning to find new potential uses. An ideal digital twin
would be identical to its physical counter-part and have a com-
plete, real-time dataset of all information on the object/system.
As the object/system increases in complexity a digital twin may
be identical in only relevant areas and have only the real-time
data necessary to support any desired simulations. How accu-
rate and useful a digital twin is, depends on the level of detail
put into it and how comprehensive the available data is.
Digital twins allow for the simulation of many options before
taking physical action in the real world to identify the strengths
and weaknesses of each plan. This is especially important in
safety critical situations, where only one option can be chosen
and there may be a number of competing plans to choose from.
This is exemplified by the rescue operation in Thailand to save a
lost soccer team that occurred in July 2018 [21] [22]. A 3D map
of the terrain, a complex cave system, was created using GIS
data, water and oxygen information inside the caves. Weather
forecasts were also used in order to create an accurate digital
twin that could simulate rescue operations and ensure the safety
of the rescuers and the lost team. The use of a digital twin
ensured that when rescuers acted, it was a best-case scenario
Preprint submitted to Cities January 11, 2021
after testing multiple options.
Digital twins can have applications in a number of different
domains. With the data generated by smart cities, digital twins
can be used to model urban planning and policy decisions. An
example of a work-in-progress digital twin of a city is Virtual
Singapore1, which is a three-dimensional (3D) city model and
data platform [23]. In this paper, we expand on the digital twin
ideas introduced in Virtual Singapore and make our model pub-
licly available on the internet2. This allows users to easily in-
teract with the model, leave feedback about urban planning de-
cisions and tag problems in their local area. This generates an
additional layer of data that can be used to make changes in a
smart city. We also show how the 3D model can be used to
create realistic flooding and crowd simulations.
In this paper, we present an open and publicly available dig-
ital twin smart cities model of the Docklands area in Dublin,
Ireland. Section 2 presents the related work that has been
conducted using digital twins in different domains. Section 3
presents the design of the digital twin smart city model and how
it is created through the combination of data from a number of
different layers across the city. Section 4 presents the experi-
mental setup that was used to conduct the simulations and the
feedback that was received by making the model publicly avail-
able. Section 5 presents the results of those simulations and
Section 6 presents some of the limitations of the current digital
twin model and how it could be improved in future iterations.
Section 7 concludes the paper and presents some future work.
2. Related Work
Digital twins are a digital replica of a living or non-living
physical entity [24]. Enabling tools for digital twin data, ser-
vices, modelling and connection to the physical world have led
to the increased popularity of digital twins [25]. Digital twins
integrate internet of things, machine learning, artificial intelli-
gence and data analytics to create living digital simulation mod-
els that update and change with their physical counterparts [26].
A digital twin is continuously learning and updating itself from
multiple data sources to represent the physical object in near
real-time. The system can learn from itself, from other simi-
lar digital twins or from human experts with relevant domain
knowledge. A digital twin can also learn from historical data in
past usage and factor this into its digital model.
Digital twins were first defined by NASA as a paradigm
for future NASA and U.S Air Force vehicles [27]. A digital
twin would allow for ultra-high fidelity simulation using data
from the vehicle’s on-board system, maintenance history and
all available historical and fleet data to identify any possible
problems in safety or reliability. They have since been applied
to a number of manufacturing projects as they can bridge the
gap between the virtual and physical space at different stages in
the product’s lifetime [28]. A digital twin allows for the prod-
uct to be tested at all stages of the design process to ensure the
design is feasible, safe, efficient and reliable [29].
1https://www.nrf.gov.sg/programmes/virtual-singapore
2https://www.scss.tcd.ie/~whiteg5/webgl/
A digital twin makes control and experimentation of a com-
plex system feasible [30]. This has led to them being used in
a number of complex systems beyond product design and the
manufacturing process. Digital twins can be used to create dig-
ital twin humans that can be used in healthcare [31]. With the
rise of quantified-self, users can now collect more data about
their physical activity, sleep quality, diet, heart rate, weight,
productivity, working environment and social interaction [32].
This data can then be used to create an accurate digital twin
to predict upcoming health issues as well as test solutions to
prevent or reduce the damage of any complications [33].
Digital twin cities can be created using the data collected
from smart city services [34]. The virtual representation allows
for modelling and visualisation of the spatiotemporal informa-
tion in a city. Much of the recent success in smart cities around
the world in integrating reliable ICT systems into the city can
be utilised to create a digital twin of a city [35, 36]. An initial
attempt to create a digital twin smart city has been conducted
in Singapore, also known as Virtual Singapore [37]. However,
there are a number of limitations with this initial approach as
the model has not been made publicly available, so citizens
cannot interact with the model or report feedback and it does
not include urban mobility data. Digital twin programmes are
in the early stages with a roadmap being outlined at the Cen-
tre for Digital Built Britain at Cambridge University [38]. The
roadmap shows the key building blocks and actors that together
would enable successful digital twins across the built environ-
ment. In this paper we tackle point 3.10 to undertake strategic
pilots to prove the information architecture with selected stake-
holders and point 4.7 to share learning from digital twin hubs,
pilots and demonstrations.
A number of private companies, such as CityZenith 3,
Agency9 who were acquired by Bentley 4and SmarterBetter-
Cities 5have started to develop in the Digital Twin Smart City
space. However, all of these companies are private and do not
make their models publicly available and charge expensive li-
censing fees. Our approach is publicly released on the internet
allowing users to interact with the model and for it to be used
in future digital twin projects for free.
In this paper, we create a digital twin of the Docklands area
in Dublin, Ireland using a publicly released 3D model 6. We
show how the model can be used for a number of urban plan-
ning and policy decisions by adding a proposed building to the
skyline as well as additional green spaces and parks. As the
model is available online2users can easily tag problem areas in
the city and fill forms to make changes in their local area. This
generates additional data that can feed back into the digital twin
to specify problem areas in the city that need to be developed.
We also show how our digital twin can be used to create a num-
ber of urban mobility simulations using pedestrian mobility, as
3https://cityzenith.com/
4https://www.bentley.com/en/products/product-line/
reality-modeling- software/opencities-planner
5https://www.smarterbettercities.ch/
6https://data.smartdublin.ie/dataset/
3d-data- hack-dublin- resources
2
well as simulating the effect that the river flooding would have
on the city.
3. Digital Twin Smart City Design
A digital twin smart city builds on a number of layers of in-
formation in the city. We define six layers in our digital twin
smart city model, as shown in Figure 1. The first five layers
build on top of each other adding more information about the
terrain, buildings, infrastructure, mobility and IoT devices in
the city. The Digital Layer/Smart City is used to collect data
from the city, which it can then pass to the Virtual Layer/Digital
Twin. The Digital Twin uses the data generated in the smart
city to perform additional simulations about mobility optimi-
sation, building placement or the design of renewable energy
such as offshore wind turbines. This information is then fed
back through the layers of the model where it is implemented
in the physical world. In this section we describe each layer of
the model as follows:
3.1. Terrain
The zeroth layer of the digital twin smart city design is the
terrain on which the city is built. This is basic information about
the city, such as what part of the city is offshore, are there rivers
or canals running through the city, are there steep gradients or
hills in the city, what part of the city is made of sand, what area
of the city has fertile soil that can be used to grow crops, what
areas of the city have soil with poor draining that can cause
problems, such as a landslide or during heavy rain or flooding.
A soil map, as show in Figure 2 can be used to incorporate this
information in the model.
3.2. Buildings
Layer 1 of the digital twin smart city model then adds the
current buildings in the city to the model. These buildings have
highly accurate building information modelling (BIM) models
that can be used as a digital twin of the building. The 3D build-
ing data can also be generated using stereoscopic aerial photog-
raphy. The building data used in our digital twin is of the Dublin
Docklands district in Ireland. This data is publicly available as
an FBX file6.
The data is limited to the area between the Samuel Beck-
ett Bridge and the Eastlink Bridge. It contains the region two
blocks north of the river and partially contains the region south
of the river up to the end of the Grand Canal.
3.3. Infrastructure
Layer 2 of the digital twin smart city model then adds the in-
frastructure that surrounds the current buildings in the city. This
is the basic physical and organisational structures and facilities
(e.g. roads, power supplies, telecommunication) needed for the
operation of a society or enterprise. This infrastructure data can
come from OpenStreetMap, which contains information about
power, public transport, motorways, highways, amenities and
telecoms. Data can also come from the 3D mapping process to
add gradient information as this may not be available in open
street maps.
5-Virtual Layer
/Digital Twin
4-Digital Layer
/Smart City
3-Mobility
2-Infrastructure
1-Buildings
0-Terrain
Data
Information
Figure 1: Layers Required to Develop a Digital Twin Smart City
3
Figure 2: Soil Map
3.4. Mobility
Layer 3 of the digital twin smart city model adds mobility
to the infrastructure and building layers. Mobility is the move-
ment of people during their daily routing and the movement of
the goods that help them in different aspects of their lives. Soft-
ware applications such as SUMO can be used to simulate ur-
ban mobility [39]. SUMO simulator supports a number of dif-
ferent transportation modes: walking, bicycles, powered two-
wheelers and generic parametrized vehicles. Additional avail-
able models are railways and waterways. This application can
be connected to the 3D model in Unity using the Traffic Control
Interface (TraCI). Unity can also be used to implement and en-
hance the traffic modes, adding additional behaviours that the
simulator does not model. In our case, we are interested in
adding multiple pedestrian types, such as adult and elderly.
3.5. Digital Layer/Smart City
The digital layer/smart city layer has become hugely popular
with a number of projects focused on integrating IoT sensors
in the city to collect data [40, 41, 42]. This data can then be
used to monitor and manage traffic and transportation systems
[3], power plants [4], utilities [5], water supply networks [6],
waste management [7], crime detection [43], information sys-
tems [44], schools [45], libraries [46], hospitals [47], and other
community services [48, 49].
As shown in Figure 1 layer 4, the digital layer/smart city is
responsible for gathering all the data needed for simulations in
the virtual layer/digital twin, from all the previous layers. The
results of these simulations are then fed back through the layers
of the city as information. The data can come from citizens, de-
vices and assets that may be mobile and located throughout the
city. Citizens can use their mobile phones and smart watches
to report data to the city authority. In Figure 1 layer 4, there
are connected vehicles that can report traffic data to the traffic
authority to help schedule lights to optimise the flow of traffic.
There are a number of smart trees that have moisture sensors
at the roots to ensure that they are watered at the correct inter-
val. There are a number of connected CCTV cameras located
throughout the city as a deterrent for crime and also to be used
as evidence for criminal behaviour. There are a number of 5G
cell towers located throughout the city that provide fast and low
latency access to the internet. A connected fire device has just
sent an alert to the fire brigade from one of the six tower build-
ings in the city after detecting smoke in one of the apartments.
Wind sensors have also been deployed near the monument off-
shore as well as on the boats to collect data for the possible
design of an offshore wind farm.
3.6. Virtual Layer/Digital Twin
The virtual layer/digital twin builds on the data that is pro-
duced from the digital layer/smart city. There is a connection
between the the virtual layer and digital layer as shown by the
arrows in Figure 1. Data is sent from the digital layer about the
mobility, infrastructure, buildings and terrain in the city. This
data is used to conduct simulations in the virtual layer, which
can then be passed back as information through the layers of
the city. For example, in Figure 1 wind data is being collected
offshore at the digital layer. This data is then used to conduct
simulations on the viability of using offshore wind turbines to
meet the renewable energy targets for the city. A highly re-
alistic digital twin of the turbines can be developed using the
wind data collected in the digital layer to influence the size and
placement of the turbines. This digital twin can then also be
used to evaluate the visual impact of the turbine placement as
citizens may not want the turbines placed close to the offshore
monument. Additional tracking information from the offshore
boats can also be used to help place the turbines in an area that
will not affect offshore traffic. In this case we are only using the
relevant components from each of the layers. For example, we
do not need the city terrain information, city buildings, urban
traffic mobility model or 5G telecommunications model to run
this simulation. We only use the relevant wind, offshore boat
and feedback data from the citizens to decide on the size and
placement of the offshore wind turbines.
The digital twin can also be used to aid with the construction
of buildings in the city. In the digital twin layer in Figure 1
we can see that two new large buildings are being proposed: a
circular skyscraper and the building with a spire on top. Using
the sensing data collected in the digital layer, simulations can
be created in the virtual layer to see how these buildings will
effect the sunlight in the city e.g., would they block the sun from
existing parks. Wind and seismic data collected in the digital
layer can also be used in the design of the new buildings. Once
a digital twin of the new buildings has been created they can
be tested against the known challenges of the city, such as high
winds or being near an earthquake fault line. Once the buildings
have attained the appropriate building safety certificate they can
be added to an online digital twin.
The online digital twin allows citizens to easily walk around
and give feedback on new urban policy and planning decisions.
Citizens can enter forms to give feedback on newly proposed
buildings or green spaces, such as parks in the city. This allows
the digital twin to generate additional smart city data that can
be used to create information through experimentation, which
is fed back through the layers of the smart city. For example, in
the green space simulation in Section 5, citizens could propose
new items that they wanted to be included in a new park, which
led to the inclusion of a children’s play pen option, which was
4
Citizens
WebGL
Internet
Unity
IoT Devices
Stereoscopy and
SUMO
Online Digital
Twin
Digital Twin
3D and Urban
Mobiliy Model
IoT Data
City Council
Researchers and
Model Developers
Deploy Feedback
Developed
Model
Additonal Citizen
Data
Model Feedback Open Source
Data
Figure 3: Online Digital Twin Interaction Diagram
not one of the original proposed options. Figure 3 shows the
online digital twin interaction diagram. We can see how the
model being deployed online over the internet allows for easy
citizen feedback. This feedback can then be send to the relevant
group, such as the researchers who developed the urban mobil-
ity model or the city council, who provide the urban IoT data.
The city council can then use this data to make informed deci-
sions about urban planning and policy. The main stakeholders
for each of the components of the online digital twin are also
shown with the blue box indicating the main technologies used.
4. Experimental Setup
4.1. Simulation Software
Unity3D Software (Unity), version 2019.2.10f1 Personal,
was used to load the digital twin, which is a 3D FBX model
that contains the first three layers of terrain, buildings and in-
frastructure. Pedestrian mobility models were implemented
in Unity to allow for crowd simulations, with different agents
types, including adult and elderly using data from an experi-
mental study [50]. Smart city data is taken from the Dublinked7
site to make the simulations as accurate as possible. The twin-
ing with real public data from an open portal allows the model
to evolve over time and allows for multidisciplinary modelling
of the city [51]. A city is always evolving over time with new
buildings and data available from the city about crowds in the
city or flooding information. This new data creates a feedback
loop allowing the digital twin to test the models and predictions
on unseen data.
7https://data.smartdublin.ie/
4.2. Skyline Simulation
A version of the model has also been made available online2.
A 3D model allows for the easy removal and addition of newly
proposed buildings. This can be useful for conducting simula-
tions to evaluate the response to new buildings being introduced
in the city and how they would affect the skyline. Any proposed
building plans can easily be added to the digital twin using the
BIM model. This model would then allow citizens and pub-
lic officials to walk around the digital twin and see the effect
that the new building would have on the skyline from a number
of different locations. The sunlight information from the smart
city combined with the BIM file of the new building could be
combined to simulate the effect that a large building would have
on the sunlight access of nearby parks or public spaces.
Building works are long term projects and can take years to
complete. This can lead to a large difference between the cur-
rent view of the city and what the city will look like when all
the current building projects are finished. In our simulation, we
show a current view of the model with all the current buildings
finished compared to the current view in the street to highlight
this point. We also add some additional BIM models as assets
to our digital twin to show how the skyline would be affected
by new buildings. In the digital twin model that is deployed on-
line, citizens can be presented with a form that they can use to
give feedback on the newly proposed building. The form asks
for the citizens name and email for verification, then the user
can vote on whether or not they approve of the new building.
Once the user has voted on whether or not they approve of the
new building they can leave additional feedback in a text box
explaining the reasons why they approve or disapprove of the
new building.
4.3. Green Space Simulation
Green space, such as parks and recreational spaces are hugely
important in smart cities for promoting healthy living and well-
being [52, 53]. The digital twin model allows for development
of these green spaces in suitable areas of the city. Data from the
smart city, such as air pollution, noise pollution, pedestrian traf-
fic flow and amount of direct sunlight can be used to influence
urban planning decisions of where to place these green spaces
in the city.
If the park or green space gets urban authority approval then
the smart city can be used to track the number of people that
visit the new green space. Different facilities in the park, such
as extra benches or new flowers can be modelled using the dig-
ital twin, while also presenting a selection of options for users
to choose or propose new suggestions. The success of this ad-
ditional equipment can also be tracked through the use of sen-
sors in the smart city. In our simulations we add additional
tree locations throughout the city and create a new park. Citi-
zens can leave feedback about what additional equipment they
would like to see in the new park by selecting from the follow-
ing options: more benches, more summer flowers, park gym
equipment or other. By selecting the ‘other’ option the citizen
can leave a suggestion that is not one of the considered options,
which may provide additional information of the local citizens
needs for urban planners.
5
4.4. User Tagging Simulation
The initial form-based skyline and green space simulations
can be extended to allow citizens to walk around the model
more freely and tag objects within it. With an accurate digital
twin available, citizens would be able to tag real life problems
in the model and then have the information sent to the relevant
government department. This message would have the exact
location of the issue as seen in the model.
The digital twin can also be used in disaster scenarios to eas-
ily show citizens in the city the areas will be most affected by
flooding and the roads that will become inaccessible. Citizens
can also tag their current location in the digital twin and whether
or not they are in need of assistance. This user tagging would
enhance the data generated by the smart city and would allow
for more detailed simulations when using the digital twin in fu-
ture as the locations of where most citizens needed assistance
would be captured. The actual level that the water rose based
on the amount of rain would also then be fed back into the dig-
ital twin to ensure that the model has an accurate model for
predicting the water level based on rainfall.
4.5. Flooding Simulation
Accurate flooding simulations require the detailed 3D terrain
and building information provided in a digital twin. Unity al-
lows the loading of a 3D digital twin, which contains accurate
street elevation information. This allows the water level to be
dynamically altered, showing the areas that would first be af-
fected by a river flooding its banks or heavy rain. These sim-
ulations can be useful for urban authorities in flood planing by
deciding where to deploy sandbags and what areas of the city
to evacuate first.
Data from the smart city about rainfall amount and river lev-
els can be fed to the digital twin to create a timeline of when
flooding could occur. This information can then be passed from
the digital twin back to the smart city to alert citizens of the
timeline for a possible flood. The historical data collected from
the smart city can then be used to create longer term flood pre-
vention mechanisms if flooding is identified as a problem for
the city. This could be for large scale projects, such as intro-
ducing water storage areas or diverting rivers. Previous flood-
ing simulation approaches have integrated propitiatory flooding
models, such as Mike Flood and have focused on the economic
cost caused by floods [54]. Our approach is focused on urban
mobility and identifying the areas that are susceptible to flood-
ing in the city.
In this flooding simulation we raise the water level in the
River Liffey in Dublin to identify the surrounding areas that
would be most effected by the river flooding its banks. This
simulation is able to identify roads and walkways that would
become inaccessible to vehicles and pedestrians in a flood,
which would alter the movement patterns in the city. This is
especially important for one way roads where vehicles may be-
come stuck and not be able to turn around. Our initial model is
simplistic, only taking into account rainfall and river levels, but
it can be extended to include additional information about cur-
rents, materials in the river beds, sewage and drainage systems.
Our model is validation using data from the office of public
works, which has historical data on past floods in Ireland and
gives low, medium and high probability ratings to a current area
being flooded.
4.6. Crowd Simulation
The crowd simulation can be carried out anywhere in the
model, but was mostly focused around an intersection just north
of the Samuel Beckett bridge. Spawn locations were placed at
entry points to the maps, as a general collection at the four cor-
ners of the main intersection and at the exits of the 3Arena.
These sets of spawn locations are the children of empty ob-
jects that describe the set and any of the sets can be used for a
flock to set the spawn locations and destinations. The average
waiting time and the average distance travelled was then com-
pared between the agent types. The two agent types elderly and
adult, were spawned at different ratios: 0-100, 25-75, and 50-
50 splits. The Elderly agents have a smaller maximum speed
range, step height and wider radius so that they would not make
as sharp turns, which is based on an experimental evaluation
[50]. Their average waiting times and distance travelled were
then compared.
A flocking algorithm was developed to control pedestrian
movement. This is done by assigning behaviours to the pedes-
trians, which will be referred to as agents. These behaviours
determine how the agent will move when interacting with its en-
vironment and other agents. The core of this algorithm contains
three scripts, FlockBehaviour, FlockAgent, and Flock. The
first, FlockBehaviour is a scriptable object, which all behaviour
scripts inherit from. Each behaviour creates a movement vector
that are summed to find the agents next move. The second and
third are both Monobehaviours that govern the properties of the
flock. FlockAgent controls individual properties and stores data
that is unique to the individual agent, while Flock controls any-
thing that is universal to the flock. The three basic behaviours
needed are cohesion, alignment and avoidance. These ensure
that the flock of agents move together, in the same direction,
and that the agents do not overlap with each other. Other be-
haviours have been added to make a more realistic crowd sim-
ulation or to incite reactions to any introduced stimuli. The
flocking algorithm is made publicly available8. The crowd sim-
ulation is validated using public data from the pedestrian foot-
fall index in Dublin city centre provided by Dublin’s open data
portal7. The model can evaluate the accuracy of the predictions
using unseen data, which it can then use to update the model
creating a continuous learning cycle.
5. Results
5.1. Skyline Simulation
A 3D model provides a low barrier to entry for citizens to be-
come engaged in city planning decisions as no detailed techni-
cal knowledge is needed. The buildings are simulated in 3D and
8https://www.scss.tcd.ie/~whiteg5/
6
(a) Current Street View
(b) Current Digital Twin
Figure 4: Approved Building Works
citizens can report if there are any problem. Figure 4 shows a
comparison between a current view of the Docklands available
on Google Maps and the current simulated model. We can see
that there is a large difference between the current view in Fig-
ure 4a and the model view in Figure 4b, with many buildings
still under construction. The digital twin gives citizens easy
access to what their city will look like in the future as these
buildings can take years to complete.
Figure 5 shows a proposed building addition, based on the
Transamerica Pyramid that would change the skyline in Dublin.
Figure 5a shows the current model of the city and Figure 5b
shows the proposed building plan. This provides easy access
to city officials as well as the public to walk around the city
and identify some of the problems that a large building like this
may have in the city, such blocking sunlight or cell towers. This
allows any complains to be heard before the building has begun
construction.
Figure 6 is the feedback that has been collected from 30 citi-
zens in the area though an online form. The citizens were asked
whether they approve of the new building proposed in Figure
5b. From the data collected 78% of citizens approved of the
new building, while 22% disapproved. Citizens were then able
to leave comments on why they chose to approve or disapprove
the design of the new building. The comments for people who
disapproved of the building were that “the design didn’t fit in
with Dublin’s architecture” and that “it is too tall and sticks out
compared to surrounding buildings”. This can provide useful
insight to urban planners and policy makers to update the de-
sign of the building.
(a) Current Digital Twin
(b) Proposed Buiding Digital Twin
Figure 5: Planned Buildings
Yes No
0%
10%
20%
30%
40%
50%
60%
70%
80%
Do you approve of the new building?
Figure 6: Skyline Simulation Feedback
7
(a) Park Creation
(b) Additonal Tree Placement
Figure 7: Green Space
5.2. Green Space Simulation
The Digital Twin concept can also be used for the creation of
green space throughout the city, this can be by the creation of
new park spaces in the city or planting additional trees. Cities
can benefit hugely from the creation of green spaces with new
parks in between buildings. Figure 7a shows a simple demon-
stration of a park that has been created in the city centre as a
place for residents and workers to relax. The amount of citizens
using the park can be tracked using sensors in the smart city. As
the digital twin is available online users can give feedback by
interacting with the model and leaving suggestions. This can
be the placement of new benches, trees, plants or outdoor park
fitness equipment. The sensors from the smart city can be used
to track engagement with the additional equipment.
Figure 7b shows a smaller green space created in the city by
planting some additional trees. Simulations using data from the
smart city can be used to ensure that the trees have access to a
suitable amount of sunlight, temperature and water throughout
the year. Citizens in the local area could also give feedback by
selecting from a short-list of trees chosen to be suitable in this
area.
Figure 8 shows the results of the feedback on additional items
that should be included in the new park. Three of the options:
more benches, more summer flowers and park gym equipment
were proposed in the form. The other extruded option for a
children’s play pen was suggested by a user in the form and
then added as an option, which become the second most popular
option. This encourages citizen engagement as they can see that
the options are being changed based on their feedback. The
More Summer Flowers
20%
Children’s Play Pen
30%
Park Gym Equipment
45%
More Benches
5%
Figure 8: Green Space Simulation Feedback
most popular option was for park gym equipment, this could
be due to the location of the park in a financial district where
employees would like the option of getting some free exercise
outdoors.
5.3. User Tagging Simulation
The availability of a 3D model allows users to interact with
and report objects in the scene. Figure 9 shows a user inter-
acting with a street light in the 3D model. Interacting with the
street light gives the user the option to report an issue such as
the light not working or the light switching on while it is still
bright outside. This report can then be sent to the city council to
fix the problem, with a detailed report of the exact location and
problem that has to be fixed. Citizens interact with a number of
different objects in the environment reporting problems such as
litter, antisocial behaviour, traffic congestion, graffiti and mis-
takes in the digital twin that need to be re-scanned. This allows
for the easy generation of additional smart city data that can be
used to identify the problems that are most often reported by
citizens.
Figure 10 shows the user tagging feedback that was collected
in the simulation. We can see in the top left corner of the map
there have been a series of user tags to report problems with
litter in this area. This can then be reported to the Dublin litter
wardens and environment health officers, with the specific loca-
tion of where the problem is occurring. Preventative measures,
such as increased CCTV or litter warden deployment can then
be implemented in that area to tackle the problem. Some of the
other areas where problems were tagged in the model can also
be seen in the map. These were for problems, such as lights
not working and potholes in the road. Both of these problems
can also be forwarded to the relevant department with the exact
location of the problem. The data can be stored long term to
conduct a detailed analysis over time of how council resources
are being deployed to different areas and what are the specific
problems or locations that are often being tagged.
5.4. Flooding Simulation
Digital Twins can also be very useful for emergency situation
simulations as they allow for the simulation of events that hap-
pen very rarely. Figure 11 shows the simulation of a flooding
8
Figure 9: User Reporting Problem
Figure 10: User Tagging Feedback
scenario in the Docklands. The simulations are able to show
how a rise in water level from the River Liffey would spill into
the surrounding streets. From Figure 11a - 11f we can see how
the increase in water level leads to more damage and how each
area in the city centre would be damaged. This information
could be used for the effective placement of sand bags and other
flooding countermeasures to protect the areas most at risk.
This flooding information can also be used for effective urban
evacuation. Urban authorities can make projections about how
far the water will rise given the forecasted rain [55]. This will
allow them to identify the areas that are most at risk and begin
evacuating people in those effected areas first. Urban authorities
will also have time estimates to evacuate these people as they
can forecast how long it will take for the water level to rise that
amount. The flooding model can then be evaluated at times
when flooding occurs. Additional complexity can be added to
the model to include currents, materials in the river bed, sewage
and drainage systems. The goal is not to create a perfect model
first time, but to create an open model that can be incrementally
improved with additional data and combined with other digital
twin simulations, such as crowd simulations.
5.5. Crowd Simulation
The crowd simulations creates two types of pedestrians in the
Unity model: a standard Adult agent and an Elderly agent. The
average wait times, distance travelled and time in simulation
were compared between the two types. Figure 12 shows the av-
erage wait time and Figure 13 shows the average distance. The
average wait time for the adults and elderly in Figure 12 does
not vary much as the percentage of elderly in the simulation in-
(a) Water Level =Raised 2m (b) Water Level =Raised 3.2m
(c) Water Level =Raised 3.3m (d) Water Level =Raised 3.5m
(e) Water Level =Raised 3.7m (f) Water Level =Raised 4m
Figure 11: Flooding Simulation
creases. However, there is a noticeable difference between the
two agent types with the elderly agents having a much longer
waiting time. This is due to the elderly agents having less mo-
bility and movement speed, which means that they can take
longer to move around obstacles and go through traffic lights.
Further experimentation can evaluate how individual street fur-
niture (e.g., bins, lights, footpath width etc.,) effects the waiting
time of pedestrian types as they move through the city. The re-
sults from these simulation can then be used to inform urban
planning and policy.
Figure 13 shows the average distance that is travelled by the
agent types. The elderly agents distance travelled remains quite
constant. However, the adult distance travelled increases as the
percentage of elderly agents in the simulation increases. This
indicates that the adult agents can use their increased speed to
move around any elderly agents in the simulation or obstacles.
This keeps their average waiting time low as shown in Figure
12, even though the distance they travel increases with the per-
centage of elderly people.
6. Limitations of Current Digital Twin
In this section we identify some of the limitations of the cur-
rent Digital Twin through the layers of the model outlined in
Figure 1. This is the first version of the model to be released
and these limitations can be addressed in future versions.
6.1. Buildings
The Docklands model includes a large area of Dublin, some
of the modern buildings along the waterfront are captured in
9
0% 20% 40% 60% 80% 100%
Percentage of Elderly
1
2
3
4
5
6
7
8
9
Average Wait Time (s)
Elderly Average Wait Time
Adult Average Wait Time
Figure 12: Average wait time of the agents vs. the percentage of the flock that
is of the Elderly type
0% 20% 40% 60% 80% 100%
Percentage of Elderly
60
80
100
120
140
160
Average Distance Travelled
Elderly Average Distance Travelled
Adult Average Distance Travelled
Figure 13: Average distance travelled by the agents vs. the percentage of the
flock that is of the Elderly type
great detail. However, there are some areas in the model, espe-
cially of older buildings and open spaces, such as the Bus Depot
in Figure 14 that are represented by grey boxes. Although the
function of the grey box cannot be determined from the model
it does not affect the functionality of the citizen feedback or
crowd simulations.
(a) Physical Bus Depot (b) Virtual Bus Depot
Figure 14: Physical and Virtual Bus Depot Comparison
(a) (b)
(c) (d)
Figure 15: Rail bridge that has pedestrian pathways to either side of it, but
cannot be passed in the 3D model
6.2. Infrastructure
The rail bridge near Samuel Beckett bridge is shown as seen
in the physical world and in the digital twin in Figure 15. Fig-
ure 15a and Figure 15c show the comparison of the physical
and virtual left side of the bridge. The virtual representation of
the pedestrian path is narrower than the physical model. The
bridge also has legs sticking out that cover the pedestrian foot-
path area in the model. Changes to the size of the footpath and
the position of the bridge were implemented in Unity to make
the simulations more realistic.
Figure 15b shows the right side of the bridge in the physical
world and Figure 15d shows how this is represented in the dig-
ital twin. The digital twin is missing the small bridge as seen in
Figure 15b to allow pedestrian access on this side of the bridge.
A small bridge structure as shown in Figure 15d is created in
Unity to allow for more accurate pedestrian simulations.
6.3. Mobility
There are some urban mobility systems that are not included
in the model. For example, Dublin has a light rail system called
Luas that is not included in the model. The addition of this light
rail system would allow for more detailed urban mobility sim-
ulations and the comparison between a range of urban mobility
systems. There is also a lack of bus stops and road markings in
the model, but this information can be added to the model using
OpenStreetMap.
6.4. Smart City
Data produced from the smart city is what drives the accurate
simulations in the digital twin. Dublin makes a lot of data avail-
able through the Dublinked9open data source. This provides a
9https://data.smartdublin.ie/
10
number of data sources about population, transportation and in-
frastructure as well as information about the environment and
energy. However, there is a lack of fine grain data, which is of-
ten aggregated. This can lead to having to interpolate datasets,
which leads to less accurate simulations.
7. Conclusion and Future Work
The results section has illustrated a range of simulations that
can be carried out by using a digital twin of a smart city. The
results from these simulations can feed back through the layers
of the digital twin model, as shown in Figure 1 to advise on
real changes in a smart city. The digital twin can be used to
engage citizens and get a lot of valuable feedback on key ur-
ban planning and policy decisions. The results of skyline and
green space planning simulations have shown how user feed-
back and suggestions can be collected to provide additional data
to inform urban planning and policy decisions to allow for ad-
ditional changes before a final decision is made. In the green
space planning simulation options can be left open to allow cit-
izens to propose their own ideas, such as a children’s play pen
in the park. These initial form-based method can be extended to
a tagging model as shown in the user tagging simulation. This
allows citizens to interact with all the objects in the digital twin
and tag problems or suggestions. These problems or sugges-
tions can then be sent to the relevant government department
with the exact location of the problem.
A digital twin can also be used for a range of other urban
planning decisions and policy. As the model is 3D, it allows
for the simulation of rare events that require 3D data, such as
flooding in the city. This can then inform the city’s policy of
what areas of the city to evacuate first and where to best place
sandbags. The crowd simulation in Section 5.5 has shown how
multiple agents types, such as adults and elderly can be created
in Unity using mobility data from previous experimental stud-
ies [50]. These simulations can be extended to evaluate future
urban planning decisions in a smart city such as the impact that
a change in gradient of a footpath or adding additional street
furniture will have on different pedestrians, such as adults and
elderly.
In future work, we plan to extend the public data that we use
for the simulations with data from additional IoT services in the
surrounding area. These service may be provided by the city
council or from private citizens or companies in the area. The
increased amount of data would allow for more realistic simula-
tions with real time information about crowds, noise pollution
and traffic in the area. This digital twin model with mobility
data can be adapted to multiple other scenarios that were not
investigated in this paper. In future work, we plan to evaluate
a concert simulation that would see an influx of pedestrian and
vehicle traffic attempting to reach the Three Arena in Dublin
(capacity 13,000). Simulations could investigate the placement
of fire evacuation points as well as the effect that increasing the
capacity of the stadium would have on the traffic and fire evac-
uation policy.
Acknowledgment
This work was funded by Science Foundation Ireland (SFI)
under grant 13/IA/1885.
References
[1] V. Albino, U. Berardi, R. M. Dangelico, Smart cities–definitions, dimen-
sions, and performance, Proceedings IFKAD (2013) 1723–1738.
[2] P. Neirotti, A. De Marco, A. C. Cagliano, G. Mangano, F. Scorrano, Cur-
rent trends in smart city initiatives: Some stylised facts, Cities 38 (2014)
25–36.
[3] H. Menouar, I. Guvenc, K. Akkaya, A. S. Uluagac, A. Kadri, A. Tuncer,
Uav-enabled intelligent transportation systems for the smart city: Appli-
cations and challenges, IEEE Communications Magazine 55 (3) (2017)
22–28.
[4] V. Oldenbroek, L. A. Verhoef, A. J. Van Wijk, Fuel cell electric vehicle as
a power plant: Fully renewable integrated transport and energy system de-
sign and analysis for smart city areas, International Journal of Hydrogen
Energy 42 (12) (2017) 8166–8196.
[5] L. S´
anchez, I. Elicegui, J. Cuesta, L. Mu˜
noz, J. Lanza, Integration of
utilities infrastructures in a future internet enabled smart city framework,
Sensors 13 (11) (2013) 14438–14465.
[6] L. Parra, S. Sendra, J. Lloret, I. Bosch, Development of a conductivity
sensor for monitoring groundwater resources to optimize water manage-
ment in smart city environments, Sensors 15 (9) (2015) 20990–21015.
[7] A. Medvedev, P. Fedchenkov, A. Zaslavsky, T. Anagnostopoulos, S. Kho-
ruzhnikov, Waste management as an iot-enabled service in smart cities,
in: Internet of Things, Smart Spaces, and Next Generation Networks and
Systems, Springer, 2015, pp. 104–115.
[8] A. Abella, M. Ortiz-De-Urbina-Criado, C. De-Pablos-Heredero, A model
for the analysis of data-driven innovation and value generation in smart
cities’ ecosystems, Cities 64 (2017) 47–53.
[9] M. Angelidou, Smart cities: A conjuncture of four forces, Cities 47
(2015) 95–106.
[10] A. Caragliu, C. F. Del Bo, Smart innovative cities: The impact of smart
city policies on urban innovation, Technological Forecasting and Social
Change 142 (2019) 373–383.
[11] M. Mohammadi, A. Al-Fuqaha, Enabling cognitive smart cities using big
data and machine learning: Approaches and challenges, IEEE Communi-
cations Magazine 56 (2) (2018) 94–101.
[12] G. White, S. Clarke, Urban intelligence with deep edges, IEEE Access 8
(2020) 7518–7530. doi:10.1109/ACCESS.2020.2963912.
[13] J. Chin, V. Callaghan, I. Lam, Understanding and personalising smart
city services using machine learning, the internet-of-things and big data,
in: 2017 IEEE 26th International Symposium on Industrial Electronics
(ISIE), IEEE, 2017, pp. 2050–2055.
[14] G. White, A. Palade, C. Cabrera, S. Clarke, Autoencoders for qos pre-
diction at the edge, in: 2019 IEEE International Conference on Perva-
sive Computing and Communications (PerCom, 2019, pp. 1–9. doi:
10.1109/PERCOM.2019.8767397.
[15] L. Wang, D. Sng, Deep learning algorithms with applications to video
analytics for a smart city: A survey, arXiv preprint arXiv:1512.03131.
[16] L. Zhao, J. Wang, J. Liu, N. Kato, Routing for crowd management in
smart cities: A deep reinforcement learning perspective, IEEE Commu-
nications Magazine 57 (4) (2019) 88–93.
[17] P. Mannion, J. Duggan, E. Howley, An experimental review of reinforce-
ment learning algorithms for adaptive traffic signal control, in: Auto-
nomic Road Transport Support Systems, Springer, 2016, pp. 47–66.
[18] R. C. Hsu, C.-T. Liu, H.-L. Wang, A reinforcement learning-based tod
provisioning dynamic power management for sustainable operation of en-
ergy harvesting wireless sensor node, IEEE Transactions on Emerging
Topics in Computing 2 (2) (2014) 181–191.
[19] M. J. Kaur, V. P. Mishra, P. Maheshwari, The convergence of digital twin,
iot, and machine learning: Transforming data into action, in: Digital Twin
Technologies and Smart Cities, Springer, 2020, pp. 3–17.
[20] S. Boschert, R. Rosen, Digital twin the simulation aspect, in: Mechatronic
Futures, Springer, 2016, pp. 59–74.
[21] D. Puri, The vital role of technology in the thai cave rescue mission
(2018).
11
URL https://www.networkworld.com/article/3291787/
the-vital- role-of- technology-in-the-thai-cave-rescue-mission.
html
[22] B. Dixon, The technology behind the thailand cave rescue (2018).
URL https://www.esri.com/about/newsroom/blog/
technology-behind- thailand-cave- rescue/
[23] K. M. Alam, A. El Saddik, C2ps: A digital twin architecture reference
model for the cloud-based cyber-physical systems, IEEE Access 5 (2017)
2050–2062.
[24] A. El Saddik, Digital twins: the convergence of multimedia technologies,
IEEE MultiMedia 25 (2) (2018) 87–92.
[25] Q. Qi, F. Tao, T. Hu, N. Anwer, A. Liu, Y. Wei, L. Wang, A. Nee, En-
abling technologies and tools for digital twin, Journal of Manufacturing
Systemsdoi:https://doi.org/10.1016/j.jmsy.2019.10.001.
URL http://www.sciencedirect.com/science/article/pii/
S027861251930086X
[26] W. Luo, T. Hu, C. Zhang, Y. Wei, Digital twin for cnc machine tool: mod-
eling and using strategy, Journal of Ambient Intelligence and Humanized
Computing 10 (3) (2019) 1129–1140.
[27] E. Glaessgen, D. Stargel, The digital twin paradigm for future nasa and
us air force vehicles, in: 53rd AIAA/ASME/ASCE/AHS/ASC Structures,
Structural Dynamics and Materials Conference 20th AIAA/ASME/AHS
Adaptive Structures Conference 14th AIAA, p. 1818.
[28] F. Tao, J. Cheng, Q. Qi, M. Zhang, H. Zhang, F. Sui, Digital twin-driven
product design, manufacturing and service with big data, The Interna-
tional Journal of Advanced Manufacturing Technology 94 (9-12) (2018)
3563–3576.
[29] R. Rosen, G. Von Wichert, G. Lo, K. D. Bettenhausen, About the im-
portance of autonomy and digital twins for the future of manufacturing,
IFAC-PapersOnLine 48 (3) (2015) 567–572.
[30] M. Grieves, J. Vickers, Digital twin: Mitigating unpredictable, undesir-
able emergent behavior in complex systems, in: Transdisciplinary per-
spectives on complex systems, Springer, 2017, pp. 85–113.
[31] K. Bruynseels, F. Santoni de Sio, J. van den Hoven, Digital twins in health
care: ethical implications of an emerging engineering paradigm, Frontiers
in genetics 9 (2018) 31.
[32] G. White, Z. Liang, S. Clarke, A quantified-self framework for exploring
and enhancing personal productivity, in: 2019 International Conference
on Content-Based Multimedia Indexing (CBMI), IEEE, 2019, pp. 1–6.
[33] S. P. Bhavnani, A. M. Sitapati, Virtual care 2.0a vision for the future of
data-driven technology-enabled healthcare, Current treatment options in
cardiovascular medicine 21 (5) (2019) 21.
[34] N. Mohammadi, J. E. Taylor, Smart city digital twins, in: 2017 IEEE
Symposium Series on Computational Intelligence (SSCI), IEEE, 2017,
pp. 1–5.
[35] N. Mohammadi, J. Taylor, Devising a game theoretic approach to enable
smart city digital twin analytics, in: Proceedings of the 52nd Hawaii In-
ternational Conference on System Sciences, 2019.
[36] G. White, V. Nallur, S. Clarke, Quality of service approaches in iot: A
systematic mapping, Journal of Systems and Software 132 (2017) 186–
203.
[37] K. H. Soon, V. H. S. Khoo, Citygml modelling for singapore 3d national
mapping, ISPRS - International Archives of the Photogrammetry, Re-
mote Sensing and Spatial Information Sciences XLII-4/W7 (2017) 37–42.
URL https://www.int-arch- photogramm-remote- sens-spatial-inf-sci.
net/XLII-4- W7/37/2017/
[38] M. Enzer, A. Bolton, C. Boulton, D. Byles, A. Cook, L. Dobbs, P. A.
El Hajj, E. Keaney, A. Kemp, C. Makri, et al., Roadmap for delivering
the information management framework for the built environmentdoi:
https://doi.org/10.17863/CAM.38227.
[39] P. A. Lopez, M. Behrisch, L. Bieker-Walz, J. Erdmann, Y.-P. Fl¨
otter¨
od,
R. Hilbrich, L. L¨
ucken, J. Rummel, P. Wagner, E. WieBner, Microscopic
traffic simulation using sumo, in: 2018 21st International Conference on
Intelligent Transportation Systems (ITSC), IEEE, 2018, pp. 2575–2582.
[40] A. Caragliu, C. Del Bo, P. Nijkamp, Smart cities in europe, Journal of
urban technology 18 (2) (2011) 65–82.
[41] R. P. Dameri, et al., Smart city implementation, Progress in IS; Springer:
Genoa, Italy.
[42] A. Cocchia, Smart and digital city: A systematic literature review, in:
Smart city, Springer, 2014, pp. 13–43.
[43] S. I. Chiodi, Crime prevention through urban design and planning in the
smart city era: The challenge of disseminating cp-udp in italy: Learning
from europe, Journal of Place Management and Development 9 (2) (2016)
137–152.
[44] M. Abdel-Basset, M. Mohamed, The role of single valued neutrosophic
sets and rough sets in smart city: Imperfect and incomplete information
systems, Measurement 124 (2018) 47–55.
[45] B. Williamson, Educating the smart city: Schooling smart citizens
through computational urbanism, Big Data & Society 2 (2) (2015)
2053951715617783.
[46] I. M. Johnson, Smart cities, smart libraries, and smart librarians.
[47] M. I. Pramanik, R. Y. Lau, H. Demirkan, M. A. K. Azad, Smart health:
Big data enabled health paradigm within smart cities, Expert Systems
with Applications 87 (2017) 370–383.
[48] R. Jalali, K. El-Khatib, C. McGregor, Smart city architecture for com-
munity level services through the internet of things, in: 2015 18th Inter-
national Conference on Intelligence in Next Generation Networks, IEEE,
2015, pp. 108–113.
[49] K. Hashimoto, K. Yamada, K. Tabata, M. Oda, T. Suganuma, A. Rahim,
P. Vlacheas, V. Stavroulaki, D. Kelaidonis, A. Georgakopoulos, ikaas data
modeling: A data model for community services and environment mon-
itoring in smart city, in: 2015 IEEE International Conference on Auto-
nomic Computing, IEEE, 2015, pp. 301–306.
[50] J. A. Oxley, E. Ihsen, B. N. Fildes, J. L. Charlton, R. H. Day, Crossing
roads safely: An experimental study of age differences in gap selection
by pedestrians, Accident Analysis and Prevention 37 (5) (2005) 962 –
971. doi:https://doi.org/10.1016/j.aap.2005.04.017.
URL http://www.sciencedirect.com/science/article/pii/
S0001457505000795
[51] G. Castelli, A. Cesta, M. Diez, M. Padula, P. Ravazzani, G. Rinaldi,
S. Savazzi, M. Spagnuolo, L. Strambini, G. Tognola, E. F. Campana, Ur-
ban intelligence: a modular, fully integrated, and evolving model for cities
digital twinning, in: 2019 IEEE 16th International Conference on Smart
Cities: Improving Quality of Life Using ICT IoT and AI (HONET-ICT),
2019, pp. 033–037.
[52] R. Anguluri, P. Narayanan, Role of green space in urban planning: Out-
look towards smart cities, Urban Forestry & Urban Greening 25 (2017)
58–65.
[53] A. C. K. Lee, H. C. Jordan, J. Horsley, Value of urban green spaces in pro-
moting healthy living and wellbeing: prospects for planning, Risk man-
agement and healthcare policy 8 (2015) 131.
[54] K. Pyatkova, A. S. Chen, S. Djordjevi´
c, D. Butler, Z. Vojinovi´
c, Y. A.
Abebe, M. Hammond, Flood impacts on road transportation using micro-
scopic traffic modelling techniques, in: Simulating Urban Traffic Scenar-
ios, Springer, 2019, pp. 115–126.
[55] S. Alvisi, G. Mascellani, M. Franchini, A. Bardossy, Water level forecast-
ing through fuzzy logic and artificial neural network approaches, Hydrol-
ogy and Earth System Sciences Discussions 10 (1) (2006) 1–17.
12
