Nat Hazards

DOI 10.1007/s11069-016-2739-5

ORIGINAL PAPER

Seismic vulnerability assessment using association rule

learning: application to the city of Constantine, Algeria

Abdelheq Guettiche1,2 • Philippe Guéguen3 •

Mostefa Mimoune2

Received: 27 May 2016 / Accepted: 27 December 2016

 Springer Science+Business Media Dordrecht 2017

Abstract We performed a seismic vulnerability assessment of the city of Constantine

(Algeria) using the Risk-UE and datamining-based methods [association rule learning
(ARL)]. The ARL method consists in establishing relationships between building attributes
(number of stories or building age) and the vulnerability classes of the European Macro-
seismic Scale, EMS98. This approach avoids the costly process of drawing up an inventory
of building characteristics in the field, which often discourages the assessment of seismic
risk initiatives in weak to moderate seismic-prone regions. We showed that the accuracy of
the assessment is independent of the subset used for the learning phase leading to devel-
opment of the Constantine vulnerability proxy. Considering only two attributes, the vul-
nerability assignment is equal to about 75%, reaching 99% if material is added to the
attributes considered. Comparison of Risk-UE and ARL results revealed a reliable
assessment of vulnerability, the differences having only a slight impact on the probability
of exceeding the damage level computed by EMS98 or Risk-UE in Constantine. The
results of this study suggest that the ARL-based vulnerability proxy is efficient and could
be applied to the rest of Algeria.

Keywords Vulnerability  Scenario  Earthquake  Association rule learning  Risk-UE 

Damage grade  EMS98  Constantine

& Philippe Guéguen

[email protected]
1
Centre Universitaire Abdelhafid Boussouf, Mila, Algeria
2
Civil Engineering Department, Université des Frères Mentouri, Constantine, Algeria
3
Institut des Sciences de la Terre – ISTerre, Université de Grenoble Alpes/CNRS/IFSTTAR,
Grenoble, France

123
 Nat Hazards

1 Introduction

In order to reduce risk, several seismic-prone cities around the world (Tucker et al.
2013), such as Quito in Ecuador (Chatelain et al. 1999), Kathmandu in Nepal (KVERMP
1998), Istanbul in Turkey (Erdik et al. 2003), Catania in Italy (Faccioli et al. 1999) and
Nice in France (Bard et al. 2005), have been analyzed in terms of seismic risk, with the
objectives of educating the public, producing seismic scenarios to simulate losses and
operational problems and implementing an action plan to manage seismic risk. Benson
and Twigg (2004) claim that with $40 million invested in preventive measures world-
wide in the 1990s, economic losses have been reduced by $280 million. They also
support the view of emergency specialists, who are increasingly insistent on the need to
invest in preparation, prevention and disaster attenuation measures, such as those sup-
ported by seismic scenarios, to reduce losses. Moreover, seismic risk scenarios are useful
to study the best investment framework for the seismic retrofitting of buildings that can
be attractive against the effects of long return periods events (Smyth et al. 2004). In fact,
predicted damage in existing structures is the key parameter to anticipate direct and
indirect seismic losses and fatalities. Consequently, before simulating and testing losses,
efforts must be concentrated on the seismic vulnerability assessment of existing struc-
tures at urban or regional scales, such as in Algeria, a region whose first seismic code
dates back to 1981 for public buildings. Assuming a small rate of renewal, the majority of
constructions of Algeria’s building stock were therefore built with no seismic design
engineering and can be considered vulnerable to regional earthquakes, as demonstrated
by the 2003 Boumerdes earthquake where many reinforced concrete buildings were
extensively damaged (Meslem et al. 2012).
Assessing vulnerability at the urban scale is a complex task due to the number of
buildings concerned, their heterogeneities in terms of structural design and seismic
response and the lack of main information concerning their design (Guéguen 2013).
Macro-scale methods have been developed, based on data collected in the field during
post-seismic periods. They propose damage functions calibrated on observed damage and
building typology, as proposed by the Federal Emergency Management Agency (FEMA)
in the USA (Hazus 1997), the Gruppo Nazionale per Difesa dai Terremoti in Italy
(Benedetti and Petrini 1984; GNDT 1993) or the Risk-UE method developed within the
framework of the European project (Spence and Brun 2006; Lestuzzi et al. 2016). Barbat
et al. (2010) published a review of the seismic vulnerability assessment methods for urban
application. Whatever the method, the difficulty remains to inventory the buildings,
involving costly visual screening throughout the city. This is even more complex in
moderate seismic-prone regions, where resources for seismic evaluation are often difficult
to mobilize and are limited (Guéguen et al. 2007), even though the seismic hazard is not
negligible.
Recently, simplified macro-scale methods have been adapted to reduce the inherent cost
of the building in situ surveys at the urban scale. Such initiatives consist in simplifying the
visual screening stage by considering only the key parameters whose contribution to
seismic vulnerability is significant (Guéguen et al. 2007) or by using remote sensing
methods (Mueller et al. 2006; Geiß et al. 2014; Riedel et al. 2015). Datamining-based
methods have also been developed to derive the best proxy linking the building features,
easily assessed by remote sensing or from preexisting databanks (e.g., national census),
with the seismic vulnerability of buildings (Riedel et al. 2014, 2015).

123
Nat Hazards

In this study, we propose to validate this approach in a seismic-prone city, Constantine

in Algeria, for which an extensive vulnerability assessment using the Risk-UE method is
available. After presenting the seismic context and urbanization of Constantine, the method
is developed and applied to the city. In the last section, the results are compared with those
of the Risk-UE method, before concluding on the efficiency of this approach.

2 The city of Constantine

The city of Constantine (Fig. 1a) is located in the northern part of Algeria. The tectonic
context of the Constantine region results from the convergence of the Eurasian and
African plates. Descriptions of the tectonic context can be found in the abundant liter-
ature (e.g., McKenzie 1972; Aoudia and Meghraoui 1995; Mickus and Jallouli 1999;
Yelles-Chaouche et al. 2006; Hamdache et al. 2012). As a result, this region is one of the
most seismically active regions of the Mediterranean (Buforn et al. 1995; Kherroubi et al.
2009), characterized by intense seismic activity. This activity mainly affects the northern
part of Algeria, home to the most important cities, i.e., the country’s most densely
populated cities, concentrating housing, infrastructures, economic and industrial
activities.
The city is exposed to a complex and moderate to strong seismic hazard (Peláez et al.
2006; Baba Hamed et al. 2013). The Ain Smara Fault, situated southeast of Constantine

Fig. 1 a General situation of the city of Constantine in Algeria. b Location of the main fault and historical
earthquakes mentioned in the text (after Bounif et al. 1987). c Seismic macro-zoning map of Algeria (after
RPA03 2003). d Location of the historic downtown area concerned by this study and aerial view of HDT
with subzones Z1, Z2 and Z3 described in this study

123
 Nat Hazards

(Fig. 1b), is a major active fault and a primary source of earthquakes affecting the Eastern
Tellian Atlas (northeast Algeria) confirmed by surface ruptures observed after the 1985
earthquake (Bounif et al. 1987). This fault can be considered as an important potential
source of seismic activity according to the probabilistic seismic hazard study done for
Algeria (Peláez et al. 2006; Fig. 1c). It generated the strongest earthquake in 1908, 1947
and in 1985, the latest corresponding to the strongest event recorded since the imple-
mentation of instrumental seismology (Bounif et al. 1987; Ousadou et al. 2013), causing
significant damage in Constantine (Ms = 5.9, October 27, 1985), with macro-seismic
intensities ranging from IX to X.
Constantine has about 1 million inhabitants according to the last census of National
Office of Statistics in 2008 (Office national des statistiques, ONS 2008). It is a very active
city in social, economic and industrial terms, considered to be the third most important city
in Algeria. It is also famous for its cultural heritage buildings, including constructions of
urban and architectural value. Analysis of the Constantine city has been performed in the
past using Hazus method (Boukri et al. 2014) with concluding to a high vulnerability of the
city. For our study, the inventory phase covered only the historic downtown area (HDT,
Fig. 1d), for the collection of building details required for the seismic vulnerability
assessment using the Risk-UE method (Milutinovic and Trendafiloski 2003). According to
official statistics published by the ONS (2008), this area is characterized by a dense, old
stock of residential buildings and is highly populated, with 448,374 inhabitants that cor-
respond to 2089 inhabitants/km2.
In total, 2252 buildings were surveyed by visual screening, collecting data on the state
of conservation and on all structural and non-structural characteristics. A specific technical
form was established (Appendix 1) for building by building inspection, after consultation
with the direction in charge of the urban planning and construction in Constantine
(Direction de l’Urbanisme et de la Construction Constantine, DUC) and the Technical
Control of Construction (CTC) in Constantine, also with the help of several technical
reports and documents available on the building construction in Constantine. Moreover, a
specific datasheet was developed to compute the vulnerability index and the associated
damage (Appendix 1). The building inventory is certainly the most time-consuming step of
the seismic vulnerability assessment process. It took 3 years to collect detailed information
on the design and construction types of Constantine’s buildings according to Risk-UE
attributes, i.e., type of material (masonry, reinforced concrete, steel), year of construction
classified into six classes, number of floors, in plan and elevation irregularities, state of
maintenance, aggregation conditions for distinguishing stand-alone, middle, corner or
header building (i.e., adjacent with another building on one side or on two or more sides),
and information on soil morphology (cliff or slope). Vulnerability indexes by typology and
modifiers used for Risk-UE are given Tables 1 and 2, respectively. At the same time, each
building was classified according to the European Macro-seismic Scale typology (EMS98,
Grünthal and Levret 2001).
This information was fed into the Constantine Building Databank (CBD). Moreover, the
national Algerian organism of technical and building inspection done in 2009 during a
detailed but partial field survey confirmed the CBD information, by crossing modifiers and
vulnerability assessment for several buildings. Finally, the HDT was divided into three
zones (Z1, Z2 and Z3) according to the historic urbanization of the area (Fig. 1d). In Z1,
about 63% of the total building stock (1887 buildings) was surveyed (i.e., 1185 buildings),
in Z2 about 83% (1016/1221) and about 41% in Z3 (51/123). The distribution of surveyed
buildings according to building material reflects the evolution of construction methods and

123
Nat Hazards

Table 1 Representative values of vulnerability indexes for each class of the building typology used in
Risk-UE (after Milutinovic and Trendafiloski 2003)
Typology Description Representatives vulnerability index IV

IVmin IV- IV* IV? IVmax

M1.1 Rubble stone 0.62 0.81 0.873 0.98 1.02

M1.2 Simple stone 0.46 0.65 0.74 0.83 1.02
M1.3 Massive stone—Ashlar 0.3 0.49 0.616 0.793 0.86
M2 Adobe (earth bricks) 0.62 0.687 0.84 0.98 1.02
M3.1 Wooden slabs—Hardwood 0.46 0.65 0.74 0.83 1.02
M3.2 Masonry arches 0.46 0.65 0.776 0.953 1.02
M3.3 Composite steel and masonry slabs 0.46 0.527 0.704 0.83 1.02
M3.4 Reinforced concrete slabs 0.3 0.49 0.616 0.793 0.86
M4 Reinf. masonry load-bearing walls 0.14 0.33 0.451 0.633 0.7
M5 Structures made completely of reinforced masonry 0.3 0.49 0.694 0.953 1.02
RC1 Concrete moment frame -0.02 0.047 0.442 0.8 1.02
RC2 Concrete shear walls -0.02 0.047 0.386 0.67 0.86
RC3.1 Regular infilled walls -0.02 0.007 0.402 0.76 0.98
RC3.2 Irregular frames 0.06 0.127 0.522 0.88 1.02
RC4 RC dual system (frame and walls) -0.02 0.047 0.386 0.67 0.86
RC5 Precast concrete tilt-up walls 0.14 0.207 0.384 0.51 0.7
RC6 Precast RC frames and shear walls 0.3 0.367 0.544 0.67 0.86
S1 Steel moment frames -0.02 0.467 0.363 0.64 0.86
S2 Steel braced frames -0.02 0.467 0.287 0.48 0.7
S3 Steel frames ? unreinf. mas. infill w 0.14 0.33 0.484 0.64 0.86
S4 Steel support beams/columns with structural concrete -0.02 0.047 0.224 0.35 0.54
wall cast in situ
S5 Steel and reinforced concrete components -0.02 0.257 0.402 0.72 1.02
W Wood structure 0.14 0.207 0.447 0.64 0.86

urbanization trends: Unreinforced masonry buildings represent 94% of the whole buildings
in Z1, 64% in Z2 and 0% in Z3.
A general description of the CBD is shown in Fig. 2. In this figure, buildings are
grouped according to four attributes: (1) period of construction, according to the historic
urbanization of the city and evolutions in Algerian design code; (2) number of stories,
defined according to the interval given in the Risk-UE method, i.e., low-rise (1–2), mid-rise
(3–5) and high-rise ([6) buildings; (3) type of material found in the studied area, i.e.,
reinforced concrete (RC), unreinforced masonry and steel; and (4) roof shape (slope or
flat). These four attributes were selected for their ease of observation, with no attribution
error, on the urban scale. In total, 78% of the buildings surveyed were unreinforced
masonry, 21% reinforced concrete and only 1% steel. The CBD contains 2252 buildings:
• 448 built before 1837, composed mainly of unreinforced masonry buildings in adobe
and rubble stone,
• 744 from 1837 to 1920, corresponding to unreinforced masonry and RC buildings;
• 819 between 1921 and 1962, corresponding to the generalization of reinforced concrete
in buildings but without application of any seismic code measures;

123
 Nat Hazards

Table 2 Scores for the vulnerability modifiers used for masonry and reinforced concreted buildings,
adapted from Risk-UE (after Milutinovic and Trendafiloski 2003) to the Constantine city
Vulnerability factors Masonry Reinforced concrete

Parameters IVM Parameters Low IVM High

code Medium code
code

Code level N/A ?0.16 0 -0.16

State of preservation Good -0.04 Good N/A
Bad ?0.04 Bad ?0.04 ?0.02 0
Number of floors Low (1 or 2) -0.02 Low (1 or 2) -0.04 -0.04 -0.04
Medium (3, 4 or 5) ?0.02 Medium (3–5) 0 0 0
High (6 or more) ?0.06 High(6 or ?0.08 ?0.06 0.04
more)
Soft story Demolition/ ?0.04 N/A
transparency
Plan irregularity ?0.04 Shape ?0.04 ?0.02 0
Torsion ?0.02 ?0.01 0
Vertical irregularity ?0.02 ?0.04 ?0.02 0
Short columns ?0.02 ?0.01 0
Bow windows ?0.04 ?0.02 0
Retrofitting -0.08 Bad mainten. ?0.04 ?0.02 0
interventions ?0.08
Aseismic devices Barbican, foil arches, -0.04 N/A
buttresses
Aggregate effect: Middle -0.04 Insufficient ?0.04 0 0
position Corner ?0.04 joint
Header ?0.06
Aggregate building: Staggered floors ?0.02 N/A
elevation Buildings -0.04
of different heights ?0.04
Foundations Foundations at ?0.04 Beams -0.04 0 0
different levels Connect. 0 0 0
beams
Isolated ?0.04 0 0
footing
Soil morphology Slope ?0.02 Slope ?0.02 ?0.02 ?0.02
Cliff ?0.04 Cliff ?0.04 ?0.04 ?0.04

• 119 from 1963 to 1981;

• 38 between 1982 and 2003;
• 84 after 2003.
Most of the constructions of the last three periods are RC buildings. The two first
periods correspond to the Ottoman and French epochs, representing approximately 50% of
buildings surveyed herein. Almost all buildings (94%) were erected before publication of
the first Algerian seismic code in 1981 (RPA81 1981), therefore considered as non-engi-
neered buildings, 2% were designed between 1981 and publication of the latest version of

123
Nat Hazards

Fig. 2 Description of the number of buildings surveyed in this study according to four attributes: period of
construction, number of floors, material type and roof shape

the Algerian seismic code of 2003 (RPA03 2003), considered as buildings with moderate
seismic design according to Risk-UE (moderate code), and only 4% of construction were
built after 2003, considered as high seismic design (high-code) buildings. Moreover, the
study contains about 120 high-rise buildings, which represent only 5% of the building
stock, 845 (38%) and 1287 (57%) buildings being classified as low-rise and mid-rise,
respectively.

Table 3 Distribution of surveyed buildings by Risk-UE typology

Typologies EMS98 Building types Risk-UE Nb % Total %

Unreinforced masonry M1.1: rubble stone 105 4.66 78.60

M1.2: simple stone 304 13.50
M1.3: massive stone—Ashlar 903 40.10
M2: adobe (earth bricks) 446 19.80
M3.1: wooden slabs—Hardwood flooring 2 0.09
M3.4: reinforced concrete slabs 9 0.40
Reinforced masonry M4: reinf. masonry load-bearing walls 1 0.04 20.78
Reinforced concrete RC1: concrete moment frame 281 12.48
RC2: concrete shear walls 76 3.37
RC3.1: regular infilled walls 80 3.55
RC3.2: irregular frames 1 0.04
RC4: RC dual system (frame and walls) 6 0.27
RC5: precast concrete tilt-up walls 22 0.98
RC6: precast C frames and shear walls 2 0.09
Steel S.1: steel moment frames 2 0.09 0.62
S.2: steel braced frames 8 0.36
S.3: steel frames ? unreinf. mas. infill w 4 0.18
Total 2252 100 100

123
 Nat Hazards

Table 3 shows the distribution of buildings classified according to the Risk-UE typology
(Milutinovic and Trendafiloski 2003). Solid stone, class M1.3 (called Ashlar), and adobe,
class M2, are the most representative typologies in the building stock surveyed. Compared
with the EMS98 typology, the vulnerability classes range from A (most vulnerable) to F
(least vulnerable), with 99% of unreinforced masonry buildings in classes A and B, 75% of
RC buildings in class C and the remaining 25% being divided among classes D and E. The
vulnerability reflects the low seismic design of the existing RC and unreinforced masonry
buildings, built before the issue of the first Algerian seismic code.

3 Methods

The flowchart of the methods followed in this study is shown Fig. 3, each branch being
explained in this section.

3.1 Brief description of Risk-UE level 1

In the first step, the seismic vulnerability assessment of zones 1–3 was computed using the
Risk-UE method, considered as the reference assessment method in this study. Risk-UE

Fig. 3 Flowchart of the methods followed in this study

123
Nat Hazards

vulnerability assessment method was developed for the eponymous European project
considering seven major European cities (Spence and Brun 2006). At first time, the method
consists classifying each building into the typology defined by the materials and/or
structural systems. Basic vulnerability indexes are attributed to each typology class (Mi-
lutinovic and Trendafiloski 2003) corresponding to the median value IV* and to the lower
IV- and upper IV? bounds of the possible values of the vulnerability index. Modifier
factors are then applied to IV*, to take into account height, irregularities, position, etc. The
final vulnerability index, independent of the hazard, is the sum of IV* and the weighted
values of the modifier factors as follows:
IV ¼ IV þ DVM þ DVR ð1Þ
where DVM represents the seismic behavior modifiers and DVR is a regional vulnerability
factor (considered equal to 0). Once vulnerability has been assessed, the average damage
grade lD is given by the following equation:
  
I þ 6:25IV  13:1
lD ¼ 2:5 1 þ tanh ð2Þ
2:3
where I is the seismic hazard described in terms of EMS98 macro-seismic intensity. lD
varies from 0 (no damage) to 5 (severe damage or destruction) following the six-level
damage scale Dk given in EMS98, with six grades (k [0, 5]) ranging from no damage (D0)
to complete destruction (D5). The binomial distribution proposed in Lagomarsino and
Giovinazzi (2006) and adjusted to post-earthquake observation is then used to give damage
as the probability P(Dk) of reaching each damage grade Dk (k [0, 5]) for a given lD as
follows:
5! l k  l 5k
D
PðDk Þ ¼ 1 D ð!: factorial operatorÞ: ð3Þ
k!ð5  kÞ! 5 5

The vulnerability curves are then plotted after computing the probability density
function P(Dk) for each vulnerability class. For each class of vulnerability and each
intensity, they represent the probability of exceeding a degree of damage k for a given
intensity (Fig. 4).

3.2 Association rule learning classification

The building-by-building inventory of structural attributes is certainly the most costly

step in any process to estimate seismic vulnerability at an urban scale. Riedel et al.
(2014) thus propose a datamining-based method for developing a seismic vulnerability
proxy using basic attributes. There is no doubt that additional information such as
material or resistance of structural elements contributes to the vulnerability of existing
buildings. However, datamining consists in discovering patterns and trends that go
beyond simple analysis, and finding ‘‘hidden’’ correlations among different attributes and
targets in large databanks. In the field of seismic vulnerability assessment, it consists in
establishing correlations using mathematical algorithms (if/then statements) between
basic attributes that are easily available (e.g., number of stories or roof shape) and the
vulnerability classes.
In this study, we applied a popular method, called association rule learning (ARL;
Agrawal et al. 1993), relevant to seismic vulnerability application (Riedel et al.
2014, 2015). Applied to the CBD, conditional probabilities between basic structural

123
 Nat Hazards

Fig. 4 Probability of exceeding damage P(Dk) for each class of vulnerability computed for macro-seismic
intensities V–XII (according to Eq. 3 and Lagomarsino and Giovinazzi 2006)

information (attribute X) and EMS-98 vulnerability classes (target Y = A, B, C, D, E) are

derived to give the Constantine vulnerability proxy (CVP). Association rules also take
the form X ? Yi, where X (consequent) and Yi (antecedent) are two sets of independent
items. Each relationship between X and Yi can be represented in binary format [0,1]:
Knowing the building attributes X, the probability of belonging to class Yi is expressed by
PðYi \ X Þ
PðYi jX Þ ¼ ð4Þ
Pð X Þ
or in practice, P(Yi|X) can be calculated as:
NXY
PðYi jX Þ ¼ ð5Þ
NX
where Nx is the total number of buildings with attribute X and Nxy the number of buildings
with attribute X and belonging to class Yi. One limitation of the ARL method is that by
searching massive numbers of possible associations, there is a significant risk that the
results will include inconsistencies, due to false associations. We used two phases applied
to the CBD in order to test the efficiency of the CVP.

3.2.1 First phase: learning

Once the databank was ready, a learning phase was applied to a subset of data. The size of
the learning subset was chosen according to the results obtained by Riedel et al. (2015).
They found that the quality of an estimate reaches an asymptote beyond a size of learning
subset representing 30% of the total data, and we assumed for this study the same size of
subset. We therefore selected 2500 sets of data randomly, each representing 30% of the
whole databank. Classification accuracy is sensitive to the dataset; so many combinations

123
Nat Hazards

Fig. 5 Accuracy of the vulnerability classification considering 2500 random subsets of 30% of the
buildings in the Constantine Building Databank for several attribute combinations: a construction period and
number of stories; b construction period, number of stories and material; c construction period, number of
stories and roof shape; d construction period, number of stories, material, and roof shape

were then tested considering one or several of the basic attributes (i.e., period of con-
struction, number of stories, material and roof). Classification accuracy is shown in Fig. 5
as the percentage of correctly classified classes of vulnerability for a given combination of
attributes.
By applying ARL, we observed that the classification (i.e., assessment of vulnerability
classes) is quite relevant even when only basic information is considered. Firstly, for all
cases, variability of the accuracy distribution is less than 1%, reflecting the independence
of subset selection for the classification (r B 0.61%). Secondly, mean accuracy is over
than 73% for two single attributes (period of construction and number of stories), reaching
about 83% for combinations including material. This attribute is considered to be a key
parameter, having significant weight in the vulnerability assessment. However, as reported
by Riedel et al. (2015), period of construction and material are two dependent attributes
(e.g., 98% of buildings built before 1920 were unreinforced masonry constructions, and
after 1962 all were RC), inferring that the benefit in terms of accuracy of considering
material is rather limited. This is certainly the most difficult attribute to assess accurately
and a balance between cost and accuracy of the inventory by visual screening and quality
of the classification must be evaluated before starting a survey. We also observed that by
adding roof shape, classification is slightly improved, suggesting correlation of this attri-
bute with the others.

123
 Nat Hazards

Table 4 Conditional probability

Attributes P(A) P(B) P(C) P(D) P(E)
for each EMS-98 vulnerability
class according to building attri-
bute (period of construction, ] \ 1837]—LR 0.827 0.173 0 0 0
number of stories) obtained using ] \ 1837]—MR 0.833 0.167 0 0 0
the ARL method ] \ 1837]—HR / / / / /
]1837–1920]—LR 0.158 0.710 0.053 0 0.079
]1837–1920]—MR 0.238 0.720 0.042 0 0
]1837–1920]—HR 0.200 0.400 0.400 0 0
]1920–1962]—LR 0.098 0.727 0.168 0 0.007
]1920–1962]—MR 0.103 0.603 0.294 0 0
]1920–1962]—HR 0.158 0.052 0.790 0 0
]1962–1981]—LR 0 0.181 0.455 0 0.364
]1962–1981]—MR 0 0 1.000 0 0
]1962–1981]—HR 0 0 1.000 0 0
]1981–2003]—LR 0 0 0 1.000 0
]1981–2003]—MR 0 0 0.250 0.667 0.083
]1981–2003]—HR 0 0 0 1.000 0
] [ 2003[– LR 0 0 0 0 1.000
] [ 2003[–MR 0 0 0.050 0 0.950
] [ 2003[– HR 0 0 0 0 1.000
/ mean no data

3.2.2 Second phase: validation on the rest of the Constantine Building Databank

After completion of the learning phase, the vulnerability proxy (CVP) was defined for all
combinations and vulnerability classes. Table 4 shows the conditional values (i.e., CVP)
of classification in the EMS98 vulnerability classes, knowing the two most basic building
attributes (i.e., period of construction and number of stories). For example, a randomly
selected building in Constantine known to have been built before 1837 and with less than
2 floors has a probability of 82.7% of being in Class A and 17.3% of being in Class B.
This proxy was then applied to the rest of the CBD, i.e., 70% of the databank, con-
sidering several attribute combinations and vulnerability classes. The buildings were then
grouped into subsets or, in our case, into geographical units. The vulnerability within each
unit was then expressed as the probability of being in class j, as follows:
X
N
Nji PðYjXi Þ
Pj ðY Þ ¼ ð6Þ
1
N

with Pj(Y) the probability of one building being in class Yi = {A, B, C, D, E}, Nji being the
number of buildings with attributes Xi in class Yj, P(Y|Xi) the proxy value in Table 4 and
N the number of buildings. Table 5 shows an example of a confusion matrix that compares
the predicted vulnerability with the ground truth for three attributes (period of construction,
number of stories, roof shape) and five classes. The values on the diagonal are the buildings
that were assigned correctly.
In this example, overall accuracy of construction assignment is 74.24%. Accuracy was
lower for classes A and B: 261 class A buildings were correctly classified but 191 and 6

123
Nat Hazards

Table 5 Example of a confusion matrix obtained with the ARL method to classify the buildings in Con-
stantine into EMS98 seismic vulnerability classes based on three attributes
EMS-98 class Vulnerability (ARL classification)

A B C D E Accuracy (%)

Vulnerability (ground truth)

A 261 191 6 0 0 56.99
B 49 706 10 1 1 92.05
C 3 130 121 1 2 47.08
D 0 0 1 22 0 95.65
E 0 7 2 2 60 84.51
Accuracy 83.39% 68.28% 86.43% 84.62% 95.24% 74.24

Bold values correspond to the perfect assessment of vulnerability

Fig. 6 Accuracy of the vulnerability classification considering 2500 random subsets of 30% of the
buildings in the Constantine Building Databank, merging classes A and B, and for two attribute
combinations: a construction period, number of stories and roof shape; b construction period, number of
stories, material, and roof shape

buildings were incorrectly classified in B and C; 706 class B buildings were correctly
classified but 49 and 10 were misclassified in A and C, respectively. As observed by Riedel
et al. (2014), distinguishing between classes A and B is difficult because of the equivalent
vulnerability associated with the different types of buildings, according to EMS98. Most of
the misclassified class A buildings are actually in B, and we can improve classification
accuracy by merging these two classes. For classes C, D and E, the accuracy of the
classification is better, with 86, 85 and 95% of well-classified buildings. Figure 6 shows
the overall accuracy of the classification considering four classes, i.e., after merging A and
B. Considering 3 attributes (period of construction, number of stories, roof shape), accu-
racy increases to 89 and to 99% if the material attribute is also included, with very slight
variability (0.13%).
In the rest of the paper, we used the CVP proxy given in Table 4 requiring only two
attributes. The purpose is to extend the proxy to other Algerian cities, based on only these
two parameters. The need for only two attributes eliminates one of the main difficulties
related to any vulnerability study, while remaining relevant at the urban scale. Application
of the proxy to other Algerian cities means assuming that the characteristics of the Con-
stantine urbanization are similar in all cities throughout the region: This can be a weak

123
 Nat Hazards

Table 6 Damage probability

Damage grade
matrix for vulnerability class A
interpreted according to EMS98 D0 D1 D2 D3 D4 D5
(after Riedel et al. 2015)
Intensity EMS98
IV 1.00 0.00 0.00 0.00 0.00 0.00
V 0.95 0.05 0.00 0.00 0.00 0.00
VI 0.60 0.35 0.05 0.00 0.00 0.00
VII 0.05 0.20 0.35 0.35 0.05 0.00
VIII 0.00 0.05 0.20 0.35 0.35 0.05
IX 0.00 0.00 0.05 0.25 0.35 0.35
X 0.00 0.00 0.00 0.00 0.20 0.80
XI 0.00 0.00 0.00 0.00 0.00 1.00
XII 0.00 0.00 0.00 0.00 0.00 1.00

assumption at the first order as shown by Riedel et al. (2015). Finally, we compared the
results of the vulnerability assessment by ARL with the mean values of vulnerability given
by Risk-UE. Having attributed the vulnerability classes, damage was computed following
two strategies.
The first strategy, named ARL0 herein, is based on the EMS98 damage scale. For a
given intensity, the number of buildings expected to suffer damage is defined by the terms
‘‘Few,’’ ‘‘Many’’ and ‘‘Most,’’ translated into numerical values 5, 35 and 80%, respectively
(Lagomarsino and Giovinazzi 2006; Bernardini et al. 2010) and finally represented in a
continuous manner by Riedel et al. (2015) to give the damage probability matrix given in
Table 6 for vulnerability class A.
The damage probability for a given intensity PEMS98(Dk) is then computed by the
equation:

1Xi¼E
PEMS98 ðDk Þ ¼ Ni PðDk ji; IEMS98 Þ ð7Þ
N i¼A

where N is the total number of buildings, Ni the number of buildings with vulnerability
class i (i = A, B, C, D, E) and P(Dk|i,IEMS98) the probability of damage grade Dk for a
given vulnerability class i and intensity IEMS98 provided in Table 6.
The second strategy, called ARL1, uses the Risk-UE damage probability model (Eq. 3),
considering the relationship between the EMS98 vulnerability class and the Risk-UE
vulnerability index (Lagomarsino and Giovinazzi 2006; Bernardini et al. 2010), as shown
in Fig. 4.

4 Results

4.1 The vulnerability map of Constantine

Figure 7 shows vulnerability in zones 1, 2 and 3 computed by Risk-UE and based on the
EMS98 classification. Almost 80% of the buildings have a Risk-UE vulnerability index

123
Nat Hazards

Fig. 7 Vulnerability distribution in zones 1, 2 and 3 of Constantine, represented by the EMS98 classes
assigned using the ARL method (upper row) and using the Risk-UE indexes (lower row)

over than 0.70, which is equivalent to vulnerability classes A and B. In comparison, 78% of
the buildings are classified as A and B according to the ARL method, which confirms the
efficiency of the datamining-based method to assess vulnerability at the urban scale with
basic building attributes compared to a more sophisticated method (Risk-UE). We observe
that zone 1, corresponding to the historic center, is the most vulnerable, with classes A and
B. This area was built before 1837 and partially between 1837 and 1920, with 94% of
unreinforced masonry constructions. The rest were built during the French period, where
most of buildings were designed without earthquake engineering. In zone 2, built between
1920 and 1962, the ARL proxy classified the majority of buildings in the northern part of
the zone in A and B, indicating a mix of all classes for the southern area. This is the most
heterogeneous area, which contains buildings of all construction periods. The modern part
of the city corresponds to zone 3, urbanized mainly between 1962 and 1981, composed
only of RC buildings (frame and shear walls) and characterized by the least vulnerable
classes (C and D). Based on the correlation between the Risk-UE indexes and the EMS98
classes, the distributions of the most vulnerable buildings are roughly similar, with a slight

123
 Nat Hazards

Fig. 8 Probability of exceeding damage P(Dk) a for intensities between V and XII computed with the
ARL0, ARL1 and Risk-UE methods and b for intensity VIII and vulnerability classes A–E. e1 is the absolute
error between Risk-UE and ARL0, e2 between ARL1 and Risk-UE and e3 between ARL0 and ARL1

difference in geographic distribution. A building-by-building comparison could be con-

ducted, but in order to be consistent with the statistical approach required for vulnerability
assessment at global scale, the comparison will be based on the probability to exceed
damage per geographical unit.

4.2 Damage assessment

The probability P(Dk) of exceeding damage level Dk was computed according to three
different approaches: the Risk-UE model (Eq. 3), the ARL0 and ARL1 methods, con-
sidering a spatially uniform seismic. For this comparison, only intensity is considered
without accounting for eventually additional effects such as site effects, soil nonlinearity
or triggered effects (e.g., landslides) that might modify the seismic hazard. In order to
check the relevancy of the ARL methods in terms of damage prediction, we computed the
total absolute error e of predicted damage P(Dk) considering all damage grades k and
different macro-seismic intensity scenarios (Fig. 8): e1 between Risk-UE and ARL0, e2
between ARL1 and Risk-UE and e3 between ARL0 and ARL1. Overall, we found
e2 \ e1 \ e3. The differences between Risk-UE and ARL1 (e2) are mainly due to the
seismic vulnerability assessment methods; the differences between ARL0 and ARL1 (e3)
are due to the model for computing damage with the same vulnerability; and the dif-
ferences between Risk-UE and ARL0 (e1) are a combination of the two.
For all intensities (Fig. 8a), the absolute error is very small, with the largest values for
the two extreme intensities equal to 0.10, 0.07, 0.06 and 0.06 for e1, 0.06, 0.04, 0.06 and
0.07 for e3 for intensities V, VI, XI and XII, respectively. The smallest error corresponds to
e2, i.e., the error for the damage model (Risk-UE) but using two different models for
vulnerability assessment. This confirms that for damage prediction, assessing seismic

123
Nat Hazards

Fig. 9 Spatial distribution of damage in Constantine computed for the intensity VIII scenario. Damage
levels are grouped into slight (D0 ? D1), moderate (D2 ? D3) and severe (D4 ? D5) and given as the
number of buildings: a ARL0 method; b ARL1 method; c Risk-UE method

vulnerability using the ARL method provides the same magnitude of damage as Risk-UE,
with differences of less than 0.04. For the highest intensities (XI and XII), we obtained the
same probability of exceedance with both ARL0 and ARL1: For these intensities, the
generalization of damage to the most vulnerable buildings smooths the error related to
damage prediction.
For a given intensity VIII (Fig. 8b), the largest errors were observed for vulnerability
classes A and E, with values equal to 0.05 and 0.07 for e1 and e3. e2 often has the lowest
values (classes B, C and E) and remains very low except for class A. The probabilities P(Dk)
are therefore comparable, regardless of the methods used for damage and vulnerability
assessment. This confirms that with only two attributes, damage predictions are reliable even
if vulnerability may be slightly variable. This remark is important because at the scale of the
city, it means that an individual building inventory is not necessary to collect data on all the
attributes and modifiers required to assess the Risk-UE index. An alternative is to use

123
 Nat Hazards

Table 7 Comparison of the damage distribution (number of buildings and percentage) obtained by ARL
and Risk-UE in Constantine for intensity VIII
D0 ? D1 D2 ? D3 D4 ? D5

Risk-UE 655 29.1% 1008 44.8% 589 26.2%

ARL0 654 29.0% 1288 57.2% 310 13.8%
ARL1 791 35% 1172 52.0% 289 13.0%

Fig. 10 Comparison of the

number of damaged buildings for
intensity VIII computed by Risk-
UE and ARL methods

existing data, for example, from preexisting national databases or collected by remote
sensing for the roof shape and the number of stories, or a combination of both.

4.3 Comparing the seismic damage scenario for Constantine

Figure 9 presents the damage distribution obtained for a given seismic scenario (intensity
VIII) considering the same intensity throughout Constantine. This scenario corresponds to
the last major earthquake that hit the region in 1985 (I = VIII). The three zones are divided
into subzones, defined as being homogenous in terms of urbanization (construction period
and typology). We observed similar results for the three approaches.
The scenario results for zone 1 (i.e., the oldest part of the city) indicate moderate to
severe damage according to the Risk-UE method and moderate damage for both ARL0 and
ARL1 methods. This is mainly due to the poor quality of buildings in this zone, with 94%
of buildings classified as A or B, zone 1 being mainly composed of unreinforced masonry
buildings (95% of the building stock). This area corresponds to a densely urbanized zone,
with residential and commercial buildings. Zones 2 and 3 may suffer slight to moderate
damage, because of the presence of a majority of frame and shear-wall RC buildings
(urbanized between 1920 and 1980).
The damage distribution for Risk-UE and ARL methods is given in Table 7 and shown
in Fig. 10. For an earthquake comparable to the 1985 earthquake (I = VIII), the damage
level computed by Risk-UE shows that nearly 29% of the buildings of the studied area
would be undamaged or only slightly damaged (D0 ? D1), while about 45% of buildings
would suffer moderate damage (D2 ? D3), and more than 25% of buildings would suffer

123
Nat Hazards

severe damage (D4 ? D5). Using ARL, similar results are obtained for slight damage
(29%), and differences are observed for moderate (57%) and severe damage (14%),
resulting from the difficulties encountered sometimes in distinguishing classes A and B.
Nevertheless, in terms of damage prediction for seismic risk management and anticipation,
both results are very similar and allow representation of the seismic risk required to
implement a seismic risk management policy.

5 Conclusions

One of the largest challenges in seismic vulnerability analysis at the urban scale is to
compensate for the lack or poor quality of information concerning construction charac-
teristics, and this is certainly the most costly step of any seismic risk analysis. To overcome
this problem, a recent approach was tested for the city of Constantine, based on the ARL
datamining method. In this manuscript, we have shown the possibility of using simplified
analysis methods, using single building type attributes to represent and analyze the seismic
risk at the urban scale. This will enable more detailed studies of existing buildings and the
assessment of future seismic measures.
One of the most significant characteristics of this method is that it extracts ‘‘hidden’’
relationships between elementary attributes of buildings and seismic vulnerability. A
vulnerability proxy is then derived to attribute the vulnerability class for all combinations
of building attributes. The proxy was derived during a learning phase and then applied to
the rest of the databank of Constantine’s buildings. We observed robust and accurate
assessment of vulnerability, regardless of the building subset used for the learning phase
and compared to the Risk-UE vulnerability assessed in Constantine considered as the
ground truth. The accuracy of the ARL method was evaluated in comparison with the
Risk-UE method, which requires a lot of information on building characteristics. Com-
parison of results showed that the two approaches provide similar results. This suggests
that the ARL methodology was successfully applied to the Constantine data. We
observed that considering the same damage model, vulnerability assessment by ARL
provides the same damage estimate as Risk-UE, even if only two attributes are used. We
confirmed that vulnerability assessment using the datamining approach provides a rel-
evant estimation of seismic damage at a cost far lower than that of conventional methods,
such as Risk-UE. In case of structural modification or retrofitting, ARL-based classifi-
cation might be updated in the same manner as the Risk-UE vulnerability, and the date
and the nature of modification could be considered as an additional attribute for the
classification. Finally, the ARL method was able to give an overall assessment of seismic
risk in an urban area. Assuming similar urbanization features through Algeria, the ARL-
based vulnerability proxy derived for Constantine could be applied to other cities to
enable seismic vulnerability and seismic risk to be assessed at the scale of the country,
using national census data or remote sensing data.

Acknowledgements The MAIF Foundation supported this work. Philippe Guéguen has been supported by a
grant from Labex OSUG@2020 (Investissements d’avenir—ANR10 LABX56).

123
 Nat Hazards

Appendix 1: Building inventory form used in Constantine and screenshot

(in French) of the automatic datasheet used to compute vulnerability
index and mean damage using Risk-UE method

ID: Address of building: Date of inspection:

General information LEGAL STATUS:

Building inspection: □ Outside □Inside □ Outside - Inside
Year of built : □ <1837 □1837-1920 □ 1921-1962 PUBLIC :
□ 1963-1981 □ 1982-2003 □ > 2003
Administrative
Year of seismic codes:□ <1981 :Low □ 1981-2003 Moderate □ >2003 High
commercial
Number of stories : □ 1-2 □3-5 □≥6
equipment
Material : □ Masonry □ Reinforced Concrete □ Steel □ Wood
PRIVATE:
Type of slabs : □ RC slabs □ Wood slabs □steel and masonry slabs
Irregular configuration in plan: □ yes □ No Type : Collective
Vertical irregularities or discontinuities: □ yes □ No Individual
Aggregate effect: building position: □ Middle □ Corner □Header
Aggregate building: elevation: □ Staggered floors □ different height
Number of occupants:
General conditions of the building
State of preservation : □ Good □ Bad □ Very bad
Retrofitting interventions : □ yes □ No □ year of interventions :
Soil morphology: □ Slope □ Cliff

Structural conditions
Structural type : □ Reinf Masonry □ Unreinf Masonr □ RC Moment Frame
□ RC Shear Wal □ RC Dual system □ Precast RC wall
Soft story : □ yes □ No □ Demolition □ transparency
Seismic joint : □ sufficient □ insufficient
Foundations types : □ isolated □ strip footings □ strip footings + beams
foundations at different levels:□ yes □ No
non-structural elements:
Aseismic Devices : □ Barbican □ Foil □ arches □ Buttresses
Bow windows : □ yes □ No

123
Nat Hazards

Appendix 2: On site pictures of inspected buildings in Constantine

M1.1 M1.2 M1.3 M.2

M3.3 M.3.4 M.5 S1

RC.1 RC.2 RC.4 RC.5

References
Agrawal R, Imielinski T, Swami A (1993) Mining association rules between sets of items in large databases.
In: Proceedings of the 1993 ACM SIGMOD international conference on Management of data, SIG-
MOD ’93. doi:10.1145/170035.17007
Aoudia A, Meghraoui M (1995) Seismotectonics in the Tell Atlas of Algeria: the Cavaignac (Abou El
Hassan) earthquake of 25.08. 1922 (Ms = 5.9). Tectonophysics 248(3):263–276
Baba Hamed FZ, Rahal DD, Rahal F (2013) Seismic risk assessment of Algerian buildings in urban area.
J Civ Eng Manag 19(3):348–363
Barbat AH, Carreño ML, Pujades LG, Lantada N, Cardona OD, Marulanda MC (2010) Seismic vulnerability
and risk evaluation methods for urban areas. A review with application to a pilot area. Struct Infrastruct
Eng 6:17–38. doi:10.1080/15732470802663763
Bard P-Y, Duval A-M, Bertrand E, Vassiliadès J-F, Vidal S, Thibault C, Guyet B, Mèneroud J-P, Guéguen
P, Foin P, Dunand F, Bonnefoy-Claudet S, Vettor G (2005) Le risque Sismique à Nice: apport
méthodologique, résultats et perspectives opérationnelles. Rapport final GEMGEP
Benedetti D, Petrini V (1984) Sulla vulnerabilita di edifici in muratura: proposta di un metodo di valu-
tazione. L’industria delle Costruzioni 149:66–74 (in Italian)
Benson C, Twigg J (2004) Measuring mitigation: methodologies for assessing natural hazard risks and the
net benefits of mitigation—a scoping study. In: International Federation of Red Cross and Red
Crescent Societies/the ProVention Consortium
Bernardini A, Lagomarsino S, Mannella A, Martinelli A, Milano L, Parodi S (2010) Forecasting seismic
damage scenarios of residential buildings from rough inventories: a case-study in the Abruzzo Region
(Italy). Proc Inst Mech Eng Part O J Risk and Reliab 224(4):279–296
Boukri M, Farsi MN, Mebarki A, Belazougui M, Amellal O, Mezagzigh B, Guessoum N, Bourenane H,
Benhamiuche A (2014) Seismic risk and damage prediction: case of the buildings in Constantine city
(Algeria). Bull Earthq Eng 12:2683–2704. doi:10.1007/s10518-014-9594-0

123
 Nat Hazards

Bounif A, Haessler H, Meghraoui M (1987) The Constantine (northeast Algeria) earthquake of October 27,
1985: surface ruptures and aftershock study. Earth Planet Sci Lett 85(4):451–460
Buforn E, De Galdeano CS, Udı́as A (1995) Seismotectonics of the Ibero-Maghrebian region. Tectono-
physics 248(3):247–261
Chatelain JL, Tucker B, Guillier B, Kaneko F, Yepes H, Fernandez J, Yamada T (1999) Earthquake risk
management pilot project in Quito, Ecuador. GeoJournal 49(2):185–196
Erdik M, Aydinoglu N, Fahjan Y, Sesetyan K, Demircioglu M, Siyahi B, Yuzugullu O (2003) Earthquake
risk assessment for Istanbul metropolitan area. Earthq Eng Eng Vib 2(1):1–23
Faccioli E, Pessina V, Calvi GM, Borzi B (1999) A study on damage scenarios for residential buildings in
Catania city. J Seismol 3(3):327–343
Geiß C, Taubenböck H, Tyagunov S, Tisch A, Post J, Lakes T (2014) Assessment of seismic building
vulnerability from space. Earthq Spectra 30(4):1553–1583
GNDT (1993) Rischio Sismico di edifici Pubblici-Parte I Aspetti Metodologici. CNR – Gruppo Nazionale
per la Difesa dai Terremoti, Roma, Italy (in Italian)
Grünthal G, Levret A (2001) L’échelle macrosismique européenne, European macroseismic scale
1998(EMS-98), Conseil de l’Europe, Cahiers du Centre Européen de Géodynamique et de Séis-
mologie, vol 19
Guéguen P (ed) (2013) Seismic vulnerability of structures Civil Engineering and geomechanics series. John
wiley and son, Hoboken, 368 pp
Guéguen P, Michel C, LeCorre L (2007) A simplified approach for vulnerability assessment in moderate-to-
low seismic hazard regions: application to Grenoble (France). Bull Earthq Eng 4(3):467–490
Hamdache M, Peláez JA, Talbi A, Mobarki M, Casado CL (2012) Ground-motion hazard values for
Northern Algeria. Pure Appl Geophys 169(4):711–723
HAZUS (1997) Earthquake loss estimation methodology, Hazus technical manuals. National Institute of
Building Science, Federal Emergency Management Agency (FEMA), Washington
Kherroubi A, Déverchère J, Yelles A, De Lépinay BM, Domzig A, Cattaneo A, Graindorge D (2009) Recent
and active deformation pattern off the easternmost Algerian margin, Western Mediterranean Sea: new
evidence for contractional tectonic reactivation. Mar Geol 261(1):17–32
KVERMP (1998) The Kathmandu Valley earthquake management action plan. http://geohaz.org/
downloads/publications/KathmanduValleyEQRiskMgtActionPlan.pdf
Lagomarsino S, Giovinazzi S (2006) Macroseismic and mechanical models for the vulnerability and damage
assessment of current buildings. Bull Earthq Eng 4(4):415–443
Lestuzzi P, Podestà S, Luchini C, Garofano A, Katzantzidou-Firtinidou D, Bozzano C, Bischof P, Haffter A,
Rouiller J-D (2016) Seismic vulnerability assessment at urban scale for two typical Swiss cities using
Risk-UE methodology. Nat Hazards. doi:10.1007/s11069-016-2420-z
McKenzie D (1972) Active tectonics of the Mediterranean region. Geophys J Int 30(2):109–185
Meslem A, Yamazaki F, Maruyama Y, Benouar D, Kibboua A, Mehani Y (2012) The effects of building
characteristics and site conditions on the damage distribution in Boumerdès after the 2003 Algeria
earthquake. Earthq Spectra 28(1):185–216
Mickus K, Jallouli C (1999) Crustal structure beneath the Tell and Atlas Mountains (Algeria and Tunisia)
through the analysis of gravity data. Tectonophysics 314(4):373–385
Milutinovic ZV, Trendafiloski GS (2003) Risk-UE an advanced approach to earthquake risk scenarios with
applications to different European towns, Contract: EVK4-CT-2000-00014, WP4: Vulnerability of
Current Buildings
Mueller M, Segl K, Heiden U, Kaufmann H (2006) Potential of high-resolution satellite data in the context
of vulnerability of buildings. Nat Hazards 38(1–2):247–258
ONS (2008) General census of housing and population, National Statistics Office, Algiers
Ousadou F, Dorbath L, Dorbath C, Bounif MA, Benhallou H (2013) The Constantine (Algeria) seismic
sequence of 27 October 1985: a new rupture model from aftershock relocation, focal mechanisms, and
stress tensors. J Seismol 17(2):207–222
Peláez JA, Hamdache M, Casado CL (2006) Seismic hazard in terms of spectral accelerations and uniform
hazard spectra in northern Algeria. Pure Appl Geophys 163(1):119–135
Riedel I, Gueguen P, Dunand F, Cottaz S (2014) Macroscale vulnerability assessment of cities using
association rule learning. Seismol Res Lett 85(2):295–305
Riedel I, Guéguen P, Dalla Mura M, Pathier E, Leduc T, Chanussot J (2015) Seismic vulnerability
assessment of urban environments in moderate-to-low seismic hazard regions using association rule
learning and support vector machine methods. Nat Hazards 76(2):1111–1141. doi:10.1007/s11069-
014-1538-0
RPA03 (2003) Règles Parasismiques Algériennes/Algerian Earthquake Resistant Regulations RPA99/Ver-
sion 2003, application since 2004, Ministère de l’Habitat et de l’Urbanisme

123
Nat Hazards

RPA81 (1981) Règles Parasismiques Algériennes/Algerian Earthquake Resistant Regulations, Ministère de

l’Habitat et de l’Urbanisme
Smyth AW, Altay G, Deodatis G, Erdik M, Franco G, Gulkan P, Yuzugullu O (2004) Probabilistic benefit-
cost analysis for earthquake damage mitigation: evaluating measures for apartment houses in Turkey.
Earthq Spectra 20(1):171–203
Spence R, Brun BL (2006) Preface. Bull Earthq Eng 4(4):319–321
Tucker BE, Erdik MÖ, Hwang CN (eds) (2013) Issues in urban earthquake risk, vol 271. Springer Science &
Business Media, Berlin
Yelles-Chaouche A, Boudiaf A, Djellit H, Bracene R (2006) La tectonique active de la région nord-
algérienne. Comptes Rendus Géosci 338(1):126–139

123