Landslide early warning systems: a perspective from the internet of things

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 13, No. 2, April 2023, pp. 2214~2222
ISSN: 2088-8708, DOI: 10.11591/ijece.v13i2.pp2214-2222  2214
Journal homepage: http://ijece.iaescore.com
Landslide early warning systems: a perspective from the
internet of things
Vladimir Henao-Céspedes1
, Yeison Alberto Garcés-Gómez1
, María Nancy Marín Olaya2
1
Unidad Académica de Formación en Ciencias Naturales y Matemáticas, Universidad Católica de Manizales, Manizales, Colombia
2
Facultad de Ingeniería y Arquitectura, Universidad Católica de Manizales, Manizales, Colombia
Article Info ABSTRACT
Article history:
Received Mei 16, 2022
Revised Sep 15, 2022
Accepted Nov 2, 2022
Populations located in the vicinity of slopes and soils derived from volcanic
ash are constantly at risk due to the possibility of landslides. Such is the case
of the city of Manizales, Colombia, which, due to its geomorphological
characteristics, has experienced a significant number of landslides that have
caused human and economic losses. The Internet of things (IoT) has allowed
important technological advances for monitoring, thanks to the low cost and
wide coverage of IoT-based systems. Slope monitoring and the development
of landslide early warning systems (EWS) have been positively impacted by
IoT developments, which shows a relationship. The objective of this article
is to review, from the scientific production, the relationship between IoT and
EWS. For this purpose, a fragmenting-deriving-combining methodology is
applied to focus on a research trends analysis of the subject, from macro-
areas such as IoT and EWS to micro areas such as EWS by IoT-based
landslides. Finally, the analysis concluded that the conceptual models of IoT
and EWS for landslides have some correspondence in some of their layers.
Keywords:
Early warning system
Internet of things
Landslide
Risk
Scientific production
This is an open access article under the CC BY-SA license.
Corresponding Author:
Vladimir Henao Céspedes
Unidad Académica de Formación en Ciencias Naturales y Matemáticas, Universidad Católica de Manizales
Cra 23 No 60-63, Manizales, Caldas, Colombia
Email: vhenao@ucm.edu.co
1. INTRODUCTION
A mountainous area, with steep slopes, hillsides, in combination with highly permeable soils derived
from volcanic ash, which allow infiltration and accumulation of rainwater [1], are potential landslide-causing
factors [2]. Such is the case of the city of Manizales, in Colombia, located on the Andes Mountain range. In
this city, due to the aforementioned characteristics, 1,141 disastrous events have occurred in the period 1917
to 2007, of which 85% have been landslides, generating 530 deaths, 4,000 victims, 110,000 people affected,
1,500 houses destroyed and 5,000 affected, and economic losses of US$ 5 million [3], and it is as a result of
these events that, since the 1970s, research has been carried out to generate risk management strategies.
The most recent case of large landslides in Manizales was on April 19, 2017, caused by heavy rains,
with rainfall levels exceeding 150 mm in certain areas of the city, specifically in the urban settlement called
Aranjuez, located in the area of one of the large landslides that occurred that day as shown in Figure 1 [4],
rainfall levels were 104 mm [5], [6]. These landslides caused 17 loss of life, 730 homes evacuated, and 259
families left homeless as shown in Figure 2 [7], and a total of 3,126 people were affected [8].
To contribute to the risk management strategies implemented in the city, it is necessary to develop
and implement monitoring technologies based on the internet of things (IoT), which allow the collection of
information in a wide spatial and temporal window, to better understand the dynamics of the slopes that
represent a risk in the city, and to issue early warnings thus forming an early warning system (EWS), which
allows generating warnings or levels of warning of any adverse effects on the safety of the population [9].

Int J Elec & Comp Eng ISSN: 2088-8708 
Landslide early warning systems: a perspective from the internet of things (Vladimir Henao-Céspedes)
2215
Figure 1. Panoramic view of landslides on
Sancancio hill, on April 19, 2017 [4]
Figure 2. Destruction in the Aranjuez neighborhood,
near Sancancio hill [7]
In order for an EWS to operate correctly, it must have a significant amount of accurate information
about the area being monitored. For this, it is necessary to define variables of interest, in the case of the EWS
for landslides these are variables associated with the slope. This allows for defining the type of sensors that
are necessary to perform the monitoring, these sensors must cover the largest possible area, for which IoT
technology is used. The area requirement is possible with IoT thanks mainly to the ease that these systems
offer to be able to take them to areas of difficult access, the low cost of implementation, low power
consumption, and the fact that they are easy to install [10] and the types of network infrastructure used called
low power wide area network (LPWAN). LPWAN technologies are designed for long-range
communications, low power consumption, low cost, and scalability, and allow multiple nodes (measurement
stations with their respective sensors) to communicate the data obtained to a gateway that subsequently
forwards them to cloud storage where they can be managed for further analysis. Regarding the use of IoT in
early warning systems there are authors who have presented reviews on this topic. Pecoraro et al. [11] made a
very complete study on different landslide early warning systems, including some that do not make use of
IoT, in which he presents important data such as inventories on the parameters monitored and instruments
used. On the other hand, Esposito et al. [12] presented a review on the use of IoT in early warning systems
for floods, earthquakes, tsunamis, and landslides. In relation to landslides, the authors present the sensors,
protocols, and techniques used by some early warning systems developed.
This paper aims to present in detail the relationship between the IoT layer model and the EWS layer
model, based on research trends analysis on landslide EWS implemented exclusively with IoT. For the
above, the authors perform an analysis of the research trends on EWS of landslides implemented exclusively
with IoT. Starting from the definition of an object of study and a theoretical framework, related, that allows
defining the information search strategy.
2. METHOD
To analyze the relationship between IoT and EWS, it is necessary to establish a bibliometric
approach to the subject. Bibliometrics allows the application of statistical methods and models to the study of
bibliographic data. It allows, using quantitative methods, to determine the intellectual structure of any
scientific field [13]. In the present study, bibliometric indicators are used to represent bibliographic data such
as a total number of articles, the total number of articles, and a total number of articles [14], this can be used
to measure productivity in the topic of interest and to define the authors who have contributed the most.
For data collection, a fragmenting-deriving-combining (FDC) framework was generated. First, the
facets of the background review were defined, such as the object of study and theoretical framework Table 1.
Subsequently, keywords associated with the established facets are “derived”. Finally, the derived keywords
are “combined”, and the search equations are generated, which can be seen in Table 2. In this review, the
bibliographic data used were obtained from the main collection of Scopus, using the search equations, shown
in Table 2 [15]. Table 2 allows us to visualize the hierarchical levels of the search. First, a macro search is
performed on the topic of the IoT to visualize the dynamics of scientific production and thematic areas. Then
a more particularized search is performed, where the relationship between IoT and mass movements can be
evidenced. Finally, a micro-level search is performed, where only results showing a relationship between
IoT, mass movements, and early warning systems are filtered.

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 2, April 2023: 2214-2222
2216
Table 1. Faces of background screening
Faces Derived keywords
Object of study “Early warning systems”
Theoretical framework “Disaster risk management”, “mass movement” “landslides”
Technology "Internet of things", “Web of things”, “WSN"
Table 2. Search equations
(“Internet of things” OR “Web of things” OR “WSN”)
((“early warning system” OR “EWS” OR “early warning monitoring system “OR “EWMS”) AND (“Internet of things” OR “Web of
things” OR “WSN”))
((“early warning system” OR “EWS” OR “early warning monitoring system “OR “EWMS”) AND (“Internet of things” OR “Web of
things” OR “WSN”) AND (“mass movement" OR “landslide”))
3. RESULTS AND DISCUSSION
The IoT concept was introduced between 2008 and 2009 [16], but the related scientific production,
as can be observed in Figure 3, has been around for years, exactly since 2002, and since 2012 it has presented
an important increase. The scientific production begins in 2002, with the publication: “The internet of things”
by Lee [17] related to radio-frequency identification (RFID)-based techniques for supply chain optimization.
In 2004, Gershenfeld et al. [18] told how the origin of the Internet would lead to things being able to
exchange information with computers, the beginnings of the IoT. That is what is described, today, as having
devices “things” that are connected, sharing, and obtaining information, which is used in research in different
thematic areas.
Concerning the scientific production that relates IoT and EWS, this has emerged since 2006 with a
single article, and again became active in 2011, and has presented a significant increase from 2016 to the
present as shown in Figure 4, presenting 670 articles in that time window (2011 to 2020). The above result
presents a coincidence with the increase in scientific production exclusive to IoT, seen in Figure 3. When the
search includes the topic of mass movements, the scientific production shows a significant reduction,
generating a result of 103 articles in a time window from 2011 to 2020 as shown in Figure 5 with an annual
growth rate of 50.34%. Figure 6 shows the 20 most cited authors, and Table 3 shows the technologies and
contributions made by authors presenting EWS developments.
Figure 3. Annual scientific production in the area of the IoT, period 2002-2020
Figure 4. Annual scientific production in the area of IoT and EWS, period 2011 to 2020

2217
Figure 5. Annual scientific production IoT, EWS, and mass movements
Figure 6. Most global cited documents
In Table 3, it is possible to observe that the most cited authors in the consulted field, propose the
development of EWS systems mostly using long range (LoRa) networks and their respective protocols to
communicate the sensors, which are also mostly a combination of weather sensors and soil sensors. On the
other hand, the emerging use of artificial intelligence (AI) techniques and predictive data analysis models
applied to the data collected by the monitoring systems can be appreciated. The above described leads to
understand that EWS systems involve all the layers of the IoT model proposed by Cisco [19], showing the
relationship between EWS and IoT.
To understand the relationship between an EWS and IoT, it is necessary to understand the functions
that an EWS focused on mass movements (landslides) must fulfill. An EWS must guarantee a timely flow of
information between governmental institutions and the community exposed to risk, to make decisions
focused on risk reduction and provide an effective response. To guarantee the above, an EWS should
consider the following elements: i) risk awareness, ii) close follow-up or monitoring, iii) hazard analysis and
forecasting, iv) communication or broadcasting of alerts and warnings, and v) local capabilities to respond to
the warning received [20].
In addition to the above elements, for the EWS to be reliable, it is necessary, to have i) an
understanding of the sliding process, ii) historical knowledge of triggering factors (e.g., precipitation), iii) an
effective monitoring program, iv) data interpretation, v) decision making, including the possibility of human
intervention, vi) public tolerance to false alarms or fake news, vii) communication system, viii) pre-
established action plans for implementation, and ix) feedback loop and adaptability of the system and to the
“new” knowledge [21].

 ISSN: 2088-8708
2218
Table 3. Top-cited articles presenting EWS developments
Article Technology Results-contributions
Wireless sensor network
for landslide monitoring
in Nusa Tenggara Timur
[22].
Perform Y- and X-axis tilt measurements with an
accelerometer. Implement an ad-hoc network,
connecting several nodes to a gateway and sending
the information to a data center.
With the obtained data they define thresholds of
accelerometer measurements for the X and Y
axes. A threshold from a position of 0.2 g to
0.49 g shows the occurrence of slow ground
motion. A value of 0.5 g shows significant
changes in ground motion and a value of 1 g or
more could cause a disaster. The system is not
yet incorporated to generate early warnings.
A study on the slope
failure monitoring of a
model slope by the
application of a
displacement sensor
[23].
They use several motion sensors deployed in two
test slopes and these are connected as an IoT end
device in a LoRa network to a gateway that
subsequently sends the data to an IoT server.
They develop a slope movement sensor, this
sensor is tested on two slopes of different
heights, and at different heights they generate cut
sections to observe the displacement signals
obtained by the sensors and define the time and
the precursors of slope failure. The system is not
incorporated into an EWS.
IoT-based geotechnical
monitoring of unstable
slopes for landslide early
warning in the
Darjeeling Himalayas
[24].
They make use of a micro-electro-mechanical
system (MEMS) to measure the slope angle, a
volumetric water content sensor embedded 30 cm
in the slope to measure the water content in the
slope. The slope sensor is located inside a box in
the ground, attached to a steel rod from which a
wireless transmission kit is located at the top
outside the slope.
It performs measurements of tilt and water
variations in the slope, during a few rainy
seasons. According to the authors, the slope data
are effective for monitoring slow movements and
predicting failure in advance.
Wireless sensor network
design for landslide
warning system in IoT
architecture [25]
They realize a network of nodes, each node is
composed of 4 sensors of temperature, humidity,
land movement, and soil moisture, and an ATmega
2560 microcontroller. Data communication is done
over a GSM network. The data is received in a
server and a My SQL database.
Analyze graphically the differences in the
measurements obtained over a period of time and
calculate for each parameter the average
difference.
Rainfall-induced
landslide prediction
using machine learning
models: the case of
Ngororero District,
Rwanda [26]
It makes use of predictive models: random forest
and logistic regression. The data used for the
models are rainfall, land cover, soil depth, soil
types, and soil type.
The results provided by the models indicate a
good correlation between 5 days antecedent
precipitation and the occurrence of landslides.
Edge computing and
artificial intelligence for
landslide monitoring
[27]
A network of sensors and multi agent system
(MAS). They measured states of ground
temperature, vibration, rainfall. They implemented
a LoRa network with a weather node and several
ground nodes. The data was sent to Edge AI-IoT
architecture uses Kubernetes and Docker.
They succeed in moving data processing from
the cloud to the edge to optimize bandwidth,
improving latency and obtaining a shorter
reaction time.
Internet of things
geosensor network for
cost-effective landslide
early warning systems
[28]
They designed a system consisting of the following
sensors: horizontal continuous shear monitor,
extensometer, piezometers. The system was
deployed using a LoRa network.
The location of the sensors should be made
according to the expected slip processes. These
low-cost systems work well for large landslides
except for slow processes.
Flexible configuration of
wireless sensor network
for monitoring of
rainfall-induced
landslide [29]
Design a sensor network using ZigBee as
communication protocol. They used temperature
and moisture sensors, and an accelerometer.
Performed an integration of star and tree topology.
The results obtained by the authors show a better
performance of the proposed system as opposed
to the systems that only use star topology or the
star topology.
Design of landslide
monitoring and early
warning system based
on internet of things [30]
They deploy a network of stations with
accelerometers, humidity, and temperature sensors,
which communicate this information through a
General packet radio service (GPRS) network.
According to the authors this design greatly
improves the efficiency of geological disaster
monitoring management and the ability to prevent
and manage.
On the other hand, the EWS must consider the unpredictability of landslides and the rapid change of
the parameters that cause them [31], i.e., must have the capacity to measure and analyze triggering indicators,
to have continuous information on landslide activity and/or the causes that could favor them [32]. A case of
triggering indicators is rainfall data [33], [34]. These data are important to generate precipitation thresholds
that can be associated with slope stability and instability, thus identifying landslide precursor events. The
transition between stability and instability is not easily conceivable, therefore, in some EWS more than two
thresholds are used, thus increasing the number of alert levels concerning exceeding different thresholds.
For the EWS to be able to generate a broad set of data related to the triggering indicators, it is also
important to increase geographic coverage. In that sense, EWS can be classified into Lo-EWS, and Te-EWS.
EWSs dealing with individual landslides at the slope scale can be referred to as local EWSs (Lo-EWSs).

2219
EWSs that operate over large areas on a regional scale are called territorial systems (Te-EWSs). Piciullo
et al. [35] proposes a model of a Te-EWS as shown in Figure 7 for precipitation-induced landslides. This
model complies with the components that an EWS must have risk awareness, monitoring, and warning
services, dissemination and communication, and response capability [36].
Figure 7. Model of an EWS for precipitation-induced landslides adapted from [35]
In Figure 7, it is possible to observe that the EWS model contains an adjustment module, in which
the coverage area is defined, the type of landslide, and the monitoring instruments are established. A
modeling module, where precipitation thresholds are defined, generates a set of data associated with
precipitation and landslides, obtained from the monitoring instruments of the first module. A third warning
module allows the definition of alert levels and danger zones. Finally, a fourth module, which generates the
response strategies, is a social aspect module, which includes communication, education, socialization
strategies, and everything necessary to reduce the risk of loss of life due to landslides, and to avoid the loss or
damage of equipment.
Between the first module of the EWS model proposed in [35] and the first layer of the IoT reference
model as shown in Figure 8, proposed by Cisco [19], it is possible to observe a correspondence. The first
layer of the IoT model is associated with things, which can be equipped with mandatory communication
capabilities and optional detection, actuation, data capture, data storage, and data processing capabilities [37].
This equipment, in the particular case of an EWS and under the model of [35], corresponds to the monitoring
instruments as well as to the monitoring and warning services component indicated in [36].
Figure 8. The 7 levels of IoT, image adapted from [19]
Given the correspondence between IoT and EWS models, an EWS is a basic type of data driven IoT
system used for environmental disaster risk and impact management. Poslad et al. [38] proposed a semantic
type IoT-EWS system, in which they enhance the richness of sensor data with the use of lightweight

 ISSN: 2088-8708
2220
semantics for metadata. On the other hand, Xu et al. [39], propose a hierarchical structure for an EWS as
shown in Figure 9, to calculate the safety factor of a slope from the processing of the information obtained
with a set of sensors.
Figure 9. The hierarchical structure of an EWS developed using IoT, adapted from [39]
The hierarchical structure of Figure 9 starts with an application layer in which intelligent controls
are generated and messages are issued, i.e., the reporting process is performed, so it is similar to the
application layer of the IoT model. Then, there is a cloud computing layer, where data evaluation and
analysis are performed, so it brings together the accumulation (storage) and data abstraction layers of the IoT
model. Following the previous layer is the IoT layer, where a communication protocol and a data acquisition
stage are displayed, as it has a protocol for data transmission, this can be similar to the connectivity layer of
the IoT model. Finally, there is the EWS detection layer, which is similar to the layer of things in the IoT
model of Figure 8 since this is where the sensors and transducers of different physical variables of the slopes
are located.
Finally, considering the above, an interconnection of sensors that records slope and landslide data,
which transmits such data to a risk monitoring center, can be considered an IoT application. This application
allows addressing the three stages, modules, or technical components of an EWS, which will be reflected in
citizen protection against disasters, thus mitigating the loss of lives. In other words, an EWS is a system that
makes use of IoT technologies.
4. CONCLUSION
The main objective of this paper was to provide the reader with a review of the scientific publication
background of the relationship between IoT and EWS focused on landslides. Therefore, some conclusions
were obtained based on the results obtained from the information searches performed. First, while the term
IoT has been around since 2002, it is only, until sometime between 2008 and 2009, that it has been used to
describe the IoT, where it can be thought of as emerging at the technological level, that is, when it begins to
be reflected in various applications in different areas of research. Second, it is possible to visualize that the
relationship reflected in scientific production between IoT and EWS focused on landslides begins in 2011,
with a significant increase in production since 2016. This year, where the increase begins, coincides with the
year in which the scientific production related only to the IoT topic increases. Third, from the review carried
out, it can be concluded that the EWS models proposed by different authors correspond to the setting
modules and the sensing and IoT layers. In other words, a correspondence between both models is observed,
evidencing the relationship between the main topics of this article IoT and EWS focused on landslides.
Finally, IoT applied to the development of EWS focused on landslides would greatly help in the investigation
and understanding of landslide dynamics, achieving a positive impact on risk mitigation in mountainous
cities such as the case of Manizales.

2221
ACKNOWLEDGEMENTS
The authors are grateful to The Universidad Católica de Manizales with the Research Group in
Technological and Environmental Developments GIDTA.
REFERENCES
[1] L. E. Tafur and J. V. E. Varón, “Physical, chemical and mineralogical characterization of soils with protective forestry vocation
Colombian central andean region,” (in Spanish) Revista Facultad Nacional de Agronomía Medellín, vol. 67, no. 2,
pp. 7335–7343, Jul. 2014, doi: 10.15446/rfnam.v67n2.44176.
[2] A. Calabrese et al., “Systems and alerts for civil protection application: Territorial analysis, scenarios elaboration and fields
application through a new technological approach,” in 2014 IEEE International Symposium on Innovations in Intelligent Systems
and Applications (INISTA) Proceedings, Jun. 2014, pp. 406–412. doi: 10.1109/INISTA.2014.6873652.
[3] J. A. P. Gómez, F. M. Fernández, and J. Z. Nájera, “Integrated environmental monitoring system of Caldas-SIMAC,” (in Spanish)
Boletín Ambient. 145, Manizales - Caldas, pp. 3–15, Mar. 2018.
[4] Instituto de Estudios Urbanos-IEU, “Manizales, one more tragedy in Colombia,” (in Spanish), Manizales, 2018.
https://www.institutodeestudiosurbanos.info/manizales-retrato-de-una-tragedia (accessed Sep. 15, 2022).
[5] The Mayor's Office of Manizales, “Studies and designs of risk mitigation works on the hillside of Morro de Sancancio
neighboring the Aranjuez neighborhood in the city of Manizales,” (in Spanish) The Mayor's Office of Manizales, 2018.
[6] J. A. Pachón-G., “Daily rainfall record and 25-day antecedent rainfall indicators,” (in Spanish), Universidad Nacional de
Colombia Corpocaldas Alcaldía de Manizales, 2017. Accessed Sep. 15, 2022. [Online]. Available:
https://idea.manizales.unal.edu.co/publicaciones/reportes_meteorologicos/red_manizales/niveles_de_alerta/reportes2017/Red%20
SAT%20Deslizamientos-Registro%20lluvias%20diarias%20y%20A25%202017.pdf
[7] Miércoles, “Aerial shots of the houses affected by the landslide in Aranjuez,” (in Spanish), La Patria. 2017.
https://www.lapatria.com/manizales/tomas-aereas-de-las-viviendas-afectadas-por-deslizamiento-en-aranjuez-360767 (accessed
Sep. 15, 2022).
[8] Sábado, “Requests from the victims have not been resolved after two years of the Aranjuez tragedy,” (in Spanish), La patria.
Manizales, Apr. 2019. https://archivo.lapatria.com/manizales/peticiones-de-los-damnificados-no-han-sido-resueltas-tras-dos-anos-
de-la-tragedia-de (accessed Sep. 15, 2022).
[9] O. Husaini and M. Ratnasamy, “An early warning system for active landslides,” Quarterly Journal of Engineering Geology and
Hydrogeology, vol. 34, no. 3, pp. 299–305, Aug. 2001, doi: 10.1144/qjegh.34.3.299.
[10] J. Kaur and K. Kaur, “Internet of things: a review on technologies, architecture, challenges, applications, future trends,”
International Journal of Computer Network and Information Security, vol. 9, no. 4, pp. 57–70, Apr. 2017, doi:
10.5815/ijcnis.2017.04.07.
[11] G. Pecoraro, M. Calvello, and L. Piciullo, “Monitoring strategies for local landslide early warning systems,” Landslides, vol. 16,
no. 2, pp. 213–231, Feb. 2019, doi: 10.1007/s10346-018-1068-z.
[12] M. Esposito, L. Palma, A. Belli, L. Sabbatini, and P. Pierleoni, “Recent advances in internet of things solutions for early warning
systems: a review,” Sensors, vol. 22, no. 6, Mar. 2022, doi: 10.3390/s22062124.
[13] P. K. Hota, B. Subramanian, and G. Narayanamurthy, “Mapping the intellectual structure of social entrepreneurship research: a
citation/co-citation analysis,” Journal of Business Ethics, vol. 166, no. 1, pp. 89–114, Sep. 2020, doi: 10.1007/s10551-019-04129-
4.
[14] Y. Ding, R. Rousseau, and D. Wolfram, Measuring scholarly impact, 1st ed. Cham: Springer International Publishing, 2014. doi:
10.1007/978-3-319-10377-8.
[15] V. Henao-Céspedes, G. Y. Florez, and Y. A. Garcés-Gómez, “The internet of things in high andean wetland monitoring, historical
review approach,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 3, pp. 1572–1579, Jun. 2021, doi:
10.11591/eei.v10i3.2653.
[16] D. Evans, “Internet of things. How the next evolution of the internet changes everything,” (in Spanish), CISCO, 2011. Accessed
Sep. 15, 2022. [Online]. Available: https://www.cisco.com/c/dam/en_us/about/ac79/docs/innov/IoT_IBSG_0411FINAL.pdf
[17] I. Lee, “The internet of things (IoT),” Forbes Magazine, vol. 169, no. 6, pp. 76–93, 2017, doi: 10.4018/978-1-5225-2104-4.ch004.
[18] N. Gershenfeld, R. Krikorian, and D. Cohen, “The internet of things,” Scientific American, vol. 291, no. 4, pp. 76–81, Oct. 2004,
doi: 10.1038/scientificamerican1004-76.
[19] CISCO, “Internet of things reference model,” CISCO, pp. 1–12, 2014. Accessed Sep. 15, 2022. [Online]. Available:
http://cdn.iotwf.com/resources/71/IoT_Reference_Model_White_Paper_June_4_2014.pdf
[20] OEA, “Manual for the design, installation, operation and maintenance of community systems,” (in Spanish), Organización de los
Estados Americanos Manual para el Diseño e Implementación de un Sistema de Unidad de Desarrollo Sostenible y Medio
Ambiente, 2001. Accessed Sep. 15, 2022. [Online]. Available: http://www.oas.org/dsd/publications/unit/oea91s/manual.pdf
[21] S. Lacasse and F. Nadim, “Landslide risk assessment and mitigation strategy,” Landslides-Disaster Risk Reduction, pp. 31–61,
2014, doi: 10.1201/b15621.
[22] H. Z. Kotta, K. Rantelobo, S. Tena, and G. Klau, “Wireless sensor network for landslide monitoring in Nusa Tenggara Timur,”
Telecommunication Computing Electronics and Control (TELKOMNIKA), vol. 9, no. 1, Apr. 2011, doi:
10.12928/telkomnika.v9i1.640.
[23] S. Park et al., “A study on the slope failure monitoring of a model slope by the application of a displacement sensor,” Journal of
Sensors, pp. 1–9, Dec. 2019, doi: 10.1155/2019/7570517.
[24] M. T. Abraham, N. Satyam, B. Pradhan, and A. M. Alamri, “IoT-based geotechnical monitoring of unstable slopes for landslide
early warning in the darjeeling Himalayas,” Sensors, vol. 20, no. 9, May 2020, doi: 10.3390/s20092611.
[25] A. Sofwan, Sumardi, M. Ridho, A. Goni, and Najib, “Wireless sensor network design for landslide warning system in IoT
architecture,” in 2017 4th International Conference on Information Technology, Computer, and Electrical Engineering
(ICITACEE), Oct. 2017, pp. 280–283. doi: 10.1109/ICITACEE.2017.8257718.
[26] M. Kuradusenge, S. Kumaran, and M. Zennaro, “Rainfall-Induced landslide prediction using machine learning models: the case of
ngororero district, Rwanda,” International Journal of Environmental Research and Public Health, vol. 17, no. 11, Jun. 2020, doi:
10.3390/ijerph17114147.
[27] M. Elmoulat, O. Debauche, S. Mahmoudi, S. A. Mahmoudi, P. Manneback, and F. Lebeau, “Edge computing and artificial
intelligence for landslides monitoring,” Procedia Computer Science, vol. 177, pp. 480–487, 2020, doi:
10.1016/j.procs.2020.10.066.

 ISSN: 2088-8708
2222
[28] M. Gamperl, J. Singer, and K. Thuro, “Internet of things geosensor network for cost-effective landslide early warning systems,”
Sensors, vol. 21, no. 8, Apr. 2021, doi: 10.3390/s21082609.
[29] Q.-A. Gian, D.-T. Tran, D.-C. Nguyen, and T. D. Bui, “Flexible configuration of wireless sensor network for monitoring of
rainfall-induced landslide,” Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), vol. 12, no. 3,
pp. 1030–1036, Dec. 2018, doi: 10.11591/ijeecs.v12.i3.pp1030-1036.
[30] J. Li, C. K. Li, K. Li, and Y. Liu, “Design of landslide monitoring and early warning system based on internet of things,” Applied
Mechanics and Materials, pp. 197–201, Feb. 2014, doi: 10.4028/www.scientific.net/AMM.511-512.197.
[31] M. V. Ramesh, “Design, development, and deployment of a wireless sensor network for detection of landslides,” Ad Hoc
Networks, vol. 13, pp. 2–18, Feb. 2014, doi: 10.1016/j.adhoc.2012.09.002.
[32] L. Zan, G. Latini, E. Piscina, G. Polloni, and P. Baldelli, “Landslides early warning monitoring system,” in IEEE International
Geoscience and Remote Sensing Symposium, 2002, vol. 1, pp. 188–190. doi: 10.1109/IGARSS.2002.1024983.
[33] D. Lagomarsino, S. Segoni, R. Fanti, and F. Catani, “Updating and tuning a regional-scale landslide early warning system,”
Landslides, vol. 10, no. 1, pp. 91–97, Feb. 2013, doi: 10.1007/s10346-012-0376-y.
[34] S. Segoni, L. Piciullo, and S. L. Gariano, “A review of the recent literature on rainfall thresholds for landslide occurrence,”
Landslides, vol. 15, no. 8, pp. 1483–1501, Aug. 2018, doi: 10.1007/s10346-018-0966-4.
[35] L. Piciullo, M. Calvello, and J. M. Cepeda, “Territorial early warning systems for rainfall-induced landslides,” Earth-Science
Reviews, vol. 179, pp. 228–247, Apr. 2018, doi: 10.1016/j.earscirev.2018.02.013.
[36] UNISDR, “Global survey of early warning systems: an assessment of capacities, gaps and opportunities toward building a
comprehensive global early warning system for all natural hazards,” UN International Strategy for Disaster Reduction (UNISDR),
vol. 46, 2006.
[37] ITU-T, “Overview of the Internet of things (ITU-T Y.4000/Y.2060 (06/2012)),” (in Spanish), Unión Internacional de
Telecomunicaciones, pp. 1–20, 2012. http://handle.itu.int/11.1002/1000/11559 (accessed Sep. 15, 2022).
[38] S. Poslad, S. E. Middleton, F. Chaves, R. Tao, O. Necmioglu, and U. Bugel, “A semantic IoT early warning system for natural
environment crisis management,” IEEE Transactions on Emerging Topics in Computing, vol. 3, no. 2, pp. 246–257, Jun. 2015,
doi: 10.1109/TETC.2015.2432742.
[39] D.-S. Xu, L.-J. Dong, L. Borana, and H.-B. Liu, “Early-warning system with quasi-distributed fiber optic sensor networks and
cloud computing for soil slopes,” IEEE Access, vol. 5, pp. 25437–25444, 2017, doi: 10.1109/ACCESS.2017.2771494.
BIOGRAPHIES OF AUTHORS
Vladimir Henao Céspedes received his B.S degree in electronic engineering, his
M.Sc. degree, and his Ph.D. in engineering from Universidad Nacional de Colombia,
Manizales. He currently is an associate professor at the Academic Unit for Training in Natural
Sciences and Mathematics, Universidad Católica de Manizales, Manizales. His research
interests include electromagnetic compatibility, electromagnetic pollution, lightning
discharges, the internet of things, industry 4.0, and remote sensing. He is a member of the
Research Group on Technological and Environmental Development GIDTA. He can be
contacted at vhenao@ucm.edu.co.
Yeison Alberto Garces-Gómez received his bachelor’s degree in Electronic
Engineering, and master’s degrees and Ph.D. in Engineering from Electrical, Electronic and
Computer Engineering Department, Universidad Nacional de Colombia, Manizales, Colombia,
in 2009, 2011 and 2015, respectively. He is a full professor at the Academic Unit for Training
in Natural Sciences and Mathematics, Universidad Católica de Manizales, and teaches several
courses such as Experimental Design, Statistics, Physics. His main research focus is on applied
technologies, embedded systems, power electronics, and power quality, and also many other
areas of electronics, signal processing, and didactics. He published more than 30 scientific and
research publications, among them more than 10 journal papers. He worked as a principal
researcher on commercial projects and projects by the Ministry of Science, Tech and
Innovation, Republic of Colombia. He can be contacted at ygarces@ucm.edu.co.
María Nancy Marín Olaya is a geologist, M.Sc. (Eng.) in physical
instrumentation, M.Sc. (Edu) Education from Diversity, candidate for a Ph.D. competency-
based education. Leader of line risk management research of the Group on Technological and
Environmental Development GIDTA. Director of the master’s degree in global changes and
disaster risk of specialization in prevention, attention, and disaster reduction at the Catholic
University of Manizales. She can be contacted at mnmarin@ucm.edu.co.

Landslide early warning systems: a perspective from the internet of things

More Related Content

Similar to Landslide early warning systems: a perspective from the internet of things (20)

More from IJECEIAES (20)

Recently uploaded (20)

Landslide early warning systems: a perspective from the internet of things