f2
f2
f2
ro
Kristina DUVNJAK
University or Rijeka, Faculty of Tourism and Hospitality Management, Opatija, Croatia
kri.duvnjak@gmail.com
Maja GREGORIĆ
University of Rijeka, Faculty of Tourism and Hospitality Management, Opatija, Croatia
majam@fthm.hr
Mateja GORŠE
University or Rijeka, Faculty of Tourism and Hospitality Management, Opatija, Croatia
mateja3007@gmail.com
Volume 12, Issue 4 / December 2020
Management Research and Practice
Abstract
In mid 20s Carson (1963) raised the question of environmental issues in economics as one that should be discussed by
practitioners and researchers. From that point, the environmental issues from the analysis of exhaustible and productive
resources to its economic role and consequentially its impact, were examined. Environment affects must be considered
as human activity-based processes which repercussions effect economy in general. Thus, the long-term decision-making
processes in economy must take into account future generations as well. Furthermore, tourism as an economic activity is
growing rapidly and one must take into consideration, that it is based on, primarily, natural environment and man-made
resources. Degradation of basic tourism resources can lead to decrease of tourism demand. Therefore, the analysis of
environmental impact on tourism, and vice versa, the impact of tourism on environment is crucial. With the development
of information technology sector, new and innovative methods for analysis and forecasting have emerged such as artificial
intelligence. The main hypothesis of this paper is to research how artificial intelligence can contribute to analysis and
investigating environmental aspect of tourism. Therefore, the paper provides a theoretical overview of possible fields of
mrp.ase.ro artificial intelligence usage in sustainability, in the context of tourism development.
Keywords: artificial intelligence, environment, sustainability, modelling, tourism
1. INTRODUCTION
The increasing number of population, urbanisation and industrialisation, faced by our planet during this century,
have forced society to consider a change for the very conditions essential to life on Earth (Thomson 1997). The
problem of global environmental issues is complex and can be explained by interactions between humans and
environment itself. Information technologies have played an increasing and central role in this interaction with
planning, predicting, supervising and controlling environmental processes at many different scales and within
various time spans (Cortés et al. 2000). Worldwide, organisations, industries, governments but also
researchers have started to take into consideration a more proactive interaction with the environment, by
introducing the environment in all crucial planning and decision-making processes regarding its impact on the
economy. Rapid developments in the information technologies sector in recent decades obtained new and
faster hardware’s that enabled interdisciplinary research links between environmental and computer scientists
possible (Cortés et al. 2000). The impact of information technologies sector in environmental research resulted
in a new discipline, known as Environmental Informatics, that combines research fields such as Artificial
Intelligence (AI), Geographical Information Systems (GIS), Modelling and Simulation, User Interfaces, etc.
(Radermacher et al. 1994). Crucial but difficult task for this area is to serve as a catalyst for the integration of
data, information, and knowledge from various sources in the environmental sector (Avouris and Page 1995).
International business and holiday tourism travel, according to the World Trade Organization (WTO, 2019) has
grown at the rate of 3.9 % and total of 1.4 billion arrivals what presents a major economic, environmental and
social impacts. Except the natural resources, man-made resources such as accommodation, transport facilities,
shops, restaurants and other facilities create physical change and expand economic activities in general that
ISSN
2067- 2462
18
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
consume resources (Koncul 2007). Tourism is the most propulsive economic activity in the world, with the
rough contribution of 10.4% of worldwide income (WTTC 2019). Regarding that tourism is a human based
activity, major issue is the waste that is appearing (Stabler and Goodall 1996) as a consequence. As Cater and
Goodall (1992) emphasized, the concentration of tourism is neglected in certain destinations in a long-term
decision-making process. Its results thereby led to over exploitation of natural resource base and the generation
of non-priced effects, as it is the case of many mass tourism dominating destinations such as Croatia, Greece,
Spain etc. that base on natural environment. Furthermore, the overcrowding and overdevelopment distorts the
destination itself especially in the peak season when visitors outnumber the resident population. The results of
tourism are majorly regarded in numbers but still, are fragile to the environment of the destination. Violation of
natural environment leads to degradation of its basics due to tourism expansion. The fragility of environment
has become an issue of concern and recognized by stakeholders and others involved in tourism (Goodall 1992;
Jenner and Smith 1992). Thus, the need for sustainable, instead of mass tourism, is necessary. This means a
planned balance between need of the customer but primarily, needs of future generations nature wise. Some
authors underline that the issue is the influx of tourists with different life-styles, financially above-average and
non-indigenous services what can consequentially destroy cultures and environment altogether (Pearce 1989).
Most visible changes in tourism, when talking about environment, are in tourism destinations. Issues such as
pollution from transit, waste and mass energy production, arise in the 1990s but were not addressed seriously.
Volume 12, Issue 4 / December 2020
Management Research and Practice
Having in mind that tourism is majorly dependent on environment, interdependence between the two and
accordingly, economic activities and quality of life is crucial. Furthermore, besides environment, tourism also
depends on man-made resources that raise political, social and scientific issues in addition to those that are
directly economic (Koncul 2007).
The goal of the paper is to present how artificial intelligence in general, and artificial neural networks in
particular, are an alternative tool for analysing, modelling and forecasting in planning and a long-term decision-
making processes for environment. Various environmental issues, such as air and water pollution and global
climate changes, have a large and crucial impact on tourism. This raised the question of environmental impact
of tourism, and vice versa, since both have a significant role in the world and local economies. Hence, new and
innovative techniques that combine mathematics and information technologies are being used as a successful
alternative to get more information. This is supported by the fact that even more publications and research
projects are paying attention to this topic.
2. RESEARCH METHODOLOGY
Although this paper is purely theoretical, it raises the question of artificial intelligence usage in environment
issues and its benefits in long-term analysis and forecasting. Therefore, to elaborate the papers issue, an
extensive desk-research of the existing literature was carried out to highlight the impact of artificial intelligence
implementation in environmental issues and its effects on tourism.
In the paper, publications released on use of artificial intelligence in general, and artificial neural networks in
particular, in analysing and forecasting environmental issues that impact tourism, were examined. More
precisely, in the publications which were examined, new and innovative methods and techniques of analysing
and modelling versus the traditional methods were used. The authors investigated approximately hundred
papers from the last four decades. Papers from recent years, that use new and innovative methods for analysis
and forecasting are in minority. This research doesn’t understate previous researches, but emphasizes the
importance of the question how usage of artificial intelligence can contribute to future decision-making
processes in the cooperation of environment and tourism. The authors conducted an extensive desk-research
in scientific important databases WOSS Core Collection, Scopus and Google Scholar. Mentioned papers are
references to obtain the main objectives of this paper. Around hundred papers were found from which, papers
that combine traditional and artificial intelligence models were included in further analysis. There are no
sufficient scientific proof that new and innovative ways, such as artificial neural networks, should be used in
analysis and forecasting of tourism and environmental issues. The dominance of the traditional quantitative
methods compared to the artificial ones is observed.
The magnitude of the research results lies largely in the fact that advanced techniques, are still not used enough
in combining environmental and tourism issues. Obtained paper results can be used as a starting point for
ISSN
2067- 2462
19
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
further research, not just scientific ones but also applicative ones to generate sustainable development of
tourism.
Cortés et al. (2000) emphasized almost two decades ago that an effective protection of the environment is
largely dependent on the quality of the available information used to make an appropriate decision. Computers
have been seen as a centre of contemporary environmental protection as they are capable of solving tasks
such as monitoring, data analysis, communication, information storage and retrieval so, it was a matter of time
when artificial intelligence will be integrated in mentioned tasks. There has been an evident technological shift
in tourism that was coined by realisation that advanced technologies, as Gretzel et al. (2015) stated, can
transform data into enhanced experience and business value-propositions with a clear focus on efficiency,
sustainability and enriched experience in tourism. By properly collecting and analysing big data and by
forecasting them, for which artificial neural networks can be used, the quest experience can be enhanced.
Pioneer in this field are Robertson et al. (1991) that presented Eco-Logic approach to the issue and was
furthered by the work of Zannetti (1994). From that point artificial intelligence has been developed. Usual
artificial intelligence techniques that are applied to environmental issues are divided into three broad categories
Volume 12, Issue 4 / December 2020
Management Research and Practice
as shown in Table 1.
Process Possibilities
• screening data to detect patterns
• identifying potential issues or opportunities
Data Interpretation and
• discovering similarities between current and past situations
Data Mining
• understanding relevant factors and their relationships
techniques
• discovering non-obvious features in the data possibility to learn
new situations
• recognising characteristic symptoms in order to develop and
Problem Diagnosis confirm hypotheses about possible causes used to suggest
techniques strategies for repairing or recovering based on the available
knowledge and/or on past experiences
• evaluating alternatives to explore their possible consequences
Decision Support
• comparing relative costs and benefits recommending
techniques
appropriate action plans
Source: Adopted from cortés et al. (2000)
Advantages of artificial intelligence presented in table 1 made this alternative method become more popular in
scientific researches as they are designed to simulate and forecast specific issues and are recognised as a
beneficial tool in engineering applications (Topçu and Sarıdemir 2008). It is especially a strong tool for data
models with low regression coefficients (Esteban et al. 2009) and for modelling complex operations in many
engineering fields in this case, environment and tourism.
Environmental models can be explained as a simplified view of nature in order to solve scientific or
management issues that include features essential to describe a given environmental issues. As the awareness
of the environment grows, so does environmental modelling. There were numerous methods that derived from
the attempt to model environment from numerical, mathematical, and statistical methods to alternative methods
of a new age such as artificial intelligence. These methods are able to deal with complexity of environment and
provides more flexibility in its modelling. Lek and Guegan (1999) emphasized that with the growing
development of computer-aided analysis that is easily accessible to all researchers, the applications of artificial
neural networks have facilitated itself in environmental modelling. With that in mind, artificial neural networks
ISSN
2067- 2462
20
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
allow environmental researchers to obtain relevant results in solving the issue of variables in environmental
data. The various applications of artificial neural networks in environmental modelling is presented in a paper
by Liu et al. (2010) from modelling effects of climate change on hydrological-ecological environments, air quality
and greenhouse gas emissions to modelling forest ecosystems, vegetation, and soil change projections. All of
the mentioned issues directly affect tourism.
With the development of artificial intelligence, the field has widened its research requirement to other
environmental issues like forestry, horticulture and waste disposal. Thus, began the development of expert
systems for environmental issues in the 80s. Papers by Lapointe et al. (1989), Guariso and Werthner (1994),
Page (1989), Hushon (1987), Sriram and Adey (1986) and Maeda (1985) should be mentioned when discussing
the development of expert systems for environmental issues. With the beginning of the 90s artificial intelligence
enabled the development of Knowledge-Based Systems (KBS) introduced by Aarts (1992), Serra et al. (1993),
Okubo et al. (1994) and Gabaldon et al. (1998). As some names appear multiple times above and throughout
this paper, they can be considered as pioneers of the field. Combining KBS with environmental issues different
derivatives emerged such as Decision Support Systems (DSS) (Bender and Simonovic, 1994) or
Environmental Decision Support Systems (EDSS) (Rizzoli and Young, 1997). However, of the mentioned
models, EDSS is most interesting for this paper. The authors have chosen EDSS as it is an important tool for
reducing risks obtained from the human-environment interaction. On one hand, benefit of using EDSS is that it
Volume 12, Issue 4 / December 2020
Management Research and Practice
takes into consideration the multidisciplinary nature of environmental issues as each module is specialised for
a given topic. These specialised modules may include empirical knowledge about the environment, situational
knowledge about local environmental and their interaction with the global environment, judgemental knowledge
about humans or theoretical knowledge about phenomena taking place in the environment. On the other hand,
the system provides fast solutions despite the complexity of environmental issues. This process consists of
combining physical and biological aspects in relation to socio-economic conditions and applicable legal
frameworks in limited time (Cortés et al. 2000). From the above mentioned, EDSS is an intelligent information
system that helps reduce the time in which decisions are made and improves the consistency and quality of
those decisions (Cortes 2001). The decision-making process in EDDS is shown in Figure 1.
EDSS
To obtain a proper decision that is expected a deviation is required, meaning that awareness of the issue based
on information, experience and knowledge must be present. As shown, systems such as EDSS are an
integration of artificial intelligence techniques, components of geographical information system, statistical or
numerical methods, and environmental ontologies. All of above mentioned makes an adequate base for a
decision-making process with an appropriate modelling tool which can bring together knowledge of different
disciplines and ability to compare them. Furthermore, as Özesmi and Özesmi (2004) accentuated, it helps
simulate different policy options, allowing the stakeholder to identify advantages and disadvantages of possible
decisions.
ISSN
2067- 2462
21
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
As Britton (1982) and Krippendorf (1986) emphasized two decades ago, low-cost mass tourism, creation of
large-scale resorts, frequent travelling and powerful international tour operators were criticized by academics
as exploiting people and destinations. Bramwell and Lane (1993) continued on this issue explaining that the
problems caused by this type of tourism ranges from environmental destruction to serious impacts on society
and traditional cultures, what outweighs tourisms economic benefits. Therefore, since the 1990s major attention
in tourism researches has been put on tourism's negative impact and because of that, its development has
become refocused through the lens of sustainable tourism (Bramwell and Lane 2003). This led to an innovative
collaboration of artificial intelligence and sustainable tourism to reduce negative effects of tourism and to
improve service effectiveness by using destination resources in a more sustainable way (Fuchs et al. 2013).
Taking into consideration economy with the nature of environmental issues, most researchers use cost-benefit
analysis (CBA) as an adequate framework for assessing monetary and non-monetary costs and benefits, long
side large capital outlays, over a long period over which both occur. Another method that has been used is the
planning balance sheet analysis (PBSA), designed in 1950s to overcome the fact that many CBA were not
measured easily in money terms (Koncul 2007). At that time, multi-criteria analysis (MCA) was considered as
the best approach because it used ranks according to criteria as Nijkamp (1975) described. Later, Saaty (1987)
Volume 12, Issue 4 / December 2020
Management Research and Practice
developed, what was widely used, a mathematical approach in decision-making between alternatives called
analytic hierarchy. The mentioned methods and techniques, as it can be seen by the date were, so to speak,
outdated so the search for alternative and innovative methods and techniques was conducted.
Tourism, as it is known, spreads over destinations as the market demands. With that in mind, land usage can
result in complex changes that influence policies, management, economics, culture, human behaviour, and
consequentially, the environment. The knowledge of land scape modelling is therefore crucial in case changes
that can largely impact the environment occur. The simulation of land use/cover changes is important for a
variety of management and planning issues as well as for academic research. Paper by Pijanowski et al. (2002)
illustrated how combining geographic information systems (GIS) and artificial neural networks can aid in
understanding the complexity of land use changing process. In one previous paper Pijanowski et al. (2000)
explained how GIS-based Land Transformation Model (LTM) was developed in order to forecast land use
changes over large regions by configuring a variety of socioeconomic, political and environmental inputs. The
main advantage of LTM is that it can link changes in land use to ecological process models and provide crucial
stakeholders with information’s about the potential effects of this changes on the environment. Lambin (1997)
and later Stephenne and Lambin (2001) defined that land use change modelling can be performed with (1)
empirical models that base on an extrapolation of the change patterns being observed in the past including
limited representation of parameters from which the changes derive and with (2) simulation models that base
on the understanding the processes of change. Geographical forecast of this issue can be accomplished by
models from the first category. As Mas et al. (2004) emphasized several studies have achieved good
forecasting results of acceptable patterns of land scape change with multivariate models that represent the
interactions between environmental variables that are controlling the changes. Spatial models attempt to
identify explicitly the proximate causes of land use change usually using statistical approaches such as
regression or weight of evidence as proven by Soares-Filho et al. (2002), Schneider and Pontius (2001) and
Almeida et al. (2003). It is assumed that the interaction between the changes and the proximate is
unchangeable over the time and therefor, can estimate short-term forecasts due to the complexity of the issue.
Artificial neural networks were more than successful in forest modelling. The importance of forests in
environment is unquestionable, and a specific research was enabled by artificial neural networks. Some cases
from practice such as studies by Guan and Gertner (1991) were carried out on individual tree survival
probabilities, tree mortality (Hasenauer et al. 2001; Castro et al. 2013), tree heights (Diamantopoulou and
Özçelik 2012), and bark volume estimation (Çatal et al. 2018). These studies showed importance in forecasting
variables affecting forest modelling. Such as in the case of the invasion of so-called palm moths or palm weevil
that devastated the Mediterranean costs of Spain, French Riviera and Croatia, some of the world’s most
significant tourism destinations. Deforestation is a global issue and has received a considerable attention in
ISSN
2067- 2462
22
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
recent years especially with eve more fires that are arising due to global warming. Deforestation is a long-term
issue that effects the climate system and life as it is. Unfortunately, despite the importance of deforestation,
there are no accurate statistical data. Therefore, a simple spatial model that enabled forecasting the
geographical location of deforestation using artificial neural networks approach was developed. Furthermore,
this model is important as the land use changes are consequentially a man-made result, taking into
consideration tourism destinations that deforest the land in order to construct concrete beaches as the demand
enlarges. Thus, tourism stakeholders should consider a model that can sufficiently satisfies the environment
as well as tourism needs. However, variables used in its modelling may have some limitations as their
interaction is complicated and usually results in noisy data regarding the complexity of the issue. To avoid non-
linearity and noisy data artificial neural networks must be taken into account as they are able to obtain better
results in this complex interaction as proven by Li and Yeh (2002) and Pijanowski et al. (2002). Planned land
scaping and forest modelling presents a crucial role in restoring tourism attractions in which case artificial neural
networks are most helpful in obtaining adequate results.
As with all of the fields of environmental modelling mentioned in this paper, agricultural modelling is no
Volume 12, Issue 4 / December 2020
Management Research and Practice
exception in selecting an appropriate method or technique to model. Because of its dynamic changes, this field
has its numerous unknown factors and thus is difficult to determine the relationship between inputs and outputs
what prevents currently used methods in agricultural and biological sciences to obtain relevant results.
Therefore, it is difficult to estimate which method is most suitable in any modelling case as there are insufficient
results based on analysis on any given issue. Samborska et al. (2014) explain how the application of artificial
neural networks in the field of biological and agricultural sciences is still very limited, but because of the
opportunities that artificial neural networks offer when dealing with vast amounts of data, it is highly expected
that artificial neural networks will become one of the major research tools in this field and help practitioners find
solutions for i.e. plant production. Artificial intelligence has reached the field of horticulture by combining
horticulture expertise with artificial intelligence making a breakthrough in fresh food production and reducing
resources (Hemming et al., 2019). On one hand, this particular knowledge can be useful for tourism as guests
are even more oriented on fresh ingredients, its origin and is it GMO free. On the other, as Hemming et al.
(2019) continued, resources such as water or fossil fuel are becoming scarce and there is an urgent need for
maximum resources efficiency.
The rapid development of numerical models provides a large number of models to be used in engineering of
environmental issues. Number of methods and techniques that are quite advanced are available and mostly
used in water quality researches. To select a numerical model most suitable for water modelling requires a
specialised and detailed knowledge on the application and limitations of each model. Yet, an emphasis on
algorithmic procedures to solve specific water modelling issues has occurred. Unfortunately, the models that
are usually used are insufficiently user-friendly. Because of its complexity, an increasing demand for artificial
intelligence has been raised to assist in selection and manipulation of mathematical models and variables.
Moreover, the development of numerical modelling systems reinforced the trend of incorporating even more
features based on the advanced computer technology (Chau 2006).
Water quality modelling considers flow and water quality issues for which, numerical models are frequently
used in analysis of the coastal water process. This analysis usually involves empirical experience on coastal
hydraulics and water quality and its affects through some simplifications and modelling techniques based on
the specialist’s experience (Yu and Righetto 2001). However, Martin et al. (1999) stated that the accuracy of
the prediction depends on a great extent to the accuracy of the open boundary conditions, used model
parameters and adopted numerical scheme. Selecting a suitable numerical model to solve a practical water
quality issue is a highly specialised task that requires knowledge on the application and limitation (Chau 2006).
The main goal of integrating coastal engineering with artificial intelligence is to acquire adequate simulation of
models. Artificial neural networks were introduced in water quality modelling because of their ability to deal with
a large quantity of information and to learn complex model functions i.e. training of the network using sets of
ISSN
2067- 2462
23
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
input and output data. The greatest advantage of artificial neural networks over other modelling techniques, as
stated by Chau (2006), is their capability to model complex, non-linear processes without having to assume
the form of the relationship between input and output variables. Because of their capability to deal with uncertain
and complex situations, artificial neural networks have found their path to water quality modelling. Kralisch et
al. (2003) employed this alternative approach for the optimization of watershed management to maintain a
reasonable balance between water quality demand and consequent restrictions for the farming industry.
Regarding the main issue of this paper, this type of modelling is useful to investigate the balance between
water quality demand and tourism destinations that are overcrowded in peak season. Researches on coastal
modelling are still insufficient, unlike researches on limnological systems (Recknagel et al. 1997; Yabunaka et
al. 1997; Karul et al. 2000) or riverine systems (Whitehead et al. 1997; Maier et al. 1998). More attention should
be paid to coastal modelling as it can be proven crucial in tourism modelling. Majority of destinations depend
on their coast so modelling it can enable investigation on main variables in i.e. sustainable solution on coastal
cleanliness. As coastal tourism has a growing trend, water quality modelling should be an issue to investigate.
Moreover, numerous studies have not yet fully addressed the question of artificial neural networks effectiveness
as a forecasting tool. Often the water quality was connected to other environmental variables simultaneously
so the importance of real-time forecasting was diminished. Generally, in water quality modelling the majority of
all possible environmental variables are implemented without a consideration about using only the adequate
Volume 12, Issue 4 / December 2020
Management Research and Practice
ones. One of artificial neural networks advantages is applicable in this case as it has the possibility to be trained
and to choose optimal variables for adequate modelling. Thus, acknowledging the advantages that this
technique offers can prove successful in its application on a certain issue.
6. CONCLUSIONS
Considering all the mentioned above, it can be concluded that environmental issues have become crucial in
economics of tourism. Thus, the emphasise on sustainable development, rationalisation of resources use,
discussion of negative consequence of tourism expansion, the need for adequate decision-making processes
of all stakeholders in future development of tourism has emerged. Some of the main issues in environmental
modelling arise primarily from the complexity of human and environmental relationship factor, secondly high
degree of complication and lastly numerous conditions that can occur. Thus, the issue is dynamic by itself,
involving numerous stakeholders and, consequently, has no right solution. There are some evidences of
deterioration of tourism destinations which has been developed without adequate planning, that led to negative
consequences of tourism on environment. As demonstrated in this paper, artificial intelligence has an important
role in environmental modelling, especially in recent times. Furthermore, their usage can prove to be successful
in modelling complex fields such as environment and tourism. More focus should be given in implementing
artificial intelligence to environment and tourism modelling in order to successfully control the effects of this
relationship to obtain results crucial for present and future generations.
ACKNOWLEDGMENTS
This paper has been financially supported by the University of Rijeka, for the project ZP UNIRI 4/17.
REFERENCES
Aarts, R.J. (1992). Knowledge-based Systems for Bioprocesses. Finland: Technical Research Centre of
Finland.
de Almeida, C.M., Batty, M., Monteiro, A.M.V., Camara, G., Soares-Filho, B.S., Cerqueira, G.C., & Pennachin,
C.L. (2003). Stochastic cellular automata modeling of urban land use dynamics: empirical development
and estimation. Computers, Environment and Urban Systems, 2(5), 481–509.
https://doi.org/10.1016/S0198-9715(02)00042-X.
Avouris, N.M., & Bernd P. (1995). Environmental Informatics: Methodology and Applications of Environmental
Information Processing. Dordrecht: Springer.
ISSN
2067- 2462
24
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
Bender, J.M., & Simonovic, S.P. (1994). Decision support system for long-range stream-flow forecasting.
Journal of Computing in Civil Engineering, 8(1), 20–34. https://doi.org/10.1061/(ASCE)0887-
3801(1994)8:1(20).
Bramwell, B. & Lane B. (2010). Interpretation and sustainable tourism: the potential and the pitfalls. Journal of
Sustainable Tourism, 1(2), 71–80.
Bramwell, B. & Lane B. (2010). Sustainable tourism: An evolving global approach. Journal of Sustainable
Tourism, 1(1),1–5.
Britton, G.S. (1982). The political economy of tourism in the third world. Annals of Tourism Research, 9(3),
331–358. https://doi.org/10.1016/0160-7383(82)90018-4.
Carson, R. (1963). Silent spring. London: Hamish Hamilton.
Çatal, Y., & Saplıoğlu, K. (2018). Comparison of adaptive neuro-fuzzy inference system, artificial neural
networks and non-linear regression for bark volume estimation in brutian pine (Pinus brutia Ten.). Applied
ecology and environmental research, 16(2), 2015–2027. https://doi.org/10.15666/aeer/1602_20152027.
Volume 12, Issue 4 / December 2020
Cater, E., & Goodall, B. (1992). Must tourism destroy its resource base? In A. Mannion & S. Bowley (Ed.),
Management Research and Practice
ISSN
2067- 2462
25
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
Hushon, M.J. (1987). Expert systems for environmental problems. Environmental Science and Technology,
21(9), 838–841.
Jenner, P., & Smith, C. (1992). The tourism industry and the environment. London: Economic intelligence Unit.
Karul, C., Soyupak, S., Çilesiz, A.F., Akbay, N., & Germen, E. (2000). Case studies on the use of neural
networks in eutrophication modelling. Ecological Modelling, 134(2–3), 145–152.
Koncul, N. (2007). Environmental issues and tourism. Economic Thought and Practice, 2, 157–166.
Kralisch, S., Fink, M., Flügel, W.A., & Beckstein, C. (2003). A neural network approach for the optimisation of
watershed management. Environmental Modelling and Software, 18(8-9), 815–823.
Krippendorf, J. (1986). Tourism in the system of industrial society. Annals of Tourism Research, 13(4), 517–
532.
Lambin, F.E. (1997). Modelling and monitoring land-cover change processes in tropical regions. Progress in
Physical Geography, 21, 375–393.
Lapointe, J., Marcos, B., Veillette, M., Laflamme, G., & Dumontier, M. (1989). Bioexpert-an expert system for
Volume 12, Issue 4 / December 2020
Management Research and Practice
wastewater treatment process diagnosis. Computers & Chemical Engineering, 13(6), 619–630.
Lek, S., & Guégan, J.F. (1999). Artificial neural networks as a tool in ecological modelling, an introduction.
Ecological modelling, 120(2-3), 65–73.
Li, X., & Yeh, A.G.O. (2002). Neural-network-based cellular automata for simulating multiple land use changes
using GIS. International Journal of Geographical Information Science, 16(4), 323–343.
Liu, Z., Peng, C., Xiang, W., Tian, D., Deng, X., & Zhao, Z. (2010). Application of artificial neural networks in
global climate change and ecological research: An overview. Chinese science bulletin, 55(34), 3853–3863.
https://doi.org/10.1007/s11434-010-4183-3
Maeda, K., (1985). An intelligent decision support system for activated sludge wastewater treatment systems.
Proceedings of the 4th IAWPRC Workshop Held in Houston and Denver, U.S.A., 27 April – 4 May 1985,
629–632.
Maiera, R.H., Graeme C.D., & Burch, M.D. (1998). Use of artificial neural networks for modelling cyanobacteria
Anabaena spp. in the River Murray. South Australia. Ecological Modelling, 105(2–3), 257–272.
Martin, J.L., McCutcheon, S.C., & Schottman, R.W. (1999). Hydrodynamics and transport for water quality
modeling. Lewis Publishers: Boca Raton.
Mas, J.F., Puig, H., Palacio, J.L., & Sosa-Lopez, A. (2004). Modelling deforestation using GIS and artificial
neural networks. Environmental Modelling & Software, 19(5), 461–471.
Nijkamp, P. (1975). A multi criteria analysis for project evaluation: economic-ecological evaluation of a land
reclamation project. Papers of the Regional Science Association, 35, 87–111.
Oliveira, C.R.V., Soares, C.P.B., Leite, H.G., Lopes de Souza, A., Nogueira, G.S., & Martins, F.B. (2013).
Individual growth model for Eucalyptus stands in Brazil using artificial neural network. ISRN Forestry 2013.
http://downloads.hindawi.com/archive/2013/196832.pdf
Okubo, T., Kubo, K., Hosomi, M., & Murakami, A. (1994). A knowledge-based decision support system for
selecting small- scale wastewater treatment processes. Water Science Technology, 30(2), 175–184.
Özesmi, U., & Özesmi, S.L. (2004). Ecological models based on people’s knowledge: a multi-step fuzzy
cognitive mapping approach. Ecological modelling, 176(1-2), 43–64.
Page, B. (1989). An analysis of environmental expert system applications with special emphasis on Canada
and the Federal Republic of Germany. Hamburg: Fachbereich Informatik.
Pearce, D. (1989). Tourist Development. Harlow: Longman.
ISSN
2067- 2462
26
Duvnjak K., Gregorić M. & Gorše M.
SUSTAINABLE DEVELOPMENT – AN ARTIFICIAL INTELLIGENCE APPROACH
Pijanowski, C.B., Brown, D.G., Shellito, B.A., & Manik, G.A. (2002). Using neural networks and GIS to forecast
land use changes: a land transformation model. Computers, environment and urban systems, 26(6), 553–
575.
Pijanowski, C.B., Gage, S.G., Long, D., & Cooper, W.C. (2000). A land transformation model: integrating policy,
socioeconomics and environmental drivers using a geographic information system. In Harris, L. and J.
Sanderson (Ed.), Landscape ecology: a top down approach. Lewis Publishers: Boca Raton.
Poch, M., Comas, J., Rodríguez-Roda, I., Sànchez-Marrè, M., & Cortés, U. (2002). Ten years of experience in
Designing and Building Real Environmental Decision Support Systems. What have we learnt? International
Congress on Environmental Modelling and Software, 168, 22–33.
Radermacher, F.J., Riekert, W.F., Page, B., & Hilty, L.M. (1994). Trends in environmental information
processing. In Thirteenth World Computer Congress 94, by K. Brunnstein and E. Raubold (Ed.), 2, 597–
604.
Robertson, D., Bundy, A., Muetzelfeldt, R., Haggith, M., & Uschold, M. (1991). Eco-Logic: Logic-based
Approaches to Ecological Models. USA: MIT Press.
Volume 12, Issue 4 / December 2020
Recknagel, F., French, M., Harkonen, P., & Yabunaka, K.I. (1997). Artificial neural network approach for
Management Research and Practice
World Tourism Organization. (2019). International Tourism Highlights. Madrid: UNWTO. doi:
10.18111/9789284421152. Accessed: January 05, 2020.
World Travel and Tourism Council: Travel & Tourism Economic Impact 2019 - March 2019. Accessed March
10, 2020.
Yabunaka, K.I., Hosomi, M., & Murakami, A. (1997). Novel application of a back-propagation artificial neural
network model formulated to predict algal bloom. Water Science and Technology, 36(5), 89–97.
Yu, L., & Righetto, A. M. (2001). Depth-averaged turbulence k–w model and applications. Advances in
Engineering Software, 32(5), 375–394.
Zannetti, P. (1994). Environmental Systems: Computer Techniques in Environmental Studies V. Computational
Mechanics Publications, 2, 205–212.
Volume 12, Issue 4 / December 2020
Management Research and Practice
ISSN
2067- 2462
28