Comparison of artificial intelligence algorithms to estimate sustainability indicators

Abstract The monitoring of sustainability indicators allows behavioural tendencies of a region to be controlled, so that adequate policies could be established in advance for a sustainable development. However, some data could be missed in the monitoring of these indicators, thus making the establishment of sustainability policies difficult. This paper therefore analyses the possibility to forecast the sustainability indicators of a region by using four different artificial intelligent algorithms: linear regression, multilayer perceptron, random forest, and M5P. The study area selected was the Algarve region in Portugal, and 180 monitored indicators were analysed between 2011 and 2017. The results showed that M5P is the most appropriate algorithm to estimate sustainability indicators. M5P was the algorithm obtaining the best estimations in a greater number of indicators. Nevertheless, the results showed that MP5 was not the best option for all indicators, since in some of them, the use of other algorithms obtained better results, thus reflecting the need of an individual previous study of each indicator. With these algorithms, it is possible for public bodies and institutions to evaluate the sustainable development of the region and to have reliable information to take corrective measures when needed, thus contributing to a more sustainable future.

[1]  Other.  Making tourism more sustainable: a guide for policy makers , 2005 .

[2]  Jorge V. Pérez-Rodríguez,et al.  Testing dependence between GDP and tourism's growth rates , 2015 .

[3]  Shuxin Wang,et al.  Impact of tourism activities on glacial changes based on the tourism heat footprint (THF) method , 2019, Journal of Cleaner Production.

[4]  A. D'Amico,et al.  Artificial Neural Networks to assess energy and environmental performance of buildings: An Italian case study , 2019 .

[5]  Christos Vlachokostas,et al.  A methodology to assess the overall environmental pressure attributed to tourism areas: A combined approach for typical all-sized hotels in Chalkidiki, Greece , 2015 .

[6]  Rannveig Ólafsdóttir,et al.  Reviewing integrated sustainability indicators for tourism , 2018 .

[7]  Wei Sun,et al.  River ice breakup timing prediction through stacking multi-type model trees. , 2018, The Science of the total environment.

[8]  S. Chandel,et al.  Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models , 2014 .

[9]  Juan D. Gomez,et al.  Predicting future monthly residential energy consumption using building characteristics and climate data: A statistical learning approach , 2016 .

[10]  Maria J. Figueroa,et al.  Review of urban sustainability indicators assessment – Case study between Asian countries , 2014 .

[11]  Sven Casteleyn,et al.  The Lisbon ranking for smart sustainable cities in Europe , 2019, Sustainable Cities and Society.

[12]  Christos Vlachokostas,et al.  Environmental, social and economic information management for the evaluation of sustainability in urban areas: A system of indicators for Thessaloniki, Greece , 2010 .

[13]  Dirk Van den Poel,et al.  Predicting customer retention and profitability by using random forests and regression forests techniques , 2005, Expert Syst. Appl..

[14]  Fang Wang,et al.  What can the news tell us about the environmental performance of tourist areas? A text mining approach to China’s National 5A Tourist Areas , 2020 .

[15]  B. Lane,et al.  Will sustainable tourism research be sustainable in the future? An opinion piece , 2017 .

[16]  D. Assouline,et al.  Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests , 2018 .

[17]  Lei Lin,et al.  A combined M5P tree and hazard-based duration model for predicting urban freeway traffic accident durations. , 2016, Accident; analysis and prevention.

[18]  Freya Higgins-Desbiolles,et al.  Sustainable tourism: sustaining tourism or something more? , 2017 .

[19]  Viktor Pocajt,et al.  The forecasting of municipal waste generation using artificial neural networks and sustainability indicators , 2012, Sustainability Science.

[20]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[21]  J. A. R. Mendes da Silva,et al.  Sustainability assessment of building rehabilitation actions in old urban centres , 2018 .

[22]  A. S. Raghubanshi,et al.  Urban sustainability indicators: Challenges and opportunities , 2018, Ecological Indicators.

[23]  Thomas Auer,et al.  A pattern recognition approach for modeling the air change rates in naturally ventilated buildings from limited steady-state CFD simulations , 2017 .

[24]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[25]  Gwo-Hshiung Tzeng,et al.  Improving metro–airport connection service for tourism development: Using hybrid MCDM models , 2013 .

[26]  Rajesh Kumar,et al.  Energy analysis of a building using artificial neural network: A review , 2013 .

[27]  Jiaying Lu,et al.  Sustainable tourism research: an analysis of papers published in the Journal of Sustainable Tourism , 2009 .

[28]  S. Dudoit,et al.  Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data , 2002 .

[29]  T. López-Guzmán,et al.  Local gastronomy, culture and tourism sustainable cities: The behavior of the American tourist , 2017 .

[30]  G. Crouch.  Destination Competitiveness: An Analysis of Determinant Attributes , 2011 .

[31]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[32]  Feifei Xu,et al.  Evolutionary analysis of sustainable tourism , 2018 .

[33]  V. Castellani,et al.  Ecological Footprint and Life Cycle Assessment in the sustainability assessment of tourism activities , 2012 .

[34]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[35]  M. Alvarez,et al.  Barriers to stakeholder involvement in the planning of sustainable tourism: the case of the Thrace region in Turkey , 2016 .

[36]  Luís Miguel Nunes,et al.  Exploring the self-assessment of sustainability indicators by different stakeholders , 2014 .

[37]  Tomás B. Ramos,et al.  Development of regional sustainability indicators and the role of academia in this process: the Portuguese practice , 2009 .

[38]  Rodrigo Lozano,et al.  Towards better embedding sustainability into companies’ systems: an analysis of voluntary corporate initiatives , 2012 .

[39]  Mahsa Modiri Gharehveran,et al.  Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm , 2017 .

[40]  Carlos Rubio-Bellido,et al.  Artificial neural networks and linear regression prediction models for social housing allocation: Fuel Poverty Potential Risk Index , 2018, Energy.

[41]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[42]  A. Golbabai,et al.  Radial basis function networks in the numerical solution of linear integro-differential equations , 2007, Appl. Math. Comput..

[43]  Emma Whittlesea,et al.  Towards a low carbon future – the development and application of REAP Tourism, a destination footprint and scenario tool , 2012 .

[44]  Satinder Kumar,et al.  Assessing progress of tourism sustainability: Developing and validating sustainability indicators , 2019, Tourism Management.

[45]  Carlos Rubio-Bellido,et al.  Comparison of linear regression and artificial neural networks models to predict heating and cooling energy demand, energy consumption and CO2 emissions , 2017 .

[46]  Nicolas Moussiopoulos,et al.  Characterisation of sustainability in urban areas: An analysis of assessment tools with emphasis on European cities , 2018, Sustainable Cities and Society.

[47]  Victor Moutinho,et al.  Change in energy-related CO2 (carbon dioxide) emissions in Portuguese tourism: a decomposition analysis from 2000 to 2008 , 2016 .

[48]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[49]  Yan Zhang,et al.  Tourism sustainability in Tibet - forward planning using a systems approach. , 2015 .

[50]  F. Hermans,et al.  Evaluation of stakeholder participation in monitoring regional sustainable development , 2011 .

[51]  Shuh-Gi Chern,et al.  Strategic ecocity development in urban–rural fringes: Analyzing Wulai District , 2015 .

[52]  Luís Miguel Nunes,et al.  Selection of sustainability indicators for planning: combining stakeholders' participation and data reduction techniques , 2015 .

[53]  A. Rylance,et al.  Local Economic Development in Mozambique: An Assessment of the Implementation of Tourism Policy as a Means to Promote Local Economies , 2012 .

[54]  David Bienvenido-Huertas,et al.  Optimizing the evaluation of thermal transmittance with the thermometric method using multilayer perceptrons , 2019, Energy and Buildings.

[55]  Izabela Kapera,et al.  Sustainable tourism development efforts by local governments in Poland , 2018, Sustainable Cities and Society.

[56]  Manuel Duarte Pinheiro,et al.  Selection Process of Sustainable Indicators for the Algarve Region—OBSERVE Project , 2019, Sustainability.

[57]  P. Coelho,et al.  The role of common local indicators in regional sustainability assessment , 2010 .

[58]  Ying Li,et al.  The dynamic analysis and evaluation on tourist ecological footprint of city: Take Shanghai as an instance , 2018 .

[59]  Consulting,et al.  What tourism managers need to know : a practical guide to the development and use of indicators of sustainable tourism , 1996 .

[60]  Juan Antonio Espinosa-Pulido,et al.  Does environmental sustainability contribute to tourism growth? An analysis at the country level , 2019, Journal of Cleaner Production.

[61]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[62]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[63]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[64]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[65]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[66]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[67]  Patrick T.I. Lam,et al.  Is urban development ecologically sustainable? Ecological footprint analysis and prediction based on a modified artificial neural network model: A case study of Tianjin in China , 2019, Journal of Cleaner Production.

[68]  Agatino Rizzo,et al.  Managing the energy transition in a tourism-driven economy: The case of Malta , 2017 .

[69]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[70]  R. Fletcher.  Practical Methods of Optimization , 1988 .