Self-organising map methods in integrated modelling of environmental and economic systems
Introduction
The need for better techniques, tools and practices to analyse ecological and economic systems within an integrated framework at wider scales has never been so great. Many environmentally concerned communities, scientists and international institutions, agree that better modelling techniques and tools are needed for an integrated analysis of human interaction with naturally evolving, highly complex and diverse ecosystems. This will allow humans and their activities to be sustained by natural systems (Graedel et al., 2001). The emphasis is on developing integrated interdisciplinary modelling techniques; an absolute contrast to the late 20th century's in-depth knowledge-based approaches. Many studies detailed in Section 2 reveal this fact. These studies elaborate on the environmental issues critical to human well-being with recommendations and measures for integrated analysis of ecological and economic indicators conducive to advancing co-ordinated efforts from a range of professionals to preserve our global ecosystem from further degradation. However, despite such efforts, policymakers and land developers continue to pay no attention to scientific predictions of the long-term detrimental effects to the environment, and argue about the reliability of current environmental impact assessment methods. This is due to a belief that environment sustainability invariably leads to socio-economic loss (Buckeridge and Tapp, 1999). Meanwhile, ecosystems continue to deteriorate with commensurate biodiversity loss (Reid, 2000). Thus, in practice achieving sustainable environmental management seems remote. The urgent need for new approaches to achieve sustainable environment management, the challenges faced in introducing interdisciplinary research efforts and the drawbacks with the current ecological modelling methods are explained. Thereafter, Kohonen's (1995) self-organising map (SOM) based artificial neural network (ANN) applications to integrated analysis of ecological and economic system data (at regional and global scales) are illustrated with examples.
Section snippets
Need for change
New modelling techniques, radical approaches and better rapport are considered to be of paramount importance for establishing better communication between the three main groups: scientists, policymakers and the general public. Vant, 1999, Reid, 2000, Clark et al., 2001 and Harris (2002), in essence, stressed the fact that better modelling tools with an integrated approach could play a significant role in enhancing a common trust between these different and equally important groups to preserve
SOMs in regional data analysis
The use of SOM methodologies in integrated analysis of regional scale data from the Waikato River water-monitoring programme is discussed in this section. Kohonen's (1995) SOMs are feed forward ANNs with an unsupervised training algorithm. They are used to project multidimensional input data onto low dimensional displays, whereby detection of useful knowledge (in the form of patterns, structures and relationships) within the raw data is enhanced; an approach generally found to be impossible
SOMs in global data analysis
In this section, SOM based integrated data analysis of different countries is illustrated. The main aim of this analysis is to study the effects of urbanisation in biodiversity on a world scale using raw data from the World Bank's statistical tables for the 1980–1990 and 1990–2000 time periods. Data on development related activities (pressure), such as gross domestic product (GDP), agriculture, industry, manufacturing, services and rural development (World Bank Report, 2002) are analysed with
Conclusion
Despite the significant efforts made by many state and international institutions to enforce sustainable environment management based on integrated analysis of ecological and economic systems, the issues remain the same. Policymakers and land developers tend to ignore the long-term human induced environmental effects on natural habitats due to misinterpretations implying that environmental sustainability invariably leads to economic loss. Furthermore, the late 20th century's in-depth,
Acknowledgements
The authors wish to thank the staff of Waikato Regional Council for permission to use their data. The literature review and the second example are excerpts of the main author's thesis submitted for a doctoral degree at the Auckland University of Technology, New Zealand.
References (28)
- et al.
A comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination
Ecological Modelling
(2001) Integrated assessment and modelling: an essential way of doing science
Environmental Modelling and Software
(2002)- et al.
Determination of the relationship between sewage odour and BOD by neural networks
Environmental Modelling & Software
(7 July 2005) - Bowler, P.J., 1992. The Problem of Perception. The Fontana History of the Environmental Sciences. R. Potter. London,...
- Buckeridge, J.S., 1994. Introducing philosophy and ethics to the engineering curriculum. Transactions of the...
- Buckeridge, J.S., Tapp, B.A., 1999. Ethics and that Ethic called Sustainability. Australasian Environmental Engineering...
- Buckeridge, J.S., 2001. Ethics, Environment and Culture: Their Significance within Engineering Education. International...
- et al.
Ecological forecasts: an emerging imperative
Science
(27 July 2001) - et al.
Visual Explorations in Finance with Self-organizing Maps
(1998) Online Manual – Viscovery SOMine ver 4. Austria
Grand Challenges in Environmental Sciences
On Ecological Engineering and Sustainable Development in a Swedish Context
Artificial intelligence and river biomonitoring
Water & Atmosphere
Cited by (39)
Machine learning-based evaluation of dynamic thermal-tempering performance and thermal diversity for 107 Cambridge courtyards
2023, Sustainable Cities and SocietyAnalysing coastal ocean model outputs using competitive-learning pattern recognition techniques
2014, Environmental Modelling and SoftwareCitation Excerpt :Such techniques have an inherent ability to recognise non-linear relationships and are robust in the face of noisy and incomplete data, rendering them very suitable for use within the environmental sciences (Reusch et al., 2005; Haupt et al., 2009; Hsieh, 2009). The most common type of neural network used within the environmental sciences to date has been a classification network called the back-propagation neural network (Wu et al., 2006), but over recent years a competitive-learning network called the Self-Organizing Map (SOM) has begun to generate significant interest (Cavaros, 2000; Tambouratzis and Tambouratzis, 2008; Shanmuganathan et al., 2006; Agarwal and Skupin, 2008; Kalteh et al., 2008; Morioka et al., 2010). SOMs have been applied successfully in coastal oceanography (Richardson et al., 2002, 2003; Demarcq et al., 2008; Jin et al., 2010; Iskandar, 2010) and have been used to analyse numerical ocean circulation model output (Iskandar et al., 2008; Liu et al., 2009).