Environmental Decision Support Systems

1

Guest-editorial

Environmental Decision Support Systems U. Cortés and M. Sànchez-Marrè Software Department, Technical University of Catalonia (UPC), Jordi Girona 1-3, E08034 Barcelona, Catalonia, Spain E-mail: {ia,miquel}@lsi.upc.es Keywords: Environmental Science, Environmental Decision Support Systems.

1. Preamble Environmental Studies and Artificial Intelligence are both of strategic interest. Both areas can provide society with nice solutions for many real applications, in order to protect the environment. The encounter between these fields is a new challenge for many researchers of both communities. In the foreword of the Environmental Science and Engineering for the 21st Century report [6], we can read an statement supporting our view: The quality of life in the 21st century will depend in large measure on the generation of new wealth, on safeguarding the health of our planet, and on opportunities for enlightenment and individual development. The environment is a critical element of the knowledge base we need to live in a safe and prosperous world. The artificial intelligence community identified the environmental issues as a very interesting and fruitful source of problems to be approached with the innovative techniques they were developing. It is possible to trace back a continuous application effort of AI technology to the environment since the early 80’s – via expert systems – until today. Researchers from several disciplines have been trying to deploy new technological answers to the environmental issues and it is also the time where society and governments are aware of the needs for these technologies and their benefits. AI Communications 14 (2001) 1–2 ISSN 0921-7126 / $8.00  2001, IOS Press. All rights reserved

2. Binding Environmental Science and Artificial Intelligence 2000 The second workshop on Binding Environmental Science and Artificial Intelligence (BESAI ’2000) was held in Berlin in the frame of ECAI ’2000. The first BESAI workshop was reported in [3]. For this edition, we received 20 papers and after a selection, based on the judgment of three referees, the organizing committee accepted 12 papers from 11 groups widely distributed in Europe. The technical issues addressed by the selected papers for this workshop come from all environmental fields: emergency and disaster management, ecological aspects in fisheries, ozone concentration prediction, landcover and landtype classification, meteorological prediction, wastewater treatment plants and integrated plant protection. This also implied a wide selection of AI tools and techniques as for example: knowledge management, advanced knowledge models and knowledge-based models; description logics; artificial neural networks and derived qualitative rules; dynamic modeling, model-based and temporal reasoning; rough sets; ontologies and AI integrated architectures; statistical clustering and inductive machine learning methods; web-technology and casebased reasoning. 2.1. This issue For this issue, extended versions of 9 of the workshop papers were submitted and passed another review by two different referees. We are presenting the 5 selected papers. Cortés et al. [2] present the under-explored methodologies for knowledge management in Environmental Decision Support Systems. In a related line Hernández and Serrano [4] discuss the use of advanced knowledge models to support environmental emergency management, with application to flood management, in the context of the ARTEMIS European research project. This works relies on the late Prof. Cuena’s work.

2

Guest-editorial

Wotawa and Wotawa [7] introduce a nice way to derive qualitative rules from artificial neural networks, with an application to ozone concentration prediction. Larguoët and Cordier [5] show the improving of landcover classification of a sequence of images using dynamic plot modeling. Comas et al. [1] show the application and evaluation of several inductive machine learning techniques applied to wastewater treatment plant data. This paper is in fact the merge of two papers as suggested during the discussions. 3. Conclusions As environmental research have matured intellectually, their requirements for knowledge across all scientific, engineering, artificial intelligence and mathematics disciplines have increased very rapidly. BESAI ’2000 was, in our opinion, an example of this constant and growing interaction between two very active communities. BESAI ’2000 was a good opportunity to bring together scientists from a broad spectrum applying AI and other techniques, which helped each other to solve problems in a hot and sensible area as Environmental Sciences are. This special issue presents the results of this fruitful collaboration and puts forward the interest of the European artificial intelligence community on the environment. Acknowledgements The co-editors would like to express their thankful feelings to the Program Committee of BESAI ’2000

and the referees for their invaluable help and advice during the reviewing processes. It has been a pleasure to work with them. We acknowledge the support of the European Union project IST-1999-176101. The views in this paper are not necessarily those of the A-TEAM consortium.

References

[1] J. Comas, S. Dzeroski, K. Gibert, I.R.-Roda and M. SànchezMarrè, Knowledge discovery by means of inductive methods in wastewater treatment plant data, AI Communications 14(1) (2001), 45–62, this issue. [2] U. Cortés, M. Sànchez-Marrè, R. Sangüesa, J. Comas, I.R.-Roda, M. Poch and D. Riaño, Knowledge Management in Environmental Decision Support Systems, AI Communications 14(1) (2001), 3–12, this issue. [3] U. Cortés, M. Sànchez-Marrè, I.R.-Roda and D. Riaño, Binding Environmental Sciences and Artificial Intelligence on ECAI ’98, AI Communications 12(4) (1999), 261–266. [4] J.Z. Hernández and J.M. Serrano, Environmental emergency management supported by knowledge modelling techniques, AI Communications 14(1) (2001), 13–22, this issue. [5] C. Largouët and M.-O. Cordier, Improving the landcover classification using domain knowledge, AI Communications 14(1) (2001), 35–43, this issue. [6] Task Force for the Environment, Environmental Science and Engineering for the 21st Century. The role of the National Science Foundation, National Science Foundation, 2000. [7] F. Wotawa and G. Wotawa, Deriving qualitative rules from neural networks – a case study for ozone forecasting, AI Communications 14(1) (2001), 23–33, this issue.