Ioannis Athanasiadis | Γιάννης Αθανασιάδης
Environmental Modelling & Software
Agent-based modelling and simulation in the irrigation management sector: applications and potential
Filed Under (Conference papers) by I N Athanasiadis on 21-12-2006
In Water Saving in Mediterranean Agriculture (WASAMED), (N. Lamaddalena, C. Bogliotti, M.Todorovic and A. Scardigno, ed.), pp. 273-286, Bari, Italy, 2007.
Abstract In the field of sustainable development, the management of common-pool resources is an issue of major importance. Several models that attempt to address the problem can be found in the literature, especially in the case of irrigation management. In fact, the latter task represents a great challenge for researchers and decision makers, as it has to cope with various water-related activities and conflicting user perspectives within a specified geographic area. Simulation models, and particularly Agent-Based Modelling and Simulation (ABMS), can facilitate overcoming these limitations: their inherent ability of integrating ecological and socio-economic dimensions, allows their effective use as tools for evaluating the possible effects of different management plans, as well as for communicating with stakeholders. This great potential has already been recognized in the irrigation management sector, where a great number of test cases have already adopted the modelling paradigm of multi-agent simulation. Our current study of agent-based models for irrigation management draws some interesting conclusions, regarding the geographic and representation scale of the reviewed models, as well as the degree of stakeholder involvement in the various development phases. Overall, we argue that ABMS tools have a great potential in representing dynamic processes in integrated assessment tools for irrigation management. Such tools, when effectively capturing social interactions and coupling them with environmental and economical models, can promote active involvement of interested parties and produce sustainable and approvable solutions to irrigation management problems.
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 11-12-2006
In Knowledge-based Systems, 20(4):388-396, 2007.
Abstract Data mining has proven a successful gateway for discovering useful knowledge and for enhancing business intelligence in a range of application fields. Incorporating this knowledge into already deployed applications, though, is highly impractical, since it requires reconfigurable software architectures, as well as human expert consulting. In an attempt to overcome this deficiency, we have developed Agent Academy, an integrated development framework that supports both design and control of multi-agent systems (MAS), as well as `agent training’. We define agent training as the automated incorporation of logic structures generated through data mining into the agents of the system. The increased flexibility and cooperation primitives of MAS, augmented with the training and retraining capabilities of Agent Academy, provide a powerful means for the dynamic exploitation of data mining extracted knowledge. In this paper, we present the methodology and tools for agent retraining. Through experimented results with the Agent Academy platform, we demonstrate how the extracted knowledge can be formulated and how retraining can lead to the improvement – in the long run – of agent intelligence.
Read also:
Filed Under (Book chapters) by I N Athanasiadis on 18-10-2006
In Environmental Modelling, Software and Decision Support: State of the art and new perspective, (A. Jakeman, A. Voinov, A. E. Rizzoli and S. Chen, ed.), pp. 205-228, 2008.
Abstract Over recent years a huge library of data mining algorithms has been developed to tackle a variety of problems in fields such as medical imaging and network traffic analysis. Many of these techniques are far more flexible than more classical modeling approaches and could be usefully applied to data-rich environmental problems. Certain techniques such as Artificial Neural Networks, Clustering, Case-Based Reasoning and more recently Bayesian Decision Networks have found application in environmental modeling while other methods, for example classification and association rule extraction, have not yet been taken up on any wide scale. We propose that these and other data mining techniques could be usefully applied to difficult problems in the field. The paper is a general introduction to Data Mining techniques for Environmental Scientists who may be interested in using them in their applications. So, special work is done on the contributions of DM techniques to environmental applications and on general guidelines of good practice in real world domains. Technical details on the specific DM techniques are not the focus of this paper, but to provide general ideas to a non expert user that reading them can decide which is the proper technique useful to solve his problem and specific references are provided
Read also:
Filed Under (Book chapters) by I N Athanasiadis on 18-10-2006
In Environmental Modelling, Software and Decision Support, (A. Jakeman, A. Voinov, A. E. Rizzoli and S. Chen, ed.), pp. 101-118, 2008.
Abstract In this chapter we investigate the motivation behind the development of modelling frameworks that explicitly target the environmental domain. Despite many commercial and industrial-strength frameworks are available, we claim that there is a definite niche for environmental-specific frameworks. We first introduce a general definition of what is an environmental integrated modelling framework, leading to the outlining of the requirements for a generic software architecture for such frameworks, which identifies the need for a knowledge layer, to support the modelling layer and the experimentation layer, to support the execution of models. The chapter then focuses on the themes of knowledge representation, model management and model execution. We advocate that appropriate knowledge representation and management tools can facilitate model integration and linking. We stress that a model development process adhering to industry standards and good practices, called “model engineering” is to be pursued. Finally, we focus on the requirements of the experimental frame, which can ensure the transparency and traceability of the execution of simulation scenarios and optimisation problems in complex integrated assessment studies.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 18-10-2006
In 9th PREBEM Conference on Business Economics, Management and Organization Science, pp. 1-26, Amersfoort, The Netherlands, 2006.
Abstract In a multi-disciplinary environment a common understanding of concepts and their relationships is needed for successful cooperation between disciplines. To achieve a common understanding between models – that is a model provides inputs to other models in a coherent way – first the modellers should understand and translate the knowledge that they let their models to exchange. The aim of this paper is to illustrate the potential usefulness of knowledge bases and ontologies in making knowledge explicit and re-usable between different models, exchanging data with spatio-temporal, biophysical and economic dimensions. We will present a case study based on the SEAMLESS project, which applies ontologies to a set of economic models, based on different methodologies, e.g. empirical econometric estimation models versus a mechanistic optimization model operating across different scales and one biophysical model, e.g. a dynamic crop growth simulation model. An ontology in computer science is considered as a specification of a conceptualization. After several iterations during our collaborative approach in which a number of scientist participated, a common ontology was developed. Within this common ontology the ontologies of the individual models can be distinguished, just as the links between these ontologies through shared concepts. We thus demonstrated how models can be linked through meaningful inputs and outputs, which are stored as concepts in an ontology. It is concluded that ontologies help to rigorously link models of different structures from different disciplines in a meaningful way, and an ontology can be beneficial in further ensuring that scientific knowledge is salient, legitimate and credible.
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 18-09-2006
In Journal of Environmental Informatics, 9(2):100-107, 2007.
Abstract Operational decision-making in air quality management systems requires intense efforts for assessing monitored data streams on time. In contrary with previous works, that are focus on air quality forecasting, this paper concentrates on near real time air quality assessment. Data uncertainty problems associated with environmental monitoring networks bring forth issues such as measurement validation and estimation of missing or erroneous values, which are critical for taking trustworthy decisions in a timely fashion. A remedy to these problems is proposed through knowledge discovery techniques. By employing classification techniques, an empirical approach is presented for supporting the decision making process involved in an environmental management system that monitors ambient air quality and triggers alerts when incidents occur. Specifically, exhaustive experiments with large, real world datasets have resulted to trustworthy predictive models, capable operational decision-making for measurement validation and estimation of missing or erroneous data. The outstanding performance of the induced predictive models signifies the added value of using data-driven approaches in operational air quality assessment.
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 09-08-2006
In International Journal of Approximate Reasoning, 45(1):152-188, 2007.
Abstract The Fuzzy Lattice Reasoning (FLR) classifier is presented for inducing descriptive, decision-making knowledge (rules) in a mathematical lattice data domain including the Euclidean space. Tunable generalization is possible based on non-linear (sigmoid) positive valuation functions; moreover, the FLR classifier can deal with missing data. Learning is carried out both incrementally and fast by computing disjunctions of join-lattice interval conjunctions, where a join-lattice interval conjunction corresponds to a hyperbox in Euclidean space. Our testbed in this work concerns the problem of estimating ambient ozone concentration from both meteorological and air-pollutant measurements. The results compare favorably with results obtained by C4.5 decision trees, fuzzy-ART as well as backpropagation neural networks. Novelties and advantages of classifier FLR are detailed extensively and in comparison with related work from the literature.
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 08-08-2006
In Simulation: Transactions of The Society for Modeling and Simulation International, 81(3):175-187, 2005.
Abstract The global effort toward sustainable development has initiated a transition in water management. Water utility companies use water-pricing policies as an instrument for controlling residential water demand. To support policy makers in their decisions, the authors have developed DAWN, a hybrid model for evaluating water-pricing policies. DAWN integrates an agent-based social model for the consumer with conventional econometric models and simulates the residential water demand-supply chain, enabling the evaluation of different scenarios for policy making. An agent community is assigned to behave as water consumers, while econometric and social models are incorporated into them for estimating water consumption. DAWN’s main advantage is that it supports social interaction between consumers, through an influence diffusion mechanism, implemented via inter-agent communication. Parameters affecting water consumption and associated with consumers’ social behavior can be simulated with DAWN. Real-world results of DAWN’s application for the evaluation of five waterpricing policies in Thessaloniki, Greece, are presented.
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 08-08-2006
In IEEE Computing in Science and Engineering, 7(1):65-70, 2005.
Abstract Every day, consumers are exposed to advertising campaigns that attempt to influence their decisions and affect their behavior. Word-of-mouth communication-the informal channels of daily interactions among friends, relatives, coworkers, neighbors, and acquaintances-plays a much more significant role in how consumer behavior is shaped, fashion is introduced, and product reputation is built. Macrolevel simulations that include this kind of social parameter are usually limited to generalized, often simplistic assumptions. In an effort to represent the phenomenon in a semantically coherent way and model it more realistically, we developed an influence-diffusion mechanism that follows agent-based social simulation primitives. The model is realized as a multiagent software platform, which we call Dawn (for distributed agents for water simulation).
Read also:
Filed Under (Journal articles) by I N Athanasiadis on 08-08-2006
In Management of Environmental Quality, 15(3):238-249, 2004.
Abstract Fairly rapid environmental changes call for continuous surveillance and on-line decision making. There are two main areas where IT technologies can be valuable. In this paper we present a multi-agent system for monitoring and assessing air-quality attributes, which uses data coming from a meteorological station. A community of software agents is assigned to monitor and validate measurements coming from several sensors, to assess air-quality, and, finally, to fire alarms to appropriate recipients, when needed. Data mining techniques have been used for adding data-driven, customized intelligence into agents. The architecture of the developed system, its domain ontology, and typical agent interactions are presented. Finally, the deployment of a real-world test case is demonstrated.
Read also:
Books edited
Find me elsewhere
