Miquel Sànchez-Marrè

Designing and building real environmental decision support systems

The complexity of environmental problems makes necessary the development and application of new tools capable of processing not only numerical aspects, but also experience from experts and wide public participation, which are all needed in decision-making processes. Environmental decision support systems (EDSSs) are among the most promising approaches to confront this complexity. The fact that different tools (artificial intelligence techniques, statistical/numerical methods, geographical information systems, and environmental ontologies) can be integrated under different architectures confers EDSSs the ability to confront complex problems, and the capability to support learning and decision-making processes. In this paper, we present our experience, obtained over the last 10 years, in designing and building two real EDSSs, one for wastewater plant supervision, and one for the selection of wastewater treatment systems for communities with less than 2000 inhabitants. The flow diagram followed to build the EDSS is presented for each of the systems, together with a discussion of the tasks involved in each step (problem analysis, data collection and knowledge acquisition, model selection, model implementation, and EDSS validation). In addition, the architecture used is presented, showing how the five levels on which it is based (data gathering, diagnosis, decision support, plans, and actions) have been implemented. Finally, we present our opinion on the research issues that need to be addressed in order to improve the ability of EDSSs to cope with complexity in environmental problems (integration of data and knowledge, improvement of knowledge acquisition methods, new protocols to share and reuse knowledge, development of benchmarks, involvement of end-users), thus increasing our understanding of the environment and contributing to the sustainable development of society.  2003 Elsevier Ltd. All rights reserved.

Artificial Intelligence and Environmental Decision Support Systems

An effective protection of our environment is largely dependent on the quality of the available information used to make an appropriate decision. Problems arise when the quantities of available information are huge and nonuniform (i.e., coming from many different disciplines or sources) and their quality could not be stated in advance. Another associated issue is the dynamical nature of the problem. Computers are central in contemporary environmental protection in tasks such as monitoring, data analysis, communication, information storage and retrieval, so it has been natural to try to integrate and enhance all these tasks with Artificial Intelligence knowledge-based techniques. This paper presents an overview of the impact of Artificial Intelligence techniques on the definition and development of Environmental Decision Support Systems (EDSS) during the last fifteen years. The review highlights the desirable features that an EDSS must show. The paper concludes with a selection of successful applications to a wide range of environmental problems.

OntoWEDSS: augmenting environmental decision-support systems with ontologies

Abstract This paper characterizes part of an interdisciplinary research effort on AI techniques applied to environmental decision-support systems. The architectural design of the OntoWEDSS decision-support system for wastewater management is presented. This system augments classic rule-based reasoning and case-based reasoning with a domain ontology, which provides a more flexible management capability to OntoWEDSS. The construction of the decision-support system is based on a specific case study. But the system is also of general interest, given that its ontology-underpinned architecture can be applied to any wastewater treatment plant and, at an appropriate level of abstraction, to other environmental domains. The OntoWEDSS system helps improve the diagnosis of faulty states of a treatment plant, provides support for complex problem-solving and facilitates knowledge modeling and reuse. In particular, the following issues are dealt with: (1) modeling information about wastewater treatment processes, (2) clarifying part of the existing terminological confusion in the domain, (3) incorporating ontology-modeled microbiologic knowledge related to the treatment process into the reasoning process and (4) creating a decision-support system that combines information through a novel integration between knowledge-based systems and ontologies.

A comparative study on the use of similarity measures in case-based reasoning to improve the classification of environmental system situations

The step of identifying to which class of operational situation belongs the current environmental system (ES) situation is a key element to build successful environmental decision support systems (EDSS). This diagnosis phase is especially difficult due to multiple features involved in most environmental systems. It is not an easy task for environmental managers to acquire, to integrate and to understand all the increasing amount of data obtained from an environmental process and to get meaningful knowledge from it. Thus, a deeper classification task in a EDSS needs a full integration of gathered data, including the use of statistics, pattern recognition, clustering techniques, similarity-based reasoning and other advanced information technology techniques. Consequently, it is necessary to use automatic knowledge acquisition and management methods to build consistent and robust decision support systems. Additionally, some environmental problems can only be solved by experts who use their own experience in the resolution of similar situations. This is the reason why many artificial intelligence (AI) techniques have been used in recent past years trying to solve these classification tasks. Integration of AI techniques in EDSS has led to more accurate and reliable EDSS. Case-based reasoning (CBR) is a good technique to solve new problems based on previous experience. Main assumption in CBR relies on the hypothesis that similar problems should have similar solutions. When working with labelled cases, the retrieval step in CBR cycle can be seen as a classification task. The new cases will be labelled (classified) with the label (class) of the most similar case retrieved from the case base. In environmental systems, these classes are operational situations. Thus, similarity measures are key elements in obtaining a reliable classification of new situations. This paper describes a comparative analysis of several commonly used similarity measures, and a study on its performance for classification tasks. In addition, it introduces L’Eixample distance, a new similarity measure for case retrieval. This measure has been tested with good accuracy results, which improve the performance of the classification task. The testing has been done using two environmental data sets and other data sets from the UCI Machine Learning Database Repository.  2003 Elsevier Ltd. All rights reserved.

A knowledge-based approach to the deflocculation problem: integrating on-line, off-line, and heuristic information

A knowledge-based approach for the supervision of the deflocculation problem in activated sludge processes was considered and successfully applied to a full-scale plant. To do that, a methodology that integrates on-line, off-line and heuristic information has been proposed. This methodology consists of three steps: (i). development of a decision tree (which involves knowledge acquisition and representation); (ii). implementation into a rule-based system; and (iii). validation. The set of symptoms most useful in diagnosing the deflocculation problem has been identified, the different branches to diagnose pin-point floc and dispersed growth have been built (using generic and specific knowledge), and all this knowledge has been codified into an object-oriented shell. The results obtained in the application of this knowledge-based approach to the Granollers WWTP (which treats about 130000 inhabitants-equivalents) showed that the system was able to identify correctly the problem with reasonable accuracy. Our positive experience building this system suggests that this approach is a practical and valuable element to include in an intelligent supervisory system combining numerical and reasoning techniques.

An approach for temporal case-based reasoning: episode-based reasoning

In recent years, several researchers have studied the suitability of CBR to cope with dynamic or continuous or temporal domains. In these domains, the current state depends on the past temporal states. This feature really makes difficult to cope with these domains. This means that classical individual case retrieval is not very accurate, as the dynamic domain is structured in a temporally related stream of cases rather than in single cases. The CBR system solutions should also be dynamic and continuous, and temporal dependencies among cases should be taken into account. This paper proposes a new approach and a new framework to develop temporal CBR systems: Episode-Based Reasoning. It is based on the abstraction of temporal sequences of cases, which are named as episodes. Our preliminary evaluation in the wastewater treatment plants domain shows that Episode-Based Reasoning seems to outperform classical CBR systems.

A purely reactive navigation scheme for dynamic environments using Case-Based Reasoning

This paper presents a new sonar based purely reactive navigation technique for mobile platforms. The method relies on Case-Based Reasoning to adapt itself to any robot and environment through learning, both by observation and self experience. Thus, unlike in other reactive techniques, kinematics or dynamics do not need to be explicitly taken into account. Also, learning from different sources allows combination of their advantages into a safe and smooth path to the goal. The method has been succesfully implemented on a Pioneer robot wielding 8 Polaroid sonar sensors.

Learning and adaptation in wastewater treatment plants through case-based reasoning

This paper discusses a case-based reasoning approach to modeling the specific or experiential knowledge coming directly from wastewater treatment plant (WWTP) operation within the overall supervisory task of a plant. A concrete implementation is detailed: case structure, case library organization, retrieving algorithm, matching function, and learning techniques. Starting from some initial cases (learning by observation), the system evolves, adapting its experiential knowledge (learning by own experience) from the actual operation of the WWTP under control. The result is a more accurate supervisory system. Recording previous experiences-cases-in the system helps to solve new similar or related situations in the plant with less effort than other methods that start from scratch to build up new solutions. Moreover, the continuous execution of the system enhances its adaptation to new situations that could appear.

Development of a case-based system for the supervision of an activated sludge process.

The development of a case-based reasoning system for the supervision of an activated sludge process is presented here. The methodology proposed permits the use of past experiences to solve new problems that arise in the process. These experiences are classified as cases or situations. The adaptation of cases and the generation of new cases are used to tune the response of the system and to learn from the new information generated by the process. The case and the case library definition, the initial seed, the search and retrieval process, the adaptation, the action, the evaluation and the learning steps are presented and outlined. The process studied is the wastewater treatment plant of Girona, Spain. Two examples of the response of the system to two different operational situations are presented. The paper also outlines the integration of different fields in a multidisciplinary approach as the most optimal solution to ensure the successful control and supervision of complex processes like the activated sludge process. With this aim the integration of an array of specific supervisory intelligent systems (for the logical analysis and reasoning) and numerical computations for detailed engineering is suggested.

Improving similarity assessment with entropy-based local weighting

This paper enhances and analyses the power of local weighted similarity measures. The paper proposes a new entropy-based local weighting algorithm (EBL) to be used in similarity assessment to improve the performance of the CBR retrieval task. We describe a comparative analysis of the performance of unweighted similarity measures, global weighted similarity measures, and local weighting similarity measures. The testing has been done using several similarity measures, and some data sets from the UCI Machine Learning Data-base Repository and other environmental databases. Main result is that using EBL, and a weight sensitive similarity measure could improve similarity assessment in case retrieval.