Joaquim Comas

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.

Biological nutrient removal in an MBR treating municipal wastewater with special focus on biological phosphorus removal

The performance of an MBR pilot plant for biological nutrient removal was evaluated during 210days of operation. The set point values for the internal recycles were determined in advance with the use of an optimisation spreadsheet based on the ASM2d model to optimise the simultaneous removal of C, N and P. The biological nutrient removal (BNR) efficiencies were high from the start of operation with COD and N removal efficiencies of 92+/-6% and 89+/-7, respectively. During the course of the experiment P removal efficiencies increased and finally a P-removal efficiency of 92% was achieved. The activity of poly-phosphate accumulating organisms (PAOs) and denitrifying poly-phosphate accumulating organisms (DPAOs) increased and the specific phosphate accumulation rates after 150days of operation amounted to 13.6mgPg(-1)VSSh(-1) and 5.6mgPg(-1)VSSh(-1), for PAOs and DPAOs, respectively.

Removal of microbial indicators from municipal wastewater by a membrane bioreactor (MBR).

The impact of removable and irremovable fouling on the retention of viral and bacterial indicators by the submerged microfiltration membrane in an MBR pilot plant was evaluated. Escherichia coli, sulphite-reducing Clostridium spores, somatic coliphages and F-specific RNA bacteriophages were used as indicators. The membrane demonstrated almost complete removal of E. coli and sulphite-reducing Clostridium spores. However, there was no correlation with membrane fouling. The phage removal varied in accordance with the irremovable fouling, rising from 2.6 to 5.6 log(10) units as the irremovable fouling increased (measured by the change in the transmembrane pressure). In contrast, removable fouling did not have any effect on the retention of viruses by the membrane. These results indicate that irremovable membrane fouling may affect the removal efficiency of MBRs and, therefore, their capacity to ensure the required microbiological standards for the permeate achieved.

Risk assessment modelling of microbiology-related solids separation problems in activated sludge systems

This paper proposes a risk assessment model for settling problems of microbiological origin in activated sludge systems (filamentous bulking, foaming and rising sludge). The aim of the model is not to diagnose microbiology-related solids separation problems with absolute certainty but to quantify in dynamic scenarios whether simulated operational procedures and control strategies lead to favourable conditions for them to arise or not. The rationale behind the model (which integrates the mechanisms of standard activated sludge models with empirical knowledge), its implementation in a fuzzy rule-based system and the details of its operation are illustrated in the different sections of the paper. The performance of the risk assessment model is illustrated by evaluating a number of control strategies facing different short-term influent conditions as well as long-term variability using the IWA/COST simulation benchmark. The results demonstrate that some control strategies, although performing better regarding operating costs and effluent quality, induce a higher risk for solids separation problems. In view of these results, it is suggested to integrate empirical knowledge into mechanistic models to increase reliability and to allow assessment of potential side-effects when simulating complex processes.

Towards a model of input–output behaviour of wastewater treatment plants using soft computing techniques

Abstract Wastewater Treatment Plants (WWTPs) control and prediction under a wide range of operating conditions is an important goal in order to avoid breaking of environmental balance, keeping the system in stable operating conditions and suitable decision-making. In this respect, the availability of models characterizing WWTP behaviour as a dynamic system is a necessary first step. However, due to the high complexity of the WWTP processes and the heterogeneity, incompleteness and imprecision of WWTP data, and finding suitable models poses substantial problems. In this work, an approach via soft computing techniques is sought, in particular, by experimenting with fuzzy heterogeneous time-delay neural networks to characterize the time variation of outgoing variables. Experimental results show that these networks are able to characterize WWTP behaviour in a statistically satisfactory sense and also that they perform better than other well-established neural network models.

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.

Scenario analysis for the role of sanitation infrastructures in integrated urban wastewater management

Traditionally, the sanitation infrastructures of most of the Urban Wastewater Systems (UWSs) have been managed individually, without considering the many relationships among the sewer systems, Wastewater Treatment Plants (WWTPs) and receiving waters. The main objective of WWTP management was to comply with the emission limits, without considering the ecological state of the receiving waters. However, the European Union approved the Water Framework Directive (WFD) in 2000 that changes the conventional practice by introducing the integrated approach concept in the hydraulic infrastructure management. The same Directive also promotes the availability and use of decision support tools for water management, specifically where water resources are becoming increasingly scarce. This paper describes the work conducted in the Besos catchment (Catalonia, NE of Spain) in order to deal with this European legislation. A study site was selected to develop an integrated model as a support tool for the UWS management. Specifically, two sewer systems, their WWTPs and a reach of the Congost River (a tributary of the Besos River) have been modelled. The selected software to model flow and water quality were Infoworks CS, GPS-X and Infoworks RS for the sewer systems, WWTPs and stream reach, respectively. Besides these, a specific program was developed to be used as a data transfer interface between software. Once this model integration platform was built, and taking into account the expert knowledge of the managers, several management scenarios were defined including some critical events such as industrial spills, rainfall episodes, inhibition of nitrification, WWTP shutdowns, obstruction of a sewer system conduit and episodes of minimum river flow rates as well as potential control actions such as the implementation of storage tanks or the use of bypasses between sewer systems or WWTPs. All these scenarios were modelled and simulated and the results obtained were then analysed, focusing the attention on the river water quality, with the main objective being to gain relevant knowledge to deal with the tested scenarios.

Automatic control systems for submerged membrane bioreactors: A state-of-the-art review

Membrane bioreactor (MBR) technology has become relatively widespread as an advanced treatment for both industrial and municipal wastewater, especially in areas prone to water scarcity. Although operational cost is a key issue in MBRs, currently only a few crucial papers and inventions aimed to optimise and enhance MBR efficiency have been published. The present review summarises the available solutions in the area of automatic control systems and widely explores the advances in automation and control for MBRs. In this review of state of the art, different control systems are evaluated comparatively, distinguishing between control systems used for the filtration process and those used for the biological process of MBRs and describing the challenge faced by integrated control systems. The existing knowledge is classified according to the manipulated variables, the operational mode (open-loop or closed-loop) and the controlled variables used.

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.

Model development and simulation for predicting risk of foaming in anaerobic digestion systems.

Although there is not a complete agreement on the causes of foaming in anaerobic digestion, experts and operators do have valuable empirical knowledge of key factors. Based on this knowledge, a model for calculating the risk of foaming in anaerobic digestion systems due to microbiological causes has been developed. Organic loading rate, variation in organic loading rate, and the presence of filamentous microorganisms in the activated sludge system, used as a feed source for the digester, have been selected as the inputs of a knowledge-based model designed to provide as output the risk of foaming in an anaerobic digester. The performance of the model is demonstrated by means of a case study using the IWA Benchmark Simulation Model No. 2 as a framework, where risk of foaming is used as a new evaluation criterion. The simulated results of an open-loop configuration and two closed-loop control strategies illustrate the usefulness of this knowledge-based approach as a means of estimating the risk of foaming in anaerobic digestion.