Slobodan P. Simonovic

Short term streamflow forecasting using artificial neural networks

The research described in this article investigates the utility of Artificial Neural Networks (ANNs) for short term forecasting of streamflow. The work explores the capabilities of ANNs and compares the performance of this tool to conventional approaches used to forecast streamflow. Several issues associated with the use of an ANN are examined including the type of input data and the number, and the size of hidden layer(s) to be included in the network. Perceived strengths of ANNs are the capability for representing complex, non-linear relationships as well as being able to model interaction effects. The application of the ANN approach is to a portion of the Winnipeg River system in Northwest Ontario, Canada. Forecasting was conducted on a catchment area of approximately 20 000xa0km2. using quarter monthly time intervals. The results were most promising. A very close fit was obtained during the calibration (training) phase and the ANNs developed consistently outperformed a conventional model during the verification (testing) phase for all of the four forecast lead-times. The average improvement in the root mean squared error (RMSE) for the 8xa0years of test data varied from 5xa0cms in the four time step ahead forecasts to 12.1xa0cms in the two time step ahead forecasts.

A fuzzy compromise approach to water resource systems planning under uncertainty

Abstract A fuzzy compromise approach to decision analysis is described within the context of water resource systems planning under uncertainty. The approach allows various sources of uncertainty and is intended to provide a flexible form of group decision support. The example compares the ELECTRE method with the fuzzy compromise approach. The comparison is intended to demonstrate the benefits of adopting a multicriteria decision analysis technique which presents subjectivity within its proper context while maintaining an intuitive and transparent technique for ranking alternatives. The fuzzy compromise approach allows a family of possible conditions to be reviewed, and supports group decisions through fuzzy sets designed to reflect collective opinions and conflicting judgements. Ranking of alternatives is accomplished with fuzzy ranking measures designed to illustrate the effect of risk tolerance differences among decision makers. Two distinct ranking measures are used – a centroid measure, and a fuzzy comparison measure based on a fuzzy goal.

One View of the Future

Abstract Floods, droughts, water scarcity, and water contamination are some among many water problems that are present today and will be even more noticeable in the future. In the past, many different tools have been used for simulation and optimization of complex water resources systems in order to provide an improved basis for decision making. The continuing evolution of information technology (hardware and software) creates a good environment for the transition to new tools. Application of the systems approach to water resources planning, management, and operations has been established as one of the most important advances made in the field of water resources engineering. Based on the lessons learned, this contribution provides my personal view on the tools to be used in the future. Two paradigm shifts are discussed. The first one is focusing on the complexity of the water resources domain and the complexity of the modelling tools in an environment characterised by continuous rapid technological development. The second one deals with water-related data availability and natural variability of domain variables in time and space affecting the uncertainty of water resources decision making.

Aggregation operators for soft decision making in water resources

This paper presents a general methodology for numerical evaluation of complex qualitative criteria based on the theory of fuzzy sets. A special emphasis is given to the criteria frequently used in water resources decision making. Water resources’ qualitative criteria are exhibiting a high level of complexity that does not allow for an easy and reliable straightforward evaluation. Due to this complexity, a satisfying evaluation is possible neither on numerical scale nor through a direct construction of suitable fuzzy membership function. The theoretical contribution of presented research consists of the analysis and development of appropriate mathematical techniques for modeling human reasoning. Analyzed techniques include flexible decomposition methodology, construction of fuzzy sets and selection of aggregation operators that can perform justifiable aggregation of fuzzy sets. Methodology presented in this paper provides precise and consistent evaluation tool for many qualitative criteria and therefore enables a successful inclusion of these criteria into qualitative decision making model. A special attention in this paper is given to the aggregation methods. An original aggregation method named polynomial composition under pseudomeasures is developed and presented along with the four well-known aggregation methods that seem to be appropriate for the implementation in water resources decision making. The new method has been developed as a suitable aggregation operator for the case study domain: qualitative evaluation of flood control.

Collaborative planning-support system: an approach for determining evaluation criteria

Abstract Extensive use of computers in water-resources planning makes the more efficient use of available information increasingly possible. It also promotes an iterative planning process by making analysis and evaluation more convenient. The concept of collaborative planning is an idea that has had limited use because of the complexities that prevent people with different backgrounds from communicating. A collaborative planning-support system (CPSS) integrates available computer technologies with modelling and analysis tools in a user-friendly environment, thereby enhancing communication between the proponent for resource development and affected or interested parties. CPSS does not provide solutions but empowers participants by identifying areas of common understanding, encouraging them to explore solutions and reach a consensus. Using the concept of ‘grounded theory’ from social sciences, the CPSS module described in this paper is a tool for developing evaluation criteria. Use of the concept is illustrated by an example from northern Manitoba which focuses on fish habitat issues relating to a hydropower development project.

Application Of Water Resources Systems Concept To The Formulation Of A Water Master Plan

ABSTRACT Some specific aspects of the planning procedure, mainly used for the generation of the water resources master plans, are presented The four step planning procedure presented is strongly oriented toward the use of mathematical models of various complexity. It includes (i) evaluation of the available water resources; (ii) estimation of the water demand; (iii) generation of technical alternatives for satisfying water demands from available water resources; and (iv) ranking of the alternative solutions in accordance with a prespecified set of objectives. Specific planning conditions, mainly valid in developing countries, are discussed and two major conceptual “changes” inside the planning procedure are introduced First, original treatment of the reservoirs as water resources for satisfying demand is presented Knowing the character of different water demands, represented by relative demand coefficients, the implicit stochastic model provides planners with the optimal value of reservoir yield Second, i...

A decision support system for the analysis and use of stage-discharge rating curves

Abstract A decision support system for fitting stage-discharge relations is being developed by the University of Manitoba, Facility for Intelligent Decision Support, for Environment Canadas hydrometric program. The process of developing and applying stage-discharge relationships has been documented, the decision support system framework established, and a number of expert ‘rules’ developed and evaluated for stable and non-stable channels. The system categorizes stage-discharge rating curves as stable if they deviate within a predetermined accuracy (e.g. ± 5% of discharge), or if one of a suite of curves can be applied within the predetermined accuracy specifications for given changes in the energy slope caused by weed growth, channel ice and other conditions affecting backwater. Non-stable channels are defined as channels that experience evolution or abrupt changes in stage-discharge relationships resulting from changes in channel form. Rating curve stability is determined based on deviations in the stage-discharge relationship, utilizing specific gauge, absolute differences between sequential streamflow measurements and an analysis of residuals. Periods of instability, such as a meander cut-off changing the hydraulic control, are often repetitive in hydraulic response, such that a pattern of instability is recognizable as events occur. In addition, periods of instability are interspersed with periods of stability. The repetition in pattern allows knowledge of correctly identified historic events to be applied to contemporary hydraulic conditions. A suite of rating curves can be developed for specific periods (e.g. summer weed growth) and stages. These curves can be automatically applied based on changing streamflow conditions such that streamflow estimates can be generated in a rigorous and accurate manner with minimal hydrographer intervention.

Risk-based parameter selection for short-term reservoir operation

Abstract A methodology has been developed to determine the optimal operating horizon for short-term reservoir operation. The modelling procedure includes: (1) an adaptive forecasting algorithm; (2) a real-time reservoir operation model; (3) a multiobjective compromise programming algorithm. The compromise programming algorithm utilizes a multiobjective compromise between the conflicting objectives of hydrologic forecast reliability and reservoir operation penalties. The algorithm requires predetermined weights defining the relative importance of the two objectives. This paper presents a risk-based methodology developed to help a decision maker in selecting the appropriate weights. Reliability, vulnerability, and resiliency are used as three risk-based criteria for assisting in selection of the weights. The methodology is presented in the form of a rule-based system designed to aid the user in the selection process. The methodology is illustrated through an application of the technique to the operation of Green Reservoir in Kentucky. The reservoir model is implemented for four different historical periods and its performance in terms of total penalties, reliability, vulnerability, and resiliency is presented as a function of the multi-objective weighting parameters. The rule-based expert system is then used for deriving recommendations regarding the selection of appropriate weights. The paper also discusses the rule-based expert system development tool, used in this research.

Sensitivity of reservoir operation performance to climatic change

The potential impacts of changing climatic conditions on the operational performance of water resource systems was investigated in this paper. A multi-site streamflow generation model was used to synthesize potential monthly flow sequences reflecting two different sets of climatic conditions. The generated data were subsequently employed as input to a reservoir operation model that was used to determine the reservoir response to the inflow resulting from the implementation of the reservoir operating policy. The performance of an example reservoir system, the Shellmouth Reservoir located in the Canadian province of Manitoba, was evaluated and compared for the two sets of conditions. The operational performance was evaluated in terms of the reliability of the system for meeting the three purposes of the actual reservoir. The reservoir performance was determined to be sensitive to the inflow data. The results indicate that climatic change has potentially important implications for the operation of the example reservoir system.

Social criteria for evaluation of flood control measures: Winnipeg case study

Abstract Floods affect people. Seldom, if ever, is complete control of floodwaters or prevention of all damages feasible. Making flood management decisions during the planning stage, flood fighting stage and post flood recovery stage, require comprehensive sets of criteria in order to properly account for all flood impacts. In most cases, economic criteria have been used to evaluate all flood impacts. This deficiency is addressed in the paper through the examination of data collected in the Canadian part of Red River Valley (Winnipeg and its surrounding) which has experienced the ‘Flood of the Century’ during April and May 1997. Both, quantitative and qualitative measures of social impacts are recommended for each stage of the flood management process and each type of the flood damage reduction measures to assist at different levels of decision making.