Developing a Model-Based Drinking Water Decision Support System Featuring Remote Sensing and Fast Learning Techniques (original) (raw)
Related papers
Water Science and Technology, 2020
Drinking water treatment plants (DWTPs) face changes in raw water quality, and treatment needs to be adjusted to produce the best water quality at the minimum environmental cost. An environmental decision support system (EDSS) was developed for aiding DWTP operators in choosing the adequate permanganate dosing rate in the pre-oxidation step. To this end, multiple linear regression (MLR) and multi-layer perceptron (MLP) models are compared for choosing the best predictive model. Besides, a case-based reasoning (CBR) model was approached to provide the user with a distribution of solutions given similar operating conditions in the past. The predictive model consisted of an MLP and has been validated against historical data with sufficient good accuracy for the utility needs (R2 = 0.76 and RSE = 0.13 mg·L−1). The integration of the predictive and the CBR models in an EDSS gives the user an augmented decision-making capacity of the process and has great potential for both assisting expe...
Journal of Environmental Protection, 2013
Decision makers involved in prevention of water contamination often lack the technical knowledge of water quality evaluation or the comprehension of complex software for environmental information management required to make effective decisions. Providing information about the environment is not an easy task due to its complex structure, relationships, and dynamic processes. Because environmental models play an important role in environmental decision support systems, the integration of models into user-friendly integrated information systems is a key factor in the support of such users. This paper presents an environmental information system which supports water protection of Coatzacoalcos River in Mexico, having as a main building block water quality assessments supported by mathematical modeling through the two-dimensional Saint Venant and Advection-Diffusion-Reaction equations to calculate the river hydrodynamics and the contaminant transport, respectively. The mathematical modeling solution yields appropriate results representing the river contaminant distribution when compared with field measurements. But the direct use of these models by decision makers is difficult at best, meaning they are not likely to be used in making practical decisions. The system described in this paper integrates these models, and several other tools, into a seamless, user-centered application, improving model usability, initial configuration, and results visualization.
Model-based Decision Support Systems - An Application to Water Treatment
The paper presents some foundations for the application of model- based systems technology within a decision support system for drinking water treatment plants. This system aims at detecting deviations from normal plant operation, identifying their possible causes, and proposing adequate remedial interventions. Its basis is a library of model fragments that represent intended processes, disturbances, and possible interventions. Based on these fragments and the available observations, possible models of the disturbed plant behavior are generated automatically as a solution to the diagnostic task. An extension of such a model by models of interventions such that the result is consistent with remedial goals represents a possible therapy proposal. We discuss in more detail how the model and consistency-based problem solving can be exploited in the basic reasoning steps.
IFIP advances in information and communication technology, 2000
The paper describes a real-time decision support system for monitoring and minimizing exceedences of water quality standards in the San Joachim River Basin, California, USA. The river system supports extensive irrigated agriculture, and there are many stakeowners in its boundaries with often competing interests. Results are presented of particularly interesting case events. Future improvements are suggested.
An Intelligent System for Monitoring and Predicting Water Quality”
Abstract: In this paper we present an intelligent system for monitoring and predicting water quality, whose main aim is to help the authorities in the" decision-making" process in the battle against the pollution of the aquatic environment, which is very vital for the public health and the economy of Northern Greece. Two sensor-telematic networks for collecting water quality measurements in real time (Andromeda, for sea waters, and Interrisk, for surface/fresh waters) were developed and deployed. Sensor readings (water temperature, ...
Identification of water quality changes in a water system - limitations and perspectives
From the abstraction point and the entrance of water in a Water System (WS) till its discharge back to the environment, water passes through a number of treatments and uses that directly affect its quality. The water quality changes several times while the water returning to the environment at a discharge point into the sea, a lake or a river has poorer quality compared to the water entering the system. All the parts of a WS should be integrated into one single model to assess the performance of the overall system for the development of design and control strategies assisting in its sustainable and cost effective management. Available models for the individual components have to be employed in order to develop the integrated tool. Problems that arise from this methodology are the increased data requirements together with incompatibility of state variables, processes and parameters used in different approaches. For improved control and performance of a WS that includes the water trea...
Decision support for water quality management of contaminants of emerging concern
Journal of environmental management, 2017
Water authorities and drinking water companies are challenged with the question if, where and how to abate contaminants of emerging concern in the urban water cycle. The most effective strategy under given conditions is often unclear to these stakeholders as it requires insight into several aspects of the contaminants such as sources, properties, and mitigation options. Furthermore the various parties in the urban water cycle are not always aware of each other's requirements and priorities. Processes to set priorities and come to agreements are lacking, hampering the articulation and implementation of possible solutions. To support decision makers with this task, a decision support system was developed to serve as a point of departure for getting the relevant stakeholders together and finding common ground. The decision support system was iteratively developed in stages. Stakeholders were interviewed and a decision support system prototype developed. Subsequently, this prototype...
Estimation of Water Quality Parameters With Data-Driven Model
Journal - American Water Works Association, 2016
Assessment of surface water quality is important in the management of water resources (Dogan et al. 2009). Water quality in rivers is paramount to the well-being of nature and humans, and surface water quality is usually related to the type of surrounding industries, agriculture, and human activities. Water is withdrawn from the hydrologic cycle to meet various needs and then is returned (Banejad & Olyaie 2011). Given the essential role of rivers to agricultural, industrial, and urban needs, it is necessary to regularly monitor and evaluate water quality in rivers. As rivers pass through different regions, changes in water quality and the level of hydrochemical parameters are observed in these regions. Because of the gradual decline in water quality over time, regulatory bodies in various countries have made decisions to mitigate the damage. Ecologically acceptable water management calls for accurate modeling, forecasting, and analyzing water quality in rivers (Durdu 2010). Numerous models have been developed for management of water quality, such as QUAL2E, Water Quality Analysis Simulation, and the US Army Corps of Engineers' Hydrologic Engineering Center-5Q (Chen et al. 2003). Using these models is time-consuming and expensive; therefore, development of cost-effective models is encouraged. Because of the propensity of varied standards for water quality, different parameters are used as quality indicators. The quantity of ammonia, cadmium, chemical oxygen demand, chlorine, copper, dissolved phosphorus, lead, nitrogen dioxide, suspended solids, total nitrogen, total phosphorus, zinc, sodium, sodium adsorption ratio, sulfate ions, bicarbonate ions, electrical conductivity (EC), total dissolved solids (TDS), and pH is frequently measured at water quality monitoring stations. EC and TDS levels in water are two of the main parameters used to determine quality of drinking and agricultural water because they directly represent the total concentration of salt in water. High EC and TDS values are not desirable in water used for irrigation because salt affects plant growth through osmosis (Phocaides 2000). Advances in data science and data mining methods such as neural networks (NNs), fuzzy inference methods, support vector machines (SVMs), and k-nearest neighbors (k-NN), have made it possible to solve complex problems in high dimensions. The general principle behind these methods lies in exploring hidden relationships in large volumes of data and building models that reflect physical processes governing the system under study. A data-derived model represents a relationship between input variables and output variables. Such a model can be highly accurate because it captures relationships of any kind that are expressed in data, including the underlying physics and chemistry.
Classifier for drinking water quality in real time
2013 International Conference on Computer Applications Technology (ICCAT), 2013
Real time features are critical for automatic assessment of Drinking Water Quality (DWQ). This paper explores the use of real time features to feed machine learning classifiers for DWQ. Two different representative datasets were used from: a) The Provincial Water Quality Monitoring Network from Ontario, Canada and b) National Hydrologic Information System from Central Region of Portugal. The procedure followed in this study was: (1) automatically computing a Water Quality Index to classify the datasets elements in five classes (excellent, good, medium, bad and very bad) using the Kumar method; (2) selecting best performed real time features on results of classified datasets; and (3) exploring machine learning algorithms (e.g. Decision Trees, Artificial Neural Networks and k-Nearest Neighbor) for producing DWQ classifiers. In this work, we perform the classification of two classes (good and medium) out of the five possible categories, due to the absence of vectors in the datasets.