Backfilling missing microbial concentrations in a riverine database using artificial neural networks

Predicting peak pathogen loadings can provide a basis for watershed and water treatment plant management decisions that can minimize microbial risk to the public from contact or ingestion. Artificial neural network models (ANN) have been successfully applied to the complex problem of predicting peak pathogen loadings in surface waters. However, these data-driven models require substantial, multiparameter databases upon which to train, and missing input values for pathogen indicators must often be estimated. In this study, ANN models were evaluated for backfilling values for individual observations of indicator bacterial concentrations in a river from 44 other related physical, chemical, and bacteriological data contained in a multi-year database. The ANN modeling approach provided slightly superior predictions of actual microbial concentrations when compared to conventional imputation and multiple linear regression models. The ANN model provided excellent classification of 300 randomly selected, individual data observations into two defined ranges for fecal coliform concentrations with 97% overall accuracy. The application of the relative strength effect (RSE) concept for selection of input variables for ANN modeling and an approach for identifying anomalous data observations utilizing cross validation with ANN model are also presented.     

Development of a neural-based forecasting tool to classify recreational water quality using fecal indicator organisms

Users of recreational waters may be exposed to elevated pathogen levels through various point/non-point sources. Typical daily notifications rely on microbial analysis of indicator organisms (e.g., Escherichia coli) that require 18, or more, hours to provide an adequate response. Modeling approaches, such as multivariate linear regression (MLR) and artificial neural networks (ANN), have been utilized to provide quick predictions of microbial concentrations for classification purposes, but generally suffer from high false negative rates. This study introduces the use of learning vector quantization (LVQ) - a direct classification approach - for comparison with MLR and ANN approaches and integrates input selection for model development with respect to primary and secondary water quality standards within the Charles River Basin (Massachusetts, USA) using meteorologic, hydrologic, and microbial explanatory variables. Integrating input selection into model development showed that discharge variables were the most important explanatory variables while antecedent rainfall and time since previous events were also important. With respect to classification, all three models adequately represented the non-violated samples (>90%). The MLR approach had the highest false negative rates associated with classifying violated samples (41-62% vs 13-43% (ANN) and <16% (LVQ)) when using five or more explanatory variables. The ANN performance was more similar to LVQ when a larger number of explanatory variables were utilized, but the ANN performance degraded toward MLR performance as explanatory variables were removed. Overall, the use of LVQ as a direct classifier provided the best overall classification ability with respect to violated/non-violated samples for both standards.     

Artificial neural network analysis of the performance characteristics of a reversibly used cooling tower under cross flow conditions for heat pump heating system in winter

This study deals with predicting the performance characteristics of a reversibly used cooling tower (RUCT) under cross flow conditions for heat pump heating system in winter using artificial neural network (ANN) technique. For this aim, extensive field experimental work has been carried out in order to gather enough data for training and prediction. After back-propagation (BP) training combined with principal component analysis, the three-layer ANN model with a tangent sigmoid transfer function at hidden layer with 11 neurons and a linear transfer function at output layer was obtained. The predictions agreed well with the experimental values with a satisfactory correlation coefficient in the range of 0.9249-0.9988, the absolute fraction of variance in the range of 0.8753-0.9976, and the mean relative error in the range of 0.0008-0.54%, moreover, the root mean square error values for the ANN training and predictions were very low relative to the range of the experiments. The results reveal that ANN model can be used effectively for predicting the performance characteristics of RUCT under cross flow conditions, then providing the theoretical basis on the research of heat and mass transfer inside RUCT, which is important for design and running control of the RUCT system.     

Evaluation of the ability of an artificial neural network model to assess the variation of groundwater quality in an area of blackfoot disease in Taiwan

The back-propagation (BP) artificial neural network (ANN) is applied to forecast the variation of the quality of groundwater in the blackfoot disease area in Taiwan. Three types of BP ANN models were established to evaluate their learning performance. Model A included five concentration parameters as input variables for seawater intrusion and three concentration parameters as input variables for arsenic pollutant, respectively, whereas models B and C used only one concentration parameter for each. Furthermore, model C used seasonal data from two seasons to train the ANN, whereas models A and C used only data from one season. The results indicate that model C outperforms models A and B. Model C can describe complex variation of groundwater quality and be used to perform reliable forecasting. Moreover, the number of hidden nodes does not significantly influence the performance of the ANN model in training or testing.     

Artificial neural network for forecasting rainfall pattern in Prince Edward Island,Canada

The forecast performance of alternative artificial neural network (ANN) models was studied to compare their forecast accuracy to the fractionally integrated autoregressive moving average model using monthly rainfall data for the Canadian province of Prince Edward Island (PEI). A multilayer feed-forward back-propagation ANN algorithm is implemented to evaluate the forecast accuracy and to analyse the statistical characteristics of the ANN model for original data and for data pre-processed with moving average and exponential smoothing transformations. The prediction performance of these models is compared to that of a seasonal autoregressive fractionally integrated moving average time series model. The statistical results show that the ANN model with exponential smoothing of the data has the smallest root mean square error and the highest correlation coefficient and thus, outperforms the alternative models investigated in this study.     

Development of predictive models for determining enterococci levels at Gulf Coast beaches

The US EPA BEACH Act requires beach managers to issue swimming advisories when water quality standards are exceeded. While a number of methods/models have been proposed to meet the BEACH Act requirement, no systematic comparisons of different methods against the same data series are available in terms of relative performance of existing methods. This study presents and compares three models for nowcasting and forecasting enterococci levels at Gulf Coast beaches in Louisiana, USA. One was developed using the artificial neural network (ANN) in MATLAB Toolbox and the other two were based on the US EPA Virtual Beach (VB) Program. A total of 944 sets of environmental and bacteriological data were utilized. The data were collected and analyzed weekly during the swimming season (May-October) at six sites of the Holly Beach by Louisiana Beach Monitoring Program in the six year period of May 2005-October 2010. The ANN model includes 15 readily available environmental variables such as salinity, water temperature, wind speed and direction, tide level and type, weather type, and various combinations of antecedent rainfalls. The ANN model was trained, validated, and tested using 308, 103, and 103 data sets (collected in 2007, 2008, and 2009) with an average linear correlation coefficient (LCC) of 0.857 and a Root Mean Square Error (RMSE) of 0.336. The two VB models, including a linear transformation-based model and a nonlinear transformation-based model, were constructed using the same data sets. The linear VB model with 6 input variables achieved an LCC of 0.230 and an RMSE of 1.302 while the nonlinear VB model with 5 input variables produced an LCC of 0.337 and an RMSE of 1.205. In order to assess the predictive performance of the ANN and VB models, hindcasting was conducted using a total of 430 sets of independent environmental and bacteriological data collected at six Holly Beach sites in 2005, 2006, and 2010. The hindcasting results show that the ANN model is capable of predicting enterococci levels at the Holly Beach sites with an adjusted RMSE of 0.803 and LCC of 0.320 while the adjusted RMSE and LCC values are 1.815 and 0.354 for the linear VB model and 1.961and 0.521 for the nonlinear VB model. The results indicate that the ANN model with 15 parameters performs better than the VB models with 6 or 5 parameters in terms of RMSE while VB models perform better than the ANN model in terms of LCC. The predictive models (especially the ANN and the nonlinear VB models) developed in this study in combination with readily available real-time environmental and weather forecast data can be utilized to nowcast and forecast beach water quality, greatly reducing the potential risk of contaminated beach waters to human health and improving beach management. While the models were developed specifically for the Holly Beach, Louisiana, the methods used in this paper are generally applicable to other coastal beaches.     

Using extreme learning machines for short-term urban water demand forecasting

This study explores the ability of various machine learning methods to improve the accuracy of urban water demand forecasting for the city of Montreal (Canada). Artificial Neural Network (ANN), Support Vector Regression (SVR) and Extreme Learning Machine (ELM) models, in addition to a traditional model (Multiple linear regression, MLR) were developed to forecast urban water demand at lead times of 1 and 3 days. The use of models based on ELM in water demand forecasting has not previously been explored in much detail. Models were based on different combinations of the main input variables (e.g., daily maximum temperature, daily total precipitation and daily water demand), for which data were available for Montreal, Canada between 1999 and 2010. Based on the squared coefficient of determination, the root mean square error and an examination of the residuals, ELM models provided greater accuracy than MLR, ANN or SVR models in forecasting Montreal urban water demand for 1 day and 3 days ahead, and can be considered a promising method for short-term urban water demand forecasting.     

Prediction of bed load sediments using different artificial neural network models

Modeling and prediction of bed loads is an important but difficult issue in river engineering. The introduced empirical equations due to restricted applicability even in similar conditions provide different accuracies with each other and measured data. In this paper, three different artificial neural networks (ANNs) including multilayer percepterons, radial based function (RBF), and generalized feed forward neural network using five dominant parameters of bed load transport formulas for the Main Fork Red River in Idaho-USA were developed. The optimum models were found through 102 data sets of flow discharge, flow velocity, water surface slopes, flow depth, and mean grain size. The deficiency of empirical equations for this river by conducted comparison between measured and predicted values was approved where the ANN models presented more consistence and closer estimation to observed data. The coefficient of determination between measured and predicted values for empirical equations varied from 0.10 to 0.21 against the 0.93 to 0.98 in ANN models. The accuracy performance of all models was evaluated and interpreted using different statistical error criteria, analytical graphs and confusion matrixes. Although the ANN models predicted compatible outputs but the RBF with 79% correct classification rate corresponding to 0.191 network error was outperform than others.     

Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine

Plastic concrete is an engineering material, which is commonly used for construction of cut-off walls to prevent water seepage under the dam. This paper aims to explore two machine learning algorithms including artificial neural network (ANN) and support vector machine (SVM) to predict the compressive strength of bentonite/sepiolite plastic concretes. For this purpose, two unique sets of 72 data for compressive strength of bentonite and sepiolite plastic concrete samples (totally 144 data) were prepared by conducting an experimental study. The results confirm the ability of ANN and SVM models in prediction processes. Also, Sensitivity analysis of the best obtained model indicated that cement and silty clay have the maximum and minimum influences on the compressive strength, respectively. In addition, investigation of the effect of measurement error of input variables showed that change in the sand content (amount) and curing time will have the maximum and minimum effects on the output mean absolute percent error (MAPE) of model, respectively. Finally, the influence of different variables on the plastic concrete compressive strength values was evaluated by conducting parametric studies.     

Calibrating and validating bacterial water quality models: A Bayesian approach

Water resource management decisions often depend on mechanistic or empirical models to predict water quality conditions under future pollutant loading scenarios. These decisions, such as whether or not to restrict public access to a water resource area, may therefore vary depending on how models reflect process, observation, and analytical uncertainty and variability. Nonetheless, few probabilistic modeling tools have been developed which explicitly propagate fecal indicator bacteria (FIB) analysis uncertainty into predictive bacterial water quality model parameters and response variables. Here, we compare three approaches to modeling variability in two different FIB water quality models. We first calibrate a well-known first-order bacterial decay model using approaches ranging from ordinary least squares (OLS) linear regression to Bayesian Markov chain Monte Carlo (MCMC) procedures. We then calibrate a less frequently used empirical bacterial die-off model using the same range of procedures (and the same data). Finally, we propose an innovative approach to evaluating the predictive performance of each calibrated model using a leave-one-out cross-validation procedure and assessing the probability distributions of the resulting Bayesian posterior predictive p-values. Our results suggest that different approaches to acknowledging uncertainty can lead to discrepancies between parameter mean and variance estimates and predictive performance for the same FIB water quality model. Our results also suggest that models without a bacterial kinetics parameter related to the rate of decay may more appropriately reflect FIB fate and transport processes, regardless of how variability and uncertainty are acknowledged.     

ANN and ANFIS performance prediction models for hydraulic impact hammers

Hydraulic impact hammers are mechanical excavators that can be used in tunneling projects economically under geologic conditions suitable for rock breakage by indentation. However, there is relatively less published material in the literature in relation to predicting the performance of that equipment employing rock properties and machine parameters. In tunnel excavation projects, there is often a need for accurate prediction the performance of such machinery. The poor prediction of machine performance can lead to very costly contractual claims. In this study, the application of soft computing methods for data analysis called artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) to predict the net breaking rate of an impact hammer is demonstrated. The prediction capabilities offered by ANN and ANFIS were shown by using field data of obtained from metro tunnel project in Istanbul, Turkey. For this purpose, two prediction models based on ANN and ANFIS were developed and the results obtained from those models were then compared to those of multiple regression-based predictions. Various statistical performance indexes were used to compare the performance of those prediction models. The results suggest that the proposed ANFIS-based prediction model outperforms both ANN model and the classical multiple regression-based prediction model, and thus can be used to produce a more accurate and reliable estimate of impact hammer performance from Schmidt hammer rebound hardness (SHRH) and rock quality designation (RQD) values obtained from the field tests.     

Neural network modeling of salinity variation in Apalachicola River.

Salinity is an important indicator for water quality and aquatic ecosystem in tidal rivers. The increase of salinity intrusion in a river may have an adverse effect on the aquatic environment system. This study presents an application of the artificial neural network (ANN) to assess salinity variation responding to the multiple forcing functions of freshwater input, tide, and wind in Apalachicola River, Florida. Parameters in the neural network model were trained until the model predictions of salinity matched well with the observations. Then, the trained model was validated by applying the model to another independent data set. The results indicate that the ANN model is capable of correlating the non-linear time series of salinity to the multiple forcing signals of wind, tides. and freshwater input in the Apalachicola River. This study suggests that the ANN model is an easy-to-use modeling tool for engineers and water resource managers to obtain a quick preliminary assessment of salinity variation in response to the engineering modifications to the river system.     

Probabilistic prediction of urban water consumption using the SCEM-UA algorithm

Prediction of urban water consumption can help to improve the performance of water distribution systems. Despite the obvious presence of uncertainty in measurements and in assumed model types/structures, most of the existing water consumption prediction models are developed and used in a deterministic context. Methods for more realistic assessment of parameter and model prediction uncertainties have begun to appear in literature only recently. A novel application of the Shuffled Complex Evolution Metropolis algorithm (SCEM-UA) for the calibration of a water consumption prediction model is proposed here. The model is applied to a case study of the city of Catania (Italy) with the aim to predict daily water consumption. The SCEM-UA algorithm is used to calibrate the parameters of the artificial neural network based prediction model and in turn to determine the associated parameter and model prediction uncertainties. The results obtained using the SCEM-UA ANN approach were compared to the corresponding results obtained using other predictive models developed recently by the authors of the paper. When compared to the these models, the SCEM-UA ANN based water consumption prediction model shows similar predictive capability but also the ability to identify simultaneously the prediction uncertainty bounds associated with the posterior distribution of the parameter estimates.     

Modeling climate change impacts on water trading

This paper presents a new method of evaluating the impacts of climate change on the long-term performance of water trading programs, through designing an indicator to measure the mean of periodic water volume that can be released by trading through a water-use system. The indicator is computed with a stochastic optimization model which can reflect the random uncertainty of water availability. The developed method was demonstrated in the Swift Current Creek watershed of Prairie Canada under two future scenarios simulated by a Canadian Regional Climate Model, in which total water availabilities under future scenarios were estimated using a monthly water balance model. Frequency analysis was performed to obtain the best probability distributions for both observed and simulated water quantity data. Results from the case study indicate that the performance of a trading system is highly scenario-dependent in future climate, with trading effectiveness highly optimistic or undesirable under different future scenarios. Trading effectiveness also largely depends on trading costs, with high costs resulting in failure of the trading program.     

Neural network prediction of concrete degradation by sulphuric acid attack

Microbiologically induced corrosion is a leading cause of the deterioration of wastewater collection, transmission and treatment infrastructure around the world. This paper examines the feasibility of using artificial neural networks (ANNs) to predict the compressive strength of concrete and its degradation under exposure to sulphuric acid of various concentrations. A database incorporating 78 concrete mixtures performed by the authors was developed to train and test the ANN models. Data were arranged in a patterned format in such a manner that each pattern contains input variables (concrete mixture parameters) and the corresponding output vector (weight loss of concrete by H₂SO₄ attack and compressive strength at different ages). Results show that the ANN model I successfully predicted the weight loss of concrete specimens subjected to sulphuric acid attack, not only for mixtures used in the training process, but also for new mixtures unfamiliar to the ANN model designed within the practical range of the input parameters used in the training process. Root-mean-squared error (RMSE) and average absolute error (AAE) for ANN predictions of weight loss due to sulphuric acid attack were 0.013 and 8.45%, respectively. The ANN model II accurately predicted the compressive strength of the various concrete mixtures at different ages with RMSE and AAE of 2.35 MPa and 4.49%, respectively. A parametric study shows that both models I and II can successfully capture the sensitivity of output variables to changes in input parameters.     

Energy-savings predictions for building-equipment retrofits

Energy-consumption data collected from two equipment-retrofit projects before and after the retrofits was used to develop a model that estimates energy savings from retrofit projects. The computation method used in the model is based on Artificial Neural Networks (ANN). The model integrates weather variables, specific equipment-usage and occupancy data, and building-operation schedules into the pre-retrofit energy-usage pattern. It then estimates the energy usage of the pre-retrofit equipment in the post-retrofit period by using weather data, occupancy, and building-operation schedules in the post-retrofit period. The difference between the recorded energy usage of the post-retrofit equipment and the predicted energy usage of the pre-retrofit equipment in the post-retrofit period is the estimate of energy savings. For the two retrofit projects used in the ANN model, the coefficient of correlation varied from 0.957 to 0.844; the root mean square error varied from 6.81% to 16.4%; and the mean absolute error varied from 5.31% to 9.95%. Additionally, the sensitivity of the model to the input variables was analyzed with one of the retrofit project data. Dry bulb temperature, wet bulb temperature, and time (representing building-occupancy and equipment-operation schedule) were determined as the most effective variables in the ANN model. The research and findings are presented in this paper.     

A composite indicator for water meter replacement in an urban distribution network

In water supply management, volumetric water meter are typically used to measure users' consumption. With water meters, utilities can collect useful data for billing, assess the water balance of the system, and identify failures in the network, water theft and anomalous user behaviour. Despite their importance, these instruments are characterised by intrinsic errors that cause so-called apparent losses. The complexity of the physical phenomena associated with metering errors in aging water meters does not allow meter replacement to be guided by single parameters, such as the meter age or the total volume passed through the meter. This paper presents a meter replacement strategy based on a composite ‘Replacement Indicator’ (RI) that aims to reduce apparent losses. The performance of a meter during its operating life was analysed by means of this indicator, which signals when the meter needs to be replaced. To test the reliability and robustness of the proposed indicator, a Monte Carlo uncertainty analysis was performed. The methodology was applied to a real case study: a district metered area (DMA) in the Palermo city water distribution network (Italy). The analysis showed that ranking based on the composite indicator is better than common ranking procedures based on typical variables (e.g., the meter error curve or the meter age): the proposed indicator can better select the meters to be replaced and favourably affect the associated costs.     

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore mine,Iran简

Blast-induced ground vibration is one of the inevitable outcomes of blasting in mining projects and may cause substantial damage to rock mass as well as nearby structures and human beings. In this paper, an attempt has been made to present an application of artificial neural network (ANN) to predict the blast-induced ground vibration of the Gol-E-Gohar (GEG) iron mine, Iran. A four-layer feed-forward back propagation multi-layer perceptron (MLP) was used and trained with Levenberg–Marquardt algorithm. To construct ANN models, the maximum charge per delay, distance from blasting face to monitoring point, stemming and hole depth were taken as inputs, whereas peak particle velocity (PPV) was considered as an output parameter. A database consisting of 69 data sets recorded at strategic and vulnerable locations of GEG iron mine was used to train and test the generalization capability of ANN models. Coefficient of determination (R²) and mean square error (MSE) were chosen as the indicators of the performance of the networks. A network with architecture 4-11-5-1 and R² of 0.957 and MSE of 0.000722 was found to be optimum. To demonstrate the supremacy of ANN approach, the same 69 data sets were used for the prediction of PPV with four common empirical models as well as multiple linear regression (MLR) analysis. The results revealed that the proposed ANN approach performs better than empirical and MLR models.     

Artificial neural networks to predict daylight illuminance in office buildings

A prediction model was developed to determine daylight illuminance for the office buildings by using artificial neural networks (ANNs). Illuminance data were collected for 3 months by applying a field measuring method. Utilizing weather data from the local weather station and building parameters from the architectural drawings, a three-layer ANN model of feed-forward type (with one output node) was constructed. Two variables for time (date, hour), 5 weather determinants (outdoor temperature, solar radiation, humidity, UV index and UV dose) and 6 building parameters (distance to windows, number of windows, orientation of rooms, floor identification, room dimensions and point identification) were considered as input variables. Illuminance was used as the output variable. In ANN modeling, the data were divided into two groups; the first 80 of these data sets were used for training and the remaining 20 for testing. Microsoft Excel Solver used simplex optimization method for the optimal weights. The model's performance was then measured by using the illuminance percentage error. As the prediction power of the model was almost 98%, predicted data had close matches with the measured data. The prediction results were successful within the sample measurements. The model was then subjected to sensitivity analysis to determine the relationship between the input and output variables. NeuroSolutions Software by NeuroDimensions Inc., was adopted for this application. Researchers and designers will benefit from this model in daylighting performance assessment of buildings by making predictions and comparisons and in the daylighting design process by determining illuminance.