Tailoring groundwater quality monitoring to vulnerability: a GIS procedure for network design

Monitoring networks aiming to assess the state of groundwater quality and detect or predict changes could increase in efficiency when fitted to vulnerability and pollution risk assessment. The main purpose of this paper is to describe a methodology aiming at integrating aquifers vulnerability and actual levels of groundwater pollution in the monitoring network design. In this study carried out in a pilot area in central Italy, several factors such as hydrogeological setting, groundwater vulnerability, and natural and anthropogenic contamination levels were analyzed and used in designing a network tailored to the monitoring objectives, namely, surveying the evolution of groundwater quality relating to natural conditions as well as to polluting processes active in the area. Due to the absence of an aquifer vulnerability map for the whole area, a proxi evaluation of it was performed through a geographic information system (GIS) methodology, leading to the so called “susceptibility to groundwater quality degradation”. The latter was used as a basis for the network density assessment, while water points were ranked by several factors including discharge, actual contamination levels, maintenance conditions, and accessibility for periodical sampling in order to select the most appropriate to the network. Two different GIS procedures were implemented which combine vulnerability conditions and water points suitability, producing two slightly different networks of 50 monitoring points selected out of the 121 candidate wells and springs. The results are compared with a “manual” selection of the points. The applied GIS procedures resulted capable to select the requested number of water points from the initial set, evaluating the most confident ones and an appropriate density. Moreover, it is worth underlining that the second procedure (point distance analysis [PDA]) is technically faster and simpler to be performed than the first one (GRID?+?PDA).     

Estimating soil temperature using neighboring station data via multi-nonlinear regression and artificial neural network models

The aim of this study is to estimate the soil temperatures of a target station using only the soil temperatures of neighboring stations without any consideration of the other variables or parameters related to soil properties. For this aim, the soil temperatures were measured at depths of 5, 10, 20, 50, and 100 cm below the earth surface at eight measuring stations in Turkey. Firstly, the multiple nonlinear regression analysis was performed with the “Enter” method to determine the relationship between the values of target station and neighboring stations. Then, the stepwise regression analysis was applied to determine the best independent variables. Finally, an artificial neural network (ANN) model was developed to estimate the soil temperature of a target station. According to the derived results for the training data set, the mean absolute percentage error and correlation coefficient ranged from 1.45% to 3.11% and from 0.9979 to 0.9986, respectively, while corresponding ranges of 1.685–3.65% and 0.9988–0.9991, respectively, were obtained based on the testing data set. The obtained results show that the developed ANN model provides a simple and accurate prediction to determine the soil temperature. In addition, the missing data at the target station could be determined within a high degree of accuracy.     

Artificial neural network modeling of dissolved oxygen in reservoir

The water quality of reservoirs is one of the key factors in the operation and water quality management of reservoirs. Dissolved oxygen (DO) in water column is essential for microorganisms and a significant indicator of the state of aquatic ecosystems. In this study, two artificial neural network (ANN) models including back propagation neural network (BPNN) and adaptive neural-based fuzzy inference system (ANFIS) approaches and multilinear regression (MLR) model were developed to estimate the DO concentration in the Feitsui Reservoir of northern Taiwan. The input variables of the neural network are determined as water temperature, pH, conductivity, turbidity, suspended solids, total hardness, total alkalinity, and ammonium nitrogen. The performance of the ANN models and MLR model was assessed through the mean absolute error, root mean square error, and correlation coefficient computed from the measured and model-simulated DO values. The results reveal that ANN estimation performances were superior to those of MLR. Comparing to the BPNN and ANFIS models through the performance criteria, the ANFIS model is better than the BPNN model for predicting the DO values. Study results show that the neural network particularly using ANFIS model is able to predict the DO concentrations with reasonable accuracy, suggesting that the neural network is a valuable tool for reservoir management in Taiwan.     

A water quality monitoring network design methodology for the selection of critical sampling points: Part II

In order to resolve the spatial component of the design of a water quality monitoring network, a methodology has been developed to identify the critical sampling locations within a watershed. This methodology, called Critical Sampling Points (CSP), focuses on the contaminant total phosphorus (TP), and is applicable to small, predominantly agricultural-forested watersheds. The CSP methodology was translated into a model, called Water Quality Monitoring Station Analysis (WQMSA). It incorporates a geographic information system (GIS) for spatial analysis and data manipulation purposes, a hydrologic/water quality simulation model for estimating TP loads, and an artificial intelligence technology for improved input data representation. The model input data include a number of hydrologic, topographic, soils, vegetative, and land use factors. The model also includes an economic and logistics component. The validity of the CSP methodology was tested on a small experimental Pennsylvanian watershed, for which TP data from a number of single storm events were available for various sampling points within the watershed. A comparison of the ratios of observed to predicted TP loads between sampling points revealed that the model's results were promising.     

Forest cover change and fragmentation using Landsat data in Maçka State Forest Enterprise in Turkey

In this study, Grey model (GM) and artificial neural network (ANN) were employed to predict suspended solids (SSeff) and chemical oxygen demand (CODeff) in the effluent from a wastewater treatment plant in industrial park of Taiwan. When constructing model or predicting, the influent quality or online monitoring parameters were adopted as the input variables. ANN was also adopted for comparison. The results indicated that the minimum MAPEs of 16.13 and 9.85% for SSeff and CODeff could be achieved using GMs when online monitoring parameters were taken as the input variables. Although a good fitness could be achieved using ANN, they required a large quantity of data. Contrarily, GM only required a small amount of data (at least four data) and the prediction results were even better than those of ANN. Therefore, GM could be applied successfully in predicting effluent when the information was not sufficient. The results also indicated that these simple online monitoring parameters could be applied on prediction of effluent quality well.     

Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China

Identification and quantification of dissolved oxygen (DO) profiles of river is one of the primary concerns for water resources managers. In this research, an artificial neural network (ANN) was developed to simulate the DO concentrations in the Heihe River, Northwestern China. A three-layer back-propagation ANN was used with the Bayesian regularization training algorithm. The input variables of the neural network were pH, electrical conductivity, chloride (Cl^?), calcium (Ca²⁺), total alkalinity, total hardness, nitrate nitrogen (NO₃-N), and ammonical nitrogen (NH₄-N). The ANN structure with 14 hidden neurons obtained the best selection. By making comparison between the results of the ANN model and the measured data on the basis of correlation coefficient (r) and root mean square error (RMSE), a good model-fitting DO values indicated the effectiveness of neural network model. It is found that the coefficient of correlation (r) values for the training, validation, and test sets were 0.9654, 0.9841, and 0.9680, respectively, and the respective values of RMSE for the training, validation, and test sets were 0.4272, 0.3667, and 0.4570, respectively. Sensitivity analysis was used to determine the influence of input variables on the dependent variable. The most effective inputs were determined as pH, NO₃-N, NH₄-N, and Ca²⁺. Cl^? was found to be least effective variables on the proposed model. The identified ANN model can be used to simulate the water quality parameters.     

Optimizing the Monitoring Strategy of Wastewater Treatment Plants by Multiobjective Neural Networks Approach

This paper applies artificial neural network (ANN) to model the observed effluent quality data. The ANN’s structure, involving the number of hidden layer and node and their connection, is determined endogenously by resorting to the compromise of data cost minimization and prediction accuracy maximization. To obtain the best compromise possible, the model introduces an aspiration variable (μ) that represents the level of aspiration achieved in one objective and the conjugate of μ, (1 − μ), represents level of aspiration achieved in the other objective. Because a massive amount of calculation is required, the model applies genetic algorithm (GA) for its computational flexibility and capability to ensure global solution. Feasibility and practicality of the model is tested by a case study with a set of 150 daily observations on 17 operational variables and quality parameters at an industrial wastewater treatment plant (WTP) located in southern Taiwan. Of these 17 variables open to selection, only 6 variables, wastewater flow rate (Q), CN⁻, SS, MLSS, pH and COD are selected by the model to achieve the maximum accuracy of prediction, 0.94, with a total cost of 5,950 NT$. By constraining budget availability, the variables included in the model are reduced in number, causing a concomitant reduction in prediction accuracy, that is, by varying μ (aspiration level of accuracy), a trajectory of cost and accuracy is generated. The calculation results a cost of 3,650 NT$ and 0.54 accuracy for the case with variables including flow rate, SCN⁻ and SS in equalization basin; aeration tank hydraulic retention time (HRT) and percentage of returned sludge (R%) are selected for building the prediction model when the importance of required budget is equal to the accuracy of prediction model. In addition, when required cost for building ANN model is between 3,650 NT$ and 3,900 NT$, the marginal return of budget input is highest in the entire range of calculation.     

WEPP and ANN models for simulating soil loss and runoff in a semi-arid Mediterranean region

This paper presents the use of both the Water Erosion Prediction Project (WEPP) and the artificial neural network (ANN) for the prediction of runoff and soil loss in the central highland mountainous of the Palestinian territories. Analyses show that the soil erosion is highly dependent on both the rainfall depth and the rainfall event duration rather than on the rainfall intensity as mostly mentioned in the literature. The results obtained from the WEPP model for the soil loss and runoff disagree with the field data. The WEPP underestimates both the runoff and soil loss. Analyses conducted with the ANN agree well with the observation. In addition, the global network models developed using the data of all the land use type show a relatively unbiased estimation for both runoff and soil loss. The study showed that the ANN model could be used as a management tool for predicting runoff and soil loss.     

Using a neural network approach and time series data from an international monitoring station in the Yellow Sea for modeling marine ecosystems

The international marine ecological safety monitoring demonstration station in the Yellow Sea was developed as a collaborative project between China and Russia. It is a nonprofit technical workstation designed as a facility for marine scientific research for public welfare. By undertaking long-term monitoring of the marine environment and automatic data collection, this station will provide valuable information for marine ecological protection and disaster prevention and reduction. The results of some initial research by scientists at the research station into predictive modeling of marine ecological environments and early warning are described in this paper. Marine ecological processes are influenced by many factors including hydrological and meteorological conditions, biological factors, and human activities. Consequently, it is very difficult to incorporate all these influences and their interactions in a deterministic or analysis model. A prediction model integrating a time series prediction approach with neural network nonlinear modeling is proposed for marine ecological parameters. The model explores the natural fluctuations in marine ecological parameters by learning from the latest observed data automatically, and then predicting future values of the parameter. The model is updated in a “rolling” fashion with new observed data from the monitoring station. Prediction experiments results showed that the neural network prediction model based on time series data is effective for marine ecological prediction and can be used for the development of early warning systems.     

Uncertainty based optimal monitoring network design for a chlorinated hydrocarbon contaminated site

An application of a newly developed optimal monitoring network for the delineation of contaminants in groundwater is demonstrated in this study. Designing a monitoring network in an optimal manner helps to delineate the contaminant plume with a minimum number of monitoring wells at optimal locations at a contaminated site. The basic principle used in this study is that the wells are installed where the measurement uncertainties are minimum at the potential monitoring locations. The development of the optimal monitoring network is based on the utilization of contaminant concentration data from an existing initial arbitrary monitoring network. The concentrations at the locations that were not sampled in the study area are estimated using geostatistical tools. The uncertainty in estimating the contaminant concentrations at such locations is used as design criteria for the optimal monitoring network. The uncertainty in the study area was quantified by using the concentration estimation variances at all the potential monitoring locations. The objective function for the monitoring network design minimizes the spatial concentration estimation variances at all potential monitoring well locations where a monitoring well is not to be installed as per the design criteria. In the proposed methodology, the optimal monitoring network is designed for the current management period and the contaminant concentration data estimated at the potential observation locations are then used as the input to the network design model. The optimal monitoring network is designed for the consideration of two different cases by assuming different initial arbitrary existing data. Three different scenarios depending on the limit of the maximum number of monitoring wells that can be allowed at any period are considered for each case. In order to estimate the efficiency of the developed optimal monitoring networks, mass estimation errors are compared for all the three different scenarios of the two different cases. The developed methodology is useful in coming up with an optimal number of monitoring wells within the budgetary limitations. The methodology also addresses the issue of redundancy, as it refines the existing monitoring network without losing much information of the network. The concept of uncertainty-based network design model is useful in various stages of a potentially contaminated site management such as delineation of contaminant plume and long-term monitoring of the remediation process.     

Application of artificial neural network approach and remotely sensed imagery for regional eco-environmental quality evaluation

Eco-environment quality evaluation is an important research theme in environment management. In the present study, Fuzhou city in China was selected as a study area and a limited number of 222 sampling field sites were first investigated in situ with the help of a GPS device. Every sampling site was assessed by ecological experts and given an Eco-environment Background Value (EBV) based on a scoring and ranking system. The higher the EBV, the better the ecological environmental quality. Then, three types of eco-environmental attributes that are physically-based and easily-quantifiable at a grid level were extracted: (1) remote sensing derived attributes (vegetation index, wetness index, soil brightness index, surface land temperature index), (2) meteorological attributes (annual temperature and annual precipitation), and (3) terrain attribute (elevation). A Back Propagation (BP) Artificial Neural Network (ANN) model was proposed for the EBV validation and prediction. A three-layer BP ANN model was designed to automatically learn the internal relationship using a training set of known EBV and eco-environmental attributes, followed by the application of the model for predicting EBV values across the whole study area. It was found that the performance of the BP ANN model was satisfactory and capable of an overall prediction accuracy of 82.4%, with a Kappa coefficient of 0.801 in the validation. The evaluation results showed that the eco-environmental quality of Fuzhou city is considered as satisfactory. Through analyzing the spatial correlation between the eco-environmental quality and land uses, it was found that the best eco-environmental areas were related to forest lands, whereas the urban area had the relatively worst eco-environmental quality. Human activities are still considered as a major impact on the eco-environmental quality in this area.     

Derivation of unit and flood hydrographs using a gis

A geographic information system (GIS) supporting a flood hydrograph prediction software package is described. The hydrograph prediction method is based on the convolution of excess rainfall with a synthetic unit hydrograph, derived by the Soil Conservation Service runoff curve number and a regional dimensionless unit hydrograph method, respectively. The GIS uses a raster method to store the following data: land use and land cover, soil type, rainfall intensity-frequency-duration statistics, runoff curve numbers (CN), regional dimensionless unit hydrograph, and regional lag-time relationship. The GIS has also the capability of computing a number of watershed and hydrologic parameters required for predictions, such as a watershed average rainfall and CN value, area, centroid, stream length etc. Most of the data for such computations are input from a digitizer. Substantial time and cost savings are possible once the data base has been created. Application of the system is illustrated by an example predicting flood frequency curves for selected watersheds in Alberta's Rocky Mountain foothills, Canada.     

Modeling of SO<Subscript>2</Subscript> distribution in Istanbul using artificial neural networks

Urban air pollution is a growing problem in developing countries. Some compounds especially sulphur dioxide (SO₂) is considered as typical indicators of the urban air quality. Air pollution modeling and prediction have great importance in preventing the occurrence of air pollution episodes and provide sufficient time to take the necessary precautions. Recently, various stochastic image-processing algorithms such as Artificial Neural Network (ANN) are applied to environmental engineering. ANN structure employs input, hidden and output layers. Due to the complexity of the problem, as the number of input–output parameters differs, ANN model settings such as the number of neurons of these layers changes. The ability of ANN models to learn, particularly capability of handling large amounts (or sets) of data simultaneously as well as their fast response time, are invariably the characteristics desired for predictive and forecasting purposes. In this paper, ANN models have been used to predict air pollutant parameter in meteorological considerations. We have especially focused on modeling of SO₂ distribution and predicting its future concentration in Istanbul, Turkey. We have obtained data sets including meteorological variables and SO₂ concentrations from Istanbul-Florya meteorological station and Istanbul-Yenibosna air pollution station. We have preferred three-layer perceptron type of ANN which consists of 10, 22 and 1 neurons for input, hidden and output layers, respectively. All considered parameters are measured as daily mean. The input parameters are: SO₂ concentration, pressure, temperature, humidity, wind direction, wind speed, strength of sunshine, sunshine, cloudy, rainfall and output parameter is the future prediction of SO₂. To evaluate the performance of ANN model, our results are compared to classical nonlinear regression methods. The over all system finds an optimum correlation between input–output variables. Here, the correlation parameter, r is 0.999 and 0.528 for training and test data. Thus in our model, the trend of SO₂ is well estimated and seasonal effects are well represented. As a result, we conclude that ANN is one of the compromising methods in estimation of environmental complex air pollution problems.     

Modeling seasonal variations of long-term soil CO<Subscript>2</Subscript> emissions in an orchard plantation in a semiarid area,SE Turkey

Emissions of soil CO₂ under different management systems have a significant effect on the carbon balance in the atmosphere. Soil CO₂ emissions were measured from an apricot orchard at two different locations: under the crown of trees (CO₂-UC) and between tree rows (CO₂-BR). For comparison, one other measurement was performed on bare soil (CO₂-BS) located next to the orchard field. Analytical data were obtained weekly during 8 years from April 2008 to December 2016. Various environmental parameters such as air temperature, soil temperature at different depths, soil moisture, rainfall, and relative humidity were used for modeling and estimating the long-term seasonal variations in soil CO₂ emissions using two different methods: generalized linear model (GLM) and artificial neural network (ANN). Before modeling, data were randomly split into two parts, one for calibration and the second for validation, with a varying number of samples in each part. Performances of the models were compared and evaluated using means absolute of estimations (MAE), square root of mean of prediction (RMSEP), and coefficient of determination (R²) values. CO₂-UC, CO₂-BR, and CO₂-BS values ranged from 11 to 3985, from 9 to 2365, and from 8 to 1722 kg ha^?1 week^?1, respectively. Soil CO₂ emissions were significantly correlated (p?<?0.05) with some environmental variables. The results showed that GLM and ANN models provided similar accuracies in modeling and estimating soil CO₂ emissions, as the number of samples in the validation data set increased. The ANN was more advantageous than GLM models by providing a better fit between actual observations and predictions and lower RMSEP and MAE values. The results suggested that the success of environmental variables for estimations of CO₂ emissions using the two methods was moderate.     

Multilayer perceptron neural network for flow prediction

Artificial neural networks (ANNs) have proven to be a tool for characterizing, modeling and predicting many of the non-linear hydrological processes such as rainfall-runoff, groundwater evaluation or simulation of water quality. After proper training they are able to generate satisfactory predictive results for many of these processes. In this paper they have been used to predict 1 or 2 days ahead the average and maximum daily flow of a river in a small forest headwaters in northwestern Spain. The inputs used were the flow and climate data (precipitation, temperature, relative humidity, solar radiation and wind speed) as recorded in the basin between 2003 and 2008. Climatic data have been utilized in a disaggregated form by considering each one as an input variable in ANN(1), or in an aggregated form by its use in the calculation of evapotranspiration and using this as input variable in ANN(2). Both ANN(1) and ANN(2), after being trained with the data for the period 2003-2007, have provided a good fit between estimated and observed data, with R(2) values exceeding 0.95. Subsequently, its operation has been verified making use of the data for the year 2008. The correlation coefficients obtained between the data estimated by ANNs and those observed were in all cases superior to 0.85, confirming the capacity of ANNs as a model for predicting average and maximum daily flow 1 or 2 days in advance.     

Hybrid Neural Networks and Boosted Regression Tree Models for Predicting Roadside Particulate Matter

This paper examines the application of artificial neural network (ANN) and boosted regression tree (BRT) methods in air quality modelling. The methods were applied to developing air quality models for predicting roadside particle mass concentration (PM₁₀, PM_2.5) and particle number counts (PNC) based on air pollution, traffic and meteorological data from Marylebone Road in London. Elastic net, Lasso and principal components analysis were used as feature selection methods for the ANN models to reduce the number of predictor variables and improve their generalisation. The performance of the ANN with feature selection (ANN hybrid) and the BRT models was evaluated and compared using statistical performance metrics. The performance parameters include root mean square error (RMSE), fraction of prediction within a factor of two of the observation (FAC2), mean bias (MB), mean gross error (MGE), the coefficient of correlation (R) and coefficient of efficiency (CoE) values. The input variables selected by the elastic net produced the best performing ANN models. The ANN hybrid produced models performed only slightly better than the BRT models. The R values of the ANN elastic net and BRT models were 0.96 and 0.95 for PM₁₀, 0.96 and 0.96 for PM_2.5 and 0.89 and 0.87 for PNC, respectively. Their corresponding CoE values were 0.72 and 0.70 for PM₁₀, 0.74 and 0.76 for PM_2.5 and 0.81 and 0.71 for PNC respectively. About 80–99% of all the model predictions are within a factor of two of the observed particle concentrations. The BRT models offer more advantages regarding model interpretation and permit feature selection. Therefore, the study recommends the use of BRT over ANN where the model interpretation is a priority.     

Role of Geographic Information System (GIS) in Watershed Simulation By Winvast Model

The uncertainty of modeling input will increase the simulation error, and this situation always happens in a model without user-friendly interface. WinVAST model, developed by the University of Virginia in 2003, treats an entire multi-catchment by a tree-view structure. Its extra computer programs can connect geographic information system (GIS). Model users can prepare all the necessary information in ArcGIS. Extracting information from GIS interface can not only decrease the inconvenience of data input, but also lower the uncertainty due to data preparation. The Daiyuku Creek and Qupoliao Creek in the Fei-tsui reservoir watershed in Northern Taiwan provided the setting for the case study reported herein. The required information, including slope, stream length, subbasin area, soil type and land-use condition, for WinVAST model should be prepared in a Microsoft Access database, which is the project file of WinVAST with extension mdb. In ArcGIS interface, when the soil layer, land-use layer, and Digital Elevation Model (DEM) map are prepared, all the watershed information can be created as well. This study compared the simulation results from automatically generated input and manual input. The results show that the relative simulation error resulting from the rough process of data input can be around 30% in runoff simulation, and even reach 70% in non-point source pollution (NPSP) simulation. It could conclude that GIS technology is significant for predicting watershed responses by WinVAST model, because it can efficiently reduce the uncertainty induced by input errors.     

Cumulative effects of developed road network on woodland—a landscape approach

Population growth, during the twentieth century, has increased demand for new farmlands. Accordingly, road networks have rapidly been developed to facilitate and accelerate human access to the essential resources resulted in extensive land use changes. The present study aims at assessing cumulative effects of developed road network on tree cover of Golestan Province in northern Iran. In order to detect changes over the study period of 1987–2002, the LULC map of the study area was initially prepared from the satellite images of Landsat TM (1987) and ETM+ (2002) using maximum likelihood supervised classification method. Afterwards, a total number of seven landscape matrices were selected to detect cumulative effects of the developed road network on woodland cover. The obtained results indicated that the fragile patches are mainly located at a distance of 171–342 m from the roadside. Furthermore, the majority of the patches affected by cumulative effects of development activities are situated at a distance of 342–684 m from the roadside, over an approximate area of 55 ha. The analysis of landscape metrics revealed that the developed road network has increased the landscape metrics of “the number of patches” and “patches perimeter-area ratio”. It has also followed by a decrease in metrics such as “patches area”, “Euclidean nearest neighbor distance”, “patches proximity”, “shape index”, “contiguity”, and “mean patches fractal dimension”. The road network has also increased the “number of patches” and decreased the “mean patches area” representing further fragmentation of the landscape. With identification of highly affected wooldland cover patches, it would be possible to apply adaptive environmental management strategies to preserve and rehabilitate high-priority patches.     

地理3G系统应用于城市固体废物管理的新模式

基于GPS、GPRS、GIS地理3G综合技术,设计城市固体废物综合监管系统,实现对固体废物从收集到再利用全过程的监督管理。该系统由申报信息系统、地面控制系统、处置保障系统、综合分析系统、应急指挥系统和线上“淘宝”系统组成,在固体废物收集站点采集的数据上传至综合分析系统,经分析与匹配后相关信息发布在线上“淘宝”交易平台,平台为买卖双方提供资源配置方案,也为管理部门的宏观调控提供数据支撑。