Predicting conductance due to upconing using neural networks

Artificial neural networks (ANNs) were developed to accurately predict highly time-variable specific conductance values in an unconfined coastal aquifer. Conductance values in the fresh water lens aquifer change in response to vertical displacements of the brackish zone and fresh water-salt water interface, which are caused by variable pumping and climate conditions. Unlike physical-based models, which require hydrologic parameter inputs, such as horizontal and vertical hydraulic conductivities, porosity, and fluid densities, ANNs can "learn" system behavior from easily measurable variables. In this study, the ANN input predictor variables were initial conductance, total precipitation, mean daily temperature, and total pumping extraction. The ANNs were used to predict salinity (specific conductance) at a single monitoring well located near a high-capacity municipal-supply well over time periods ranging from 30 d to several years. Model accuracy was compared against both measured/interpolated values and predictions were made with linear regression, and in general, excellent prediction accuracy was achieved. For example, although the average percent change of conductance over 90-d periods was 39%, the absolute mean prediction error achieved with the ANN was only 1.1%. The ANNs were also used to conduct a sensitivity analysis that quantified the importance of each of the four predictor variables on final conductance values, providing valuable insights into the dynamics of the system. The results demonstrate that the ANN technology can serve as a powerful and accurate prediction and management tool, minimizing degradation of ground water quality to the extent possible by identifying appropriate pumping policies under variable and/or changing climate conditions.     

Diagnostic study and modeling of the annual positive water temperature onset

A data-driven model is designed using artificial neural networks (ANN) to predict the average onset for the annual water temperature cycle of North-American streams. The data base is composed of daily water temperature time series recorded at 48 hydrometric stations in Québec (Canada) and northern US, as well as the geographic and physiographic variables extracted from the 48 associated drainage basins. The impact of individual and combined drainage area characteristics on the stream annual temperature cycle starting date is investigated by testing different combinations of input variables. The best model allows to predict the average temperature onset for a site, given its geographical coordinates and vegetation and lake coverage characteristics, with a root mean square error (RMSE) of 5.6 days. The best ANN model was compared favourably with parametric approaches.     

Evaluating ground water-sea water interactions via resistivity and seepage meters

We investigated submarine ground water discharge and salt water-fresh water interactions at two locations along the shoreline of the Upper Gulf of Thailand to evaluate mechanisms of water and material transport into the coastal zone. Our data set illustrates the value of using a combined approach consisting of automatic seepage meters to monitor flow rates while assessing the conductivity (salinity) of the subterranean fluids via remote resistivity measurements. Negative correlations between electric conductivities of fluids measured directly inside seepage meter chambers and the remotely assessed resistivities of subsurface pore water show that such measurements may evaluate the spatial distribution of flow rates as well as the subterranean water quality in the coastal zone. Combined seepage and resistivity measurements may thus provide a more complete understanding of coastal ground water dynamics.     

A neural network model for predicting aquifer water level elevations

Artificial neural networks (ANNs) were developed for accurately predicting potentiometric surface elevations (monitoring well water level elevations) in a semiconfined glacial sand and gravel aquifer under variable state, pumping extraction, and climate conditions. ANNs "learn" the system behavior of interest by processing representative data patterns through a mathematical structure analogous to the human brain. In this study, the ANNs used the initial water level measurements, production well extractions, and climate conditions to predict the final water level elevations 30 d into the future at two monitoring wells. A sensitivity analysis was conducted with the ANNs that quantified the importance of the various input predictor variables on final water level elevations. Unlike traditional physical-based models, ANNs do not require explicit characterization of the physical system and related physical data. Accordingly, ANN predictions were made on the basis of more easily quantifiable, measured variables, rather than physical model input parameters and conditions. This study demonstrates that ANNs can provide both excellent prediction capability and valuable sensitivity analyses, which can result in more appropriate ground water management strategies.     

Multiple‐station neural network for modelling tidal currents across Shinnecock inlet,USA

This paper presents the development of a multiple‐station neural network for predicting tidal currents across a coastal inlet. Unlike traditional hydrodynamic models, the neural network model does not need inputs of coastal topography and bathymetry, grids, surface and bottom frictions, and turbulent eddy viscosity. Without solving hydrodynamic equations, the neural network model applies an interconnected neural network to correlate the inputs of boundary forcing of water levels at a remote station to the outputs of tidal currents at multiple stations across a local coastal inlet. Coefficients in the neural network model are trained using a continuous dataset consisting of inputs of water levels at a remote station and outputs of tidal currents at the inlet, and verified using another independent input and output dataset. Once the neural network model has been satisfactorily trained and verified, it can be used to predict tidal currents at a coastal inlet from the inputs of water levels at a remote station. For the case study at Shinnecock Inlet in the southern shore of New York, tidal currents at nine stations across the inlet were predicted by the neural network model using water level data located from a station about 70 km away from the inlet. A continuous dataset in May 2000 was used for the training, and another dataset in July 2000 was used for the verification of the neural network model. Comparing model predictions and observations indicates correlation coefficients range from 0·95 to 0·98, and the root‐mean‐square error ranges from 0·04 to 0·08 m s^?1 at the nine current locations across the inlet. Copyright © 2007 John Wiley & Sons, Ltd.     

Prediction of daily sediment discharge using a back propagation neural network training algorithm: A case study of the Narmada River,India

Most of the studies on Artificial Neural Network (ANN) models remain restricted to smaller rivers and catchments. In this paper, an attempt has been made to correlate variability of sediment loads with rainfall and runoff through the application of the Back Propagation Neural Network (BPNN) algorithm for a large tropical river. The algorithm and simulation are done through MATLAB environment. The methodology comprised of a collection of data on rainfall, water discharge, and sediment discharge for the Narmada River at various locations (along with time variables) and application to develop a threelayer BPNN model for the prediction of sediment discharges. For training and validation purposes a set of 549 data points for the monsoon (16 June-15 November) period of three consecutive years (1996–1998) was used. For testing purposes, the BPNN model was further trained using a set of 732 data points of monsoon season of four years (2006–07 to 2009–10) at nine stations. The model was tested by predicting daily sediment load for the monsoon season of the year 2010–11. To evaluate the performance of the BPNN model, errors were calculated by comparing the actual and predicted loads. The validation and testing results obtained at all these locations are tabulated and discussed. Results obtained from the model application are robust and encouraging not only for the sub-basins but also for the entire basin. These results suggest that the proposed model is capable of predicting the daily sediment load even at downstream locations, which show nonlinearity in the transportation process. Overall, the proposed model with further training might be useful in the prediction of sediment discharges for large river basins.     

Evaluation of total load sediment transport formulas using ANN

The calculated results from various sediment transport formulas often differ from each other and from measured data. Some parameters in the sediment transport formulas are more effective than others to estimate total sediment load. In this study, an Artificial Neural Network （ANN） model is trained using four dominant parameters of sediment transport formulas. ANN models are able to reveal hidden laws of natural phenomena such as sediment transport process. The results of ANN and some total bed material load sediment transport formulas have been compared to indicate the importance of variables which can be used in developing sediment transport formulas. To train ANN, average flow velocity, water surface slopes, average flow depth, and median particle diameter are used as dominant parameters to estimate total bed material load. Two hundreds and fifty samples are used to train the ANN model. Twenty-four sets of field data not used in the training nor calibration of ANN are used to compare or verify the accuracy of ANN and some well-known total bed material load formulas. The test results show that the ANN model developed in this study using minimum number of dominant factors is a reliable and uncomplicated method to predict total sediment transport rate or total bed material load transport rate. Results show that the accuracy of formulas in descending order are those by Yang （1973）, Laursen （1958）, Engelund and Hansen （1972）, Ackers and White （1973）, and Toffaleti （1969）. These results are similar to those made by ASCE （1982） based on laboratory and field data not used in this paper. Study results also show that the formulas based on physical laws of sediment transport, like those formulas that were developed based on power concept, are more accurate than other formulas for estimating total bed material sediment load in rivers.     

Ecological water quality analysis of the Guayas river basin (Ecuador) based on macroinvertebrates indices

The Guayas river basin is one of the major watersheds in Ecuador, where increasing human activities are affecting water quality and related ecosystem services. The aims of this study were (1) to assess the ecological water quality based on macroinvertebrate indices and (2) to determine the major environmental variables affecting these macroinvertebrate indices. To do so, we performed an integrated water quality assessment at 120 locations within the river basin. Biological and physical–chemical data were collected to analyze the water quality. Two biotic indices were calculated to assess the water quality with an ecological approach: the Biological Monitoring Working Party Colombia (BMWP-Col) and the Neotropical Low-land Stream Multimetric Index (NLSMI). Both the BMWP-Col and NLSMI indicated good water quality at the (upstream) forested locations, lower water quality for sites situated at arable land and bad water quality at residential areas. Both indices gave relevant assessment outcomes and can be considered valuable for supporting the local water management. A correspondence analysis (CA) applied on both indices suggested that flow velocity, chlorophyll concentration, conductivity, land use, sludge layer and sediment type were the major environmental variables determining the ecological water quality. We also suggested that nutrient and pesticide measurements are important to study water quality in the area where intensive agriculture activities take place. The nutrient levels detected in agricultural areas were relatively low and illustrated that the types of crops and the current cultivation methods were not leading to eutrophication. The applied methods and results of this study can be used to support the future water management of the Guayas river basin and similar basins situated in the tropics.     

Impurity effect on clear water evaporation: toward modelling wastewater evaporation using ANN,ANFIS-SC and GEP techniques

The growing shortage of freshwater resources and increasing environmental awareness give rise to the use of treated wastewater as an alternative resource for water supply. Accurate estimation of wastewater evaporation (WWE), as the main cause of water losses, is necessary for proper water resources management. Unfortunately, few studies have focused on modelling WWE despite its vital importance. This study investigates the ability of gene expression programming (GEP), adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANN) techniques to estimate WWE as a function of variables including wastewater properties, clear water evaporation and climatic factors. The study uses measured data from an experiment conducted in Neishaboor municipal wastewater treatment plant, Iran. Results indicate that the ANN model is superior among the three methods, and also demonstrates higher accuracy when compared with those of a dimensional analysis model using the F-test statistic.     

Pumping optimization of coastal aquifers based on evolutionary algorithms and surrogate modular neural network models

Pumping optimization of coastal aquifers involves complex numerical models. In problems with many decision variables, the computational burden for reaching the optimal solution can be excessive. Artificial Neural Networks (ANN) are flexible function approximators and have been used as surrogate models of complex numerical models in groundwater optimization. However, this approach is not practical in cases where the number of decision variables is large, because the required neural network structure can be very complex and difficult to train. The present study develops an optimization method based on modular neural networks, in which several small subnetwork modules, trained using a fast adaptive procedure, cooperate to solve a complex pumping optimization problem with many decision variables. The method utilizes the fact that salinity distribution in the aquifer, depends more on pumping from nearby wells rather than from distant ones. Each subnetwork predicts salinity in only one monitoring well, and is controlled by relatively few pumping wells falling within certain control distance from the monitoring well. While the initial control area is radial, its shape is adaptively improved using a Hermite interpolation procedure. The modular neural subnetworks are trained adaptively during optimization, and it is possible to retrain only the ones not performing well. As optimization progresses, the subnetworks are adapted to maximize performance near the current search space of the optimization algorithm. The modular neural subnetwork models are combined with an efficient optimization algorithm and are applied to a real coastal aquifer in the Greek island of Santorini. The numerical code SEAWAT was selected for solving the partial differential equations of flow and density dependent transport. The decision variables correspond to pumping rates from 34 wells. The modular subnetwork implementation resulted in significant reduction in CPU time and identified an even better solution than the original numerical model.     

Artificial neural network application to estimate kinematic soil pile interaction response parameters

Six artificial neural network (ANN) models are developed to predict various response parameters of kinematic soil pile interaction. These responses include (1) kinematic response factors for free and fixed head piles in homogenous soil layer to derive foundation input motion (2) normalized bending moment at fixed head of pile in homogenous soil layer (3) normalized kinematic pile moment at the interface of two soil layers of sharply different soil stiffnesses. These ANN models represent simple solutions that can be implemented in a simple calculator capable of matrix operation and bypass the site response analysis and the complex wave diffraction analysis. The data required for ANN training is generated using beam on dynamic Winkler formulation (BDWF). Fifty percent of the data is used to train the ANN models while remaining 50% is used to test the ANN models. The trained ANN models show good agreement with BDWF results.     

A bioindicator system for water quality on inshore coral reefs of the Great Barrier Reef

Responses of bioindicator candidates for water quality were quantified in two studies on inshore coral reefs of the Great Barrier Reef (GBR). In Study 1, 33 of the 38 investigated candidate indicators (including coral physiology, benthos composition, coral recruitment, macrobioeroder densities and FORAM index) showed significant relationships with a composite index of 13 water quality variables. These relationships were confirmed in Study 2 along four other water quality gradients (turbidity and chlorophyll). Changes in water quality led to multi-faceted shifts from phototrophic to heterotrophic benthic communities, and from diverse coral dominated communities to low-diversity communities dominated by macroalgae. Turbidity was the best predictor of biota; hence turbidity measurements remain essential to directly monitor water quality on the GBR, potentially complemented by our final calibrated 12 bioindicators. In combination, this bioindicator system may be used to assess changes in water quality, especially where direct water quality data are unavailable.     

Internet-based applications for interrogating 50 years of data from the South African national water quality monitoring network

ABSTRACT

National and regional water quality monitoring networks have been operated in South Africa since the early 1970s. These originally had text-based inventories that were convenient for specialists who were familiar with the national networks and knew the locations of their sites of interest. However, within two decades the networks had expanded in geographical extent and variables monitored to such an extent that users needed spatial context in order to locate sites that fitted their information requirements. Mapping applications running on the Internet, such as Google Earth and Leaflet, form the foundation of a system for providing online inventories and summaries of the data available on the water quality database. The interfaces were constructed using available software, mainly ArcInfo and R. A recent concern is a decrease in the collection of water quality data, which is reducing the value of data summaries for water resource management.     

Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization

Abstract

Artificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020.

Editor Z.W. Kundzewicz; Associate editor L. See

Citation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005     

Performance of intertidal topography video monitoring of a meso-tidal reflective beach in South Portugal

This study discusses site-specific system optimization efforts related to the capability of a coastal video station to monitor intertidal topography. The system consists of two video cameras connected to a PC, and is operating at the meso-tidal, reflective Faro Beach (Algarve coast, S. Portugal). Measurements from the period February 4, 2009 to May 30, 2010 are discussed in this study. Shoreline detection was based on the processing of variance images, considering pixel intensity thresholds for feature extraction, provided by a specially trained artificial neural network (ANN). The obtained shoreline data return rate was 83%, with an average horizontal cross-shore root mean square error (RMSE) of 1.06 m. Several empirical parameterizations and ANN models were tested to estimate the elevations of shoreline contours, using wave and tidal data. Using a manually validated shoreline set, the lowest RMSE (0.18 m) for the vertical elevation was obtained using an ANN while empirical parameterizations based on the tidal elevation and wave run-up height resulted in an RMSE of 0.26 m. These errors were reduced to 0.22 m after applying 3-D data filtering and interpolation of the topographic information generated for each tidal cycle. Average beach-face slope tan(β) RMSE were around 0.02. Tests for a 5-month period of fully automated operation applying the ANN model resulted in an optimal, average, vertical elevation RMSE of 0.22 m, obtained using a one tidal cycle time window and a time-varying beach-face slope. The findings indicate that the use of an ANN in such systems has considerable potential, especially for sites where long-term field data allow efficient training.     

Comparing the stream re-aeration coefficient estimated from ANN and empirical models / Comparaison d'estimations par un RNA et par des modèles empiriques du coefficient de réaération en cours d'eau

Abstract

Dissolved oxygen (DO) is one of the most useful indices of river's health and the stream re-aeration coefficient is an important input to computations related to DO. Normally, this coefficient is expressed as a function of several variables, such as mean stream velocity, shear stress velocity, bed slope, flow depth, and Froude number. However, in free surface flows, some of these variables are interrelated, and it is possible to obtain simplified stream re-aeration equations. In recent years, different functional forms have been advanced to represent the re-aeration coefficient for different data sets. In the present study, the artificial neural network (ANN) technique has been applied to estimate the re-aeration coefficient (K ₂) using data sets measured at different reaches of the Kali River in India and values obtained from the literature. Observed stream/channel velocity, bed slope, flow depth, cross-sectional area and re-aeration coefficient data were used for the analysis. Different combinations of variables were tested to obtain the re-aeration coefficient using an ANN. The performance of the ANN was compared with other estimation methods. It was found that the re-aeration coefficient estimated by using an ANN was much closer to the observed values as compared with the other techniques.     

Data-Worth Assessment for a Three-Dimensional Optimal Design in Nonlinear Groundwater Systems

Groundwater model predictions are often uncertain due to inherent uncertainties in model input data. Monitored field data are commonly used to assess the performance of a model and reduce its prediction uncertainty. Given the high cost of data collection, it is imperative to identify the minimum number of required observation wells and to define the optimal locations of sampling points in space and depth. This study proposes a design methodology to optimize the number and location of additional observation wells that will effectively measure multiple hydrogeological parameters at different depths. For this purpose, we incorporated Bayesian model averaging and genetic algorithms into a linear data-worth analysis in order to conduct a three-dimensional location search for new sampling locations. We evaluated the methodology by applying it along a heterogeneous coastal aquifer with limited hydrogeological data that is experiencing salt water intrusion (SWI). The aim of the model was to identify the best locations for sampling head and salinity data, while reducing uncertainty when predicting multiple variables of SWI. The resulting optimal locations for new observation wells varied with the defined design constraints. The optimal design (OD) depended on the ratio of the start-up cost of the monitoring program and the installation cost of the first observation well. The proposed methodology can contribute toward reducing the uncertainties associated with predicting multiple variables in a groundwater system.     

Field Measurements and Numerical Simulations of the 2004 Tsunami Impact on the East Coast of Sri Lanka

This paper employs a numerical model of tsunami propagation together with documented observations and field measurements of the evidence left behind by the tsunami in December 2004, to identify and interpret the factors that have contributed to the significant spatial variability of the level of tsunami impact along the coastal belt of the eastern province of Sri Lanka. The model results considered in the present analysis include the distribution of the amplitude of the tsunami and the pattern of wave propagation over the continental shelf off the east coast, while the field data examined comprise the maximum water levels measured at or near the shoreline, the horizontal inundation distances and the number of housing and other buildings damaged. The computed maximum amplitude of the tsunami at water points nearest the shoreline along the east coast shows considerable variation ranging from 2.2 m to 11.4 m with a mean value of 5.7 m; moreover, the computed amplitudes agree well with the available field measurements. We also show that the shelf bathymetry off the east coast, particularly the submarine canyons at several locations, significantly influences the near-shore transformation of tsunami waves, and consequently, the spatial variation of the maximum water levels along the coastline. The measured values of inundation also show significant variation along the east coast and range from 70 m to 4560 m with a median value of 700 m. Our analyses of field data also show the dominant influence of the coastal topography and geomorphology on the extent of tsunami inundation. Furthermore, the measured inundation distances indicate no apparent correlation with the computed tsunami heights at the respective locations. We also show that both the computed tsunami heights and the measured inundation distances for the east coast closely follow the log-normal statistical distribution.     

Comparative study of fuzzy evidential reasoning and fuzzy rule-based approaches: an illustration for water quality assessment in distribution networks

This paper presents the use of two multi-criteria decision-making (MCDM) frameworks based on hierarchical fuzzy inference engines for the purpose of assessing drinking water quality in distribution networks. Incommensurable and uncertain water quality parameters (WQPs) at various sampling locations of the water distribution network (WDN) are monitored. Two classes of WQPs including microbial and physicochemical parameters are considered. Partial, incomplete and subjective information on WQPs introduce uncertainty to the water quality assessment process. Likewise, conflicting WQPs result in a partially reliable assessment of the quality associated with drinking water. The proposed methodology is based on two hierarchical inference engines tuned using historical data on WQPs in the WDN and expert knowledge. Each inference engine acts as a decision-making agent specialized in assessing one aspect of quality associated with drinking water. The MCDM frameworks were developed to assess the microbial and physicochemical aspects of water quality assessment. The MCDM frameworks are based on either fuzzy evidential or fuzzy rule-based inference. Both frameworks can interpret and communicate the relative quality associated with drinking water, while the second is superior in capturing the nonlinear relationships between the WQPs and estimated water quality. More comprehensive rules will have to be generated prior to reliable water quality assessment in real-case situations. The examples presented here serve to demonstrate the proposed frameworks. Both frameworks were tested through historical data available for a WDN, and a comparison was made based on their performance in assessing levels of water quality at various sampling locations of the network.     

Polychlorinated biphenyls in the Mediterranean Sea

Although concentrations of polychlorinated biphenyls (PCBs) in biota, sediment and water of the Mediterranean Sea have been determined, most available data are for samples collected within the narrow coastal zone at relatively few locations. PCB concentrations in samples from the open Mediterranean Sea have not previously been reported. We report here the concentrations of PCBs in surface and sub-surface water from 36 locations. Analysis of our data indicate that there may be some correlation between PCB concentration in Mediterranean seawater and certain demographic and oceanographic features of the region.