Use of artificial neural networks as explicit finite difference operators

Results of a numerical exercise, substituting a numerical operator by an artificial neural network (ANN) are presented in this paper. The numerical operator used is the explicit form of the finite difference (FD) scheme. The FD scheme was used to discretize the one-dimensional transport equation, which included both the advection and dispersion terms. Inputs to the ANN are the FD representation of the transport equation, and the concentration was designated as the output. Concentration values used for training the ANN were obtained from analytical solutions. The numerical operator was reconstructed from a back calculation of the weights of the ANN. Linear transfer functions were used for this purpose. The ANN was able to accurately recover the velocity used in the training data, but not the dispersion coefficient. This capability was improved when numerical dispersion was taken into account; however, it is limited to the condition: C/P<0.5 , where C is the Courant number and P , the Peclet number (i.e., the restriction imposed by the Neumann stability condition).

Improved particle swarm optimization-based artificial neural network for rainfall-runoff modeling

This paper presents the application of an improved particle swarm optimization (PSO) technique for training an artificial neural network (ANN) to predict water levels for the Heshui watershed, China. Daily values of rainfall and water levels from 1988 to 2000 were first analyzed using ANNs trained with the conjugate-gradient, gradient descent and Levenberg-Marquardt neural network (LM-NN) algorithms. The best results were obtained from LM-NN and these results were then compared with those from PSO-based ANNs, including conventional PSO neural network (CPSONN) and improved PSO neural network (IPSONN) with passive congregation. The IPSONN algorithm improves PSO convergence by using the selfish herd concept in swarm behavior. Our results show that the PSO-based ANNs performed better than LM-NN. For models run using a single parameter (rainfall) as input, the root mean square error (RMSE) of the testing dataset for IPSONN was the lowest (0.152 m) compared to those for CPSONN (0.161 m) and LM-NN (0.205 m). For multi-parameter (rainfall and water level) inputs, the RMSE of the testing dataset for IPSONN was also the lowest (0.089 m) compared to those for CPSONN (0.105 m) and LM-NN (0.145 m). The results also indicate that the LM-NN model performed poorly in predicting the low and peak water levels, in comparison to the PSO-based ANNs. Moreover, the IPSONN model was superior to CPSONN in predicting extreme water levels. Lastly, IPSONN had a quicker convergence rate compared to CPSONN.

Comparison between response surface models and artificial neural networks in hydrologic forecasting

Developing an efficient and accurate hydrologic forecasting model is crucial to managing water resources and flooding issues. In this study, response surface (RS) models including multiple linear regression (MLR), quadratic response surface (QRS), and nonlinear response surface (NRS) were applied to daily runoff (e.g., discharge and water level) prediction. Two catchments, one in southeast China and the other in western Canada, were used to demonstrate the applicability of the proposed models. Their performances were compared with artificial neural network (ANN) models, trained with the learning algorithms of the gradient descent with adaptive learning rate (ANN-GDA) and Levenberg-Marquardt (ANN-LM). The performances of both RS and ANN in relation to the lags used in the input data, the length of the training samples, long-term (monthly and yearly) predictions, and peak value predictions were also analyzed. The results indicate that the QRS and NRS were able to obtain equally good performance in runoff prediction, as compared with ANN-GDA and ANN-LM, but require lower computational efforts. The RS models bring practical benefits in their application to hydrologic forecasting, particularly in the cases of short-term flood forecasting (e.g., hourly) due to fast training capability, and could be considered as an alternative to ANN

DOC and UVA attenuation with soil aquifer treatment in the saturated zone of an artificial coastal sandfill

Results from a direct recharge experiment conducted in the field to investigate DOC and UVA(254) attenuation rates during the direct injection of UF treated wastewater into a artificial coastal sandfill are presented in this paper. Approximately 500 m(3) of ultra-filtered wastewater was injected into the saturated zone, over a period of 9 days. The movement of the plume was tracked over 80 days, during which time samples were obtained from multilevel samplers installed in transects across the drift axis of the plume. An analysis of fluorescein in the samples obtained during the drift of the UF plume showed that DOC and UVA were attenuated beyond rates predicted by conservative mixing, by up to a maximum of 45%. A degradation coefficient of 0.0175 day(-1) was found to be applicable for DOC degradation. After a drift period of 80 days, DOC and UVA reduced to approximately 4.5 mg/l and 0.100 cm(-1), respectively, from initial values of 8.06 mg/l and 0.199 cm(-1).

Three algorithms for learning artificial neural network: A comparison for induction motor flux estimation

This paper presents a comparative study of three algorithms for learning artificial neural network. As neural estimator, back-propagation (BP) algorithm, uncorrelated real time recurrent learning (URTRL) algorithm and correlated real time recurrent learning (CRTRL) algorithm are used in the present work to learn the artificial neural network (ANN). The approach proposed here is based on the flux estimation of high performance induction motor drives. Simulation of the drive system was carried out to study the performance of the motor drive. It is observed that the proposed CRTRL algorithm based methodology provides better performance than the BP and URTRL algorithm based technique. The proposed method can be used for accurate measurement of the rotor flux.

Formations of robotic swarm: an artificial force based approach

Cooperative control of multiple mobile robots is an attractive and challenging problem which has drawn considerable attention in the recent past. This paper introduces a scalable decentralized control algorithm to navigate a group of mobile robots (swarm) into a predefined shape in 2D space. The proposed architecture uses artificial forces to control mobile agents into the shape and spread them inside the shape while avoiding intermember collisions. The theoretical analysis of the swarm behavior describes the motion of the complete swarm and individual members in relevant situations. We use computer simulated case studies to verify the theoretical assertions and to demonstrate the robustness of the swarm under external disturbances such as death of agents, change of shape etc. Also the performance of the proposed distributed swarm control architecture was investigated in the presence of realistic implementation issues such as localization errors, communication range limitations, boundedness of forces etc.

Rigs-to-reefs: Will the deep sea benefit from artificial habitat?

As a peak in the global number of offshore oil rigs requiring decommissioning approaches, there is growing pressure for the implementation of a "rigs-to-reefs" program in the deep sea, whereby obsolete rigs are converted into artificial reefs. Such decommissioned rigs could enhance biological productivity, improve ecological connectivity, and facilitate conservation/restoration of deep-sea benthos (eg cold-water corals) by restricting access to fishing trawlers. Preliminary evidence indicates that decommissioned rigs in shallower waters can also help rebuild declining fish stocks. Conversely, potential negative impacts include physical damage to existing benthic habitats within the "drop zone", undesired changes in marine food webs, facilitation of the spread of invasive species, and release of contaminants as rigs corrode. We discuss key areas for future research and suggest alternatives to offset or minimize negative impacts. Overall, a rigs-to-reefs program may be a valid option for deep-sea benthic conservation. © The Ecological Society of America.

An improved Gbest guided artificial bee colony (IGGABC) algorithm for classification and prediction tasks

Artificial Neural Networks (ANN) performance depends on network topology, activation function, behaviors of data, suitable synapse's values and learning algorithms. Many existing works used different learning algorithms to train ANN for getting high performance. Artificial Bee Colony (ABC) algorithm is one of the latest successfully Swarm Intelligence based technique for training Multilayer Perceptron (MLP). Normally Gbest Guided Artificial Bee Colony (GGABC) algorithm has strong exploitation process for solving mathematical problems, however the poor exploration creates problems like slow convergence and trapping in local minima. In this paper, the Improved Gbest Guided Artificial Bee Colony (IGGABC) algorithm is proposed for finding global optima. The proposed IGGABC algorithm has strong exploitation and exploration processes. The experimental results show that IGGABC algorithm performs better than that standard GGABC, BP and ABC algorithms for Boolean data classification and time-series prediction tasks.