Optimization Techniques with FORTRAN

Over the past 15 years, artificial neural networks (ANNs) have been used increasingly for prediction and forecasting in water resources and environmental engineering. However, despite this high level of research activity, methods for developing ANN models are not yet well established. In this paper, the steps in the development of ANN models are outlined and taxonomies of approaches are introduced for each of these steps. In order to obtain a snapshot of current practice, ANN development methods are assessed based on these taxonomies for 210 journal papers that were published from 1999 to 2007 and focus on the prediction of water resource variables in river systems. The results obtained indicate that the vast majority of studies focus on flow prediction, with very few applications to water quality. Methods used for determining model inputs, appropriate data subsets and the best model structure are generally obtained in an ad-hoc fashion and require further attention. Although multilayer perceptrons are still the most popular model architecture, other model architectures are also used extensively. In relation to model calibration, gradient based methods are used almost exclusively. In conclusion, despite a significant amount of research activity on the use of ANNs for prediction and forecasting of water resources variables in river systems, little of this is focused on methodological issues. Consequently, there is still a need for the development of robust ANN model development approaches.

Review: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

Participants are requested to register and obtain meeting badges at the registration counter, located on the ground floor, UNCC, from 08:30 hours to 09:00 hours on the event day. Participants who are not able to register during the time indicated above are requested to do so upon their arrival at UNCC before going to the conference room. Only the names of duly registered participants will be included in the list of participants.

/pdf/economic-and-social-commission-for-asia-and-the-pacific-1cgptjifai.pdf

Economic and social commission for asia and the pacific

This paper presents a survey of simulation and optimization modeling approaches used in reservoir systems operation problems. Optimization methods have been proved of much importance when used with simulation modeling and the two approaches when combined give the best results. The main objective of this review article is to discuss simulation, optimization and combined simulation–optimization modeling approach and to provide an overview of their applications reported in literature. In addition to classical optimization techniques, application and scope of computational intelligence techniques, such as, evolutionary computations, fuzzy set theory and artificial neural networks, in reservoir system operation studies are reviewed. Conclusions and suggestive remarks based on this survey are outlined, which could be helpful for future research and for system managers to decide appropriate methodology for application to their systems.

/pdf/simulation-optimization-modeling-a-survey-and-potential-1xvkgabzfk.pdf

Simulation-optimization modeling: a survey and potential application in reservoir systems operation.

Flood hazard risk assessment model based on random forest

Flood hazard and risk assessment was conducted to identify the priority areas in the southwest region of Bangladesh for flood mitigation. Simulation of flood flow through the Gorai and Arial Khan river system and its floodplains was done by using a hydrodynamic model. After model calibration and verification, the model was used to simulate the flood flow of 100-year return period for a duration of four months. The maximum flooding depths at different locations in the rivers and floodplains were determined. The process in determining long flooding durations at every grid point in the hydrodynamic model is laborious and time-consuming. Therefore the flood durations were determined by using satellite images of the observed flood in 1988, which has a return period close to 100 years. Flood hazard assessment was done considering flooding depth and duration. By dividing the study area into smaller land units for hazard assessment, the hazard index and the hazard factor for each land unit for depth and duration of flooding were determined. From the hazard factors of the land units, a flood hazard map, which indicates the locations of different categories of hazard zones, was developed. It was found that 54% of the study area was in the medium hazard zone, 26% in the higher hazard zone and 20% in the lower hazard zone. Due to lack of sufficient flood damage data, flood damage vulnerability is simply considered proportional to population density. The flood risk factor of each land unit was determined as the product of the flood hazard factor and the vulnerability factor. Knowing the flood risk factors for the land units, a flood risk map was developed based on the risk factors. These maps are very useful for the inhabitants and floodplain management authorities to minimize flood damage and loss of human lives. Copyright  2005 John Wiley & Sons, Ltd.

Flood hazard and risk analysis in the southwest region of Bangladesh

The depth-averaged velocity and bottom shear stress distributions in a rectangular channel near a groyne are computed by using a 2-D depth averaged model. The model uses a hybrid finite difference scheme and an iterative method to solve the governing equations of flow and turbulence transport. Due to streamline curvature effects in the region near the groyne tip, a correction factor is incorporated into the \Ik\N=ϵ\N turbulence model that significantly improves the agreement between the computed and experimental data of the velocities and of the streamline pattern compared to previous numerical methods. In this region the bottom shear stress is found to be largely influenced by the 3-D effects. A 3-D correction factor is introduced which considerably improves the computed bottom shear stresses. Sensitivity analysis is made on the \Ik\N=ϵ\N model coefficients and on the correction factors of the streamline curvature and the 3-D effects. The experimental errors in the velocity and bottom shear stress measurements are analyzed. The average errors between the computed and previous experimental results are presented with confidence intervals.

2‐D Depth‐Averaged Flow Computation near Groyne

In this study, the existing self-cleansing design criteria for sewers based on minimum velocity and minimum bed shear stress have been reviewed. Based on several laboratory experiments, the study then develops non-deposition criteria for non-cohesive sediment in uniform flow. The developed criteria take into account geometry of flow sections, hydraulic and sediment properties based upon three dimensionless parameters, namely, the densimetric Froude number, the volumetric sediment concentration and the relative grain size. The proposed criteria provide improved estimates of self-cleansing minimum velocities compared to the traditional one-parameter design criteria and agree well with the well-known existing design criteria, namely, Macke's formula for suspended load and May's formula for bed load. The present study therefore contributes new non-deposition design criteria for sewers with part-full flow in the range of the experiment conducted and yet which are simple for practical applications. Further rese...

Non-deposition design criteria for sewers with part-full flow

Two lumped conceptual hydrological models, namely tank and NAM and a neural network model are applied to flood forecasting in two river basins in Thailand, the Wichianburi on the Pasak River and the Tha Wang Pha on the Nan River using the flood forecasting procedure developed in this study. The tank and NAM models were calibrated and verified and found to give similar results. The results were found to improve significantly by coupling stochastic and deterministic models (tank and NAM) for updating forecast output. The neural network (NN) model was compared with the tank and NAM models. The NN model does not require knowledge of catchment characteristics and internal hydrological processes. The training process or calibration is relatively simple and less time consuming compared with the extensive calibration effort required by the tank and NAM models. The NN model gives good forecasts based on available rainfall, evaporation and runoff data. The black-box nature of the NN model and the need for selecting parameters based on trial and error or rule-of-thumb, however, characterizes its inherent weakness. The performance of the three models was evaluated statistically. Copyright © 2000 John Wiley & Sons, Ltd.

Application of tank, NAM, ARMA and neural network models to flood forecasting

A one-dimensional numerical model for dam failure due to flow overtopping is developed. The MacCormack explicit finite difference scheme is used to solve the one-dimensional equations of continuity and momentum for unsteady varied flow over steep bed slopes. In the computation of erosion process, sediment transport equations are considered and the modified Smart formula developed for steep bed slope is selected. The sliding stability of the overtopped dam is checked by modified ordinary method of slices. The model has been successfully calibrated and verified using laboratory experimental data. By comparing with the experimental results, it was found that the model accuracy depends largely on the sediment transport formula and pore water pressure coefficient. The model was found to predict actual breach outflow of the Buffalo Creek Dam reasonably well and closer than other existing numerical models.

Tawatchai Tingsanchali

Papers

Flood hazard and risk analysis in the southwest region of Bangladesh

2‐D Depth‐Averaged Flow Computation near Groyne

Non-deposition design criteria for sewers with part-full flow

Application of tank, NAM, ARMA and neural network models to flood forecasting

Numerical modelling of dam failure due to flow overtopping