Neural network prediction of nitrate in groundwater of Harran Plain, Turkey

Monitoring groundwater quality by cost-effective techniques is important as the aquifers are vulnerable to contamination from the uncontrolled discharge of sewage, agricultural and industrial activities. Faulty planning and mismanagement of irrigation schemes are the principle reasons of groundwater quality deterioration. This study presents an artificial neural network (ANN) model predicting concentration of nitrate, the most common pollutant in shallow aquifers, in groundwater of Harran Plain. The samples from 24 observation wells were monthly analysed for 1 year. Nitrate was found in almost all groundwater samples to be significantly above the maximum allowable concentration of 50 mg/L, probably due to the excessive use of artificial fertilizers in intensive agricultural activities. Easily measurable parameters such as temperature, electrical conductivity, groundwater level and pH were used as input parameters in the ANN-based nitrate prediction. The best back-propagation (BP) algorithm and neuron numbers were determined for optimization of the model architecture. The Levenberg–Marquardt algorithm was selected as the best of 12 BP algorithms and optimal neuron number was determined as 25. The model tracked the experimental data very closely (R = 0.93). Hence, it is possible to manage groundwater resources in a more cost-effective and easier way with the proposed model application.     

Fluid flow equations governing primary oil migration as a separate phase

A mathematical model of primary oil migration as a separate phase out of compacting shales is presented. During burial and oil generation, source rock porosity decreases and oil saturation increases until residual oil saturation is reached. At this stage oil is expelled out by capillary and excess fluid pressure gradients. The model is a system of differential equations which relate changes in oil and water saturation in time to water and oil flow out of the source rock during burial. An additional set of equations for periods of erosion of overburden are also provided. The equations can be numerically solved by finite difference method. If oil and water flow is to be simulated during oil generation, then at each time step, changes by oil generation in oil and water saturations and porosity must be calculated. The solution procedure is briefly outlined.     

Development of a new rubber seismic isolator: ‘Ball Rubber Bearing (BRB)’

This paper presents an experimental research aimed at developing a new rubber‐based seismic isolator called ‘Ball Rubber Bearing (BRB)’. The BRB is composed of a conventional steel‐reinforced multi‐layered rubber bearing with its central hole filled with small diameter steel balls that are used to provide energy dissipation capacity through friction. A large set of BRBs with different geometrical and material properties are manufactured and tested under reversed cyclic horizontal loading at different vertical compressive load levels. Extensive test results indicate that steel balls do not only increase the energy dissipation capacity of the elastomeric bearing (EB), but also increase its horizontal and vertical stiffness. It is also observed that the energy dissipation capacity of a BRB does not degrade as the number of loading cycles increases. Copyright © 2011 John Wiley & Sons, Ltd.     

Analyzing radar rainfall estimate errors with three vector norms: application to weather radar rainfall data in Muğla,Turkey

Theoretical and Applied Climatology - Over the past several decades, weather radar has become an indispensable tool in flood forecasting studies, especially in ungauged regions. However, the...