Prediction of Ground Water Levels in the Uplands of a Tropical Coastal Riparian Wetland using Artificial Neural Networks

Artificial Neural Networks (ANNs) have been found to be a robust tool to model many non-linear hydrological processes. The present study aims at evaluating the performance of ANN in simulating and predicting ground water levels in the uplands of a tropical coastal riparian wetland. The study involves comparison of two network architectures, Feed Forward Neural Network (FFNN) and Recurrent Neural Network (RNN) trained under five algorithms namely Levenberg Marquardt algorithm, Resilient Back propagation algorithm, BFGS Quasi Newton algorithm, Scaled Conjugate Gradient algorithm, and Fletcher Reeves Conjugate Gradient algorithm by simulating the water levels in a well in the study area. The study is analyzed in two cases-one with four inputs to the networks and two with eight inputs to the networks. The two networks-five algorithms in both the cases are compared to determine the best performing combination that could simulate and predict the process satisfactorily. Ad Hoc (Trial and Error) method is followed in optimizing network structure in all cases. On the whole, it is noticed from the results that the Artificial Neural Networks have simulated and predicted the water levels in the well with fair accuracy. This is evident from low values of Normalized Root Mean Square Error and Relative Root Mean Square Error and high values of Nash-Sutcliffe Efficiency Index and Correlation Coefficient (which are taken as the performance measures to calibrate the networks) calculated after the analysis. On comparison of ground water levels predicted with those at the observation well, FFNN trained with Fletcher Reeves Conjugate Gradient algorithm taken four inputs has outperformed all other combinations.

Surface chemical characterisation of Paenibacillus polymyxa before and after adaptation to sulfide minerals

A heterotroph Paenibacillus polymyxa bacteria is adapted to pyrite, chalcopyrite, galena and sphalerite minerals by repeated subculturing the bacteria in the presence of the mineral until their growth characteristics became similar to the growth in the absence of mineral. The unadapted and adapted bacterial surface have been chemically characterised by zeta-potential, contact angle, adherence to hydrocarbons and FT-IR spectroscopic studies. The surface free energies of bacteria have been calculated by following the equation of state and surface tension component approaches. The aim of the present paper is to understand the changes in surface chemical properties of bacteria during adaptation to sulfide minerals and the projected consequences in bioflotation and bioflocculation processes. The mineral-adapted cells became more hydrophilic as compared to unadapted cells. There are no significant changes in the surface charge of bacteria before and after adaptation, and all the bacteria exhibit an iso-electric point below pH 2.5. The contact angles are observed to be more reliable for hydrophobicity assessment than the adherence to hydrocarbons. The Lifschitz–van der Waals/acid–base approach to calculate surface free energy is found to be relevant for mineral–bacteria interactions. The diffuse reflectance FT-IR absorbance bands for all the bacteria are the same illustrating similar surface chemical composition. However, the intensity of the bands for unadapted and adapted cells is significantly varied and this is due to different amounts of bacterial secretions underlying different growth conditions.