Zulfiqar Ahmad

Comparative efficacy of ANN and ANFIS models in estimating biosurfactant production produced by Klebseilla sp. FKOD36

Optimization of environmental and medium parameters is an important step for bioprocess engineering. In the present study, the efficacies of Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were compared for their utility in estimating biosurfactant production, surface tension reduction, and emulsification under different environmental and medium parameters. Biosurfactant was collected from the bacterial isolate FKOD36. In these models, temperature, pH, incubation period, carbon, nitrogen, and hydrocarbon sources were used as input variables, whereas surface tension reduction, emulsification index, and biosurfactant production were the dependent output variables. Models were trained for six inputs and three ANFIS sub-networks were developed for each output. Each of three ANFIS models was then used to predict one of the three outputs. The performance indices of both ANN and ANFIS illustrate that proposed ANFIS network produced better results with coefficient of determination (R2) values ranging from 0.96 to 0.99 for the training dataset and 0.90–0.99 for the validation dataset as compared to ANN which had R2 values of 0.95–0.99 for the training set and 0.89–0.98 testing set. Based on the results, the multilayer ANFIS model with its fuzzy application rules proved to give better prediction results than the ANN model.

Salt-Induced Variations in Physiological Parameters and Nutrient Concentrations of Two Wheat Cultivars

Two wheat cultivars, Pasban-90 and Sehr-2006, were screened and sown under different levels of sodium chloride (NaCl) concentrations, following the factorial design with four replications, to evaluate the effects of salinity and stress duration on growth of seedling, photosynthetic productivity, and ion contents. Leaf chlorophyll and relative growth rate were determined after an interval of a week while other parameters were determined 25 days after treatment. The two cultivars differed significantly for all the parameters measured at 200 mM NaCl. The lowest concentration of NaCl (50 mM) decreased total leaf area up to 19 and 29% and dry weight by 55 and 63% in Pasban-90 and Sehr-2006, respectively. Salinity concentrations increased sodium (Na) and calcium (Ca) concentrations in tissues. The results of the study indicate great variation for salinity tolerance in two cultivars and greater photosynthetic capacity, comparatively low tissue Na accumulation at high salt levels, and greater relative growth rate. These results are related with the capacity of wheat to salt tolerance.

Soil microbial dynamics prediction using machine learning regression methods

Abstract Soil microbial dynamics is significant for the soil productivity. The present study explores the application of machine learning based regression methods in the prediction of selected soil microbial dynamics, including bacterial population (BP), phosphate solubilization (PS), and enzyme activities. An experiment was designed in a salt medium with rock phosphate inoculated with the solubilizing microorganism to measure the PS, BP, and 1-Aminocyclopropane-1-carboxylate (ACC) deaminase activity at a different temperature, pH, and incubation period. The artificial neural network (ANN), support vector regression (SVR), Wang and Mendel’s (WM) - fuzzy inference systems (FIS), and subtractive clustering (SC)-FIS methods have been applied in the estimation of PS, BP, and ACC deaminase activity using the experimental conditions. The performance of four regression methods has been evaluated in the terms of the coefficient of determination (R2), root mean square error (RMSE), and correlation coefficient (ρ). The SC-FIS method has better performance than the rest three methods in the prediction of each of the soil microbial dynamics (R2 of 0.99 in the prediction of PS).