The bacterial strain MJ01 was isolated from stock tank water of one of the Iranian south oil field production facilities. The 16S rRNA gene of isolate, MJ01, showed 99% similarity to Bacillus subtilis. The results revealed that biosurfactant produced by this strain was lipopeptide-like surfactin based on FTIR analysis. Critical micelle concentration of produced surfactin in distilled water was 0.06 g/l. Wettability study showed that at zero salinity surfactin can change original oil-wet state to water-wet state, but in seawater salinity it cannot modify the wettability significantly. To utilize this biosurfactant in ex situ MEOR process, economical and reservoir engineering technical parameters were considered to introduce a new optimization strategy using the response surface methodology. Comparing the result of this optimization strategy with the previous optimization research works was shown that significant save in use of nutrients is possible by using this medium. Furthermore, using this method leads to less formation damage due to the incompatibility of injecting fluid and formation brine, and less formation damage due to the bioplugging.

Three models were developed to estimate the potential of the selected bacteria Petrotoga sp., a thermophilic anaerobic oil‐degrading microorganism. Fourteen data sets of these bacteria were simulated by a multilayer feed‐forward neural network and an adaptive neuro‐fuzzy interference system. Twelve data sets served for training and two for testing these models. A simplified numerical model was performed assuming two phases in the growth process of oil‐degrading microorganisms, the logarithmic growth phase and the death phase. Comparison between these models in predicting bacterial cell concentration for different data sets indicates little difference between the overall average relative errors of the three methods and that all can be applied for prediction. Effects of salinity concentration, amount of yeast extract, and temperature on bacterial cell concentration were simulated by numerical and neural network models.

No abstract