Development of Bio-Inspired- and Wavelet-Based Hybrid Models for Reconnaissance Drought Index Modeling

The present study aimed to model reconnaissance drought index (RDI) time series at three various time scales (i.e., RDI-6, RDI-9, RDI-12). Two weather stations located at Iran, namely Tehran and Dezful, were selected as the case study. First, support vector regression (SVR) was utilized as the standalone modeling technique. Then, hybrid models were implemented via coupling the standalone SVR with two bio-inspired-based techniques including firefly algorithm (FA) and whale optimization algorithm (WOA) as well as wavelet analysis (W). Accordingly, the hybrid SVR-FA, SVR-WOA, and W-SVR models were proposed. It is worth mentioning that six mother wavelets (i.e., Haar, Daubechies (db2, db4), Coifflet, Symlet, and Fejer-Korovkin) were employed in development of the hybrid W-SVR models. The performance of models was assessed through root mean square error (RMSE), mean absolute error (MAE), Willmott index (WI), and Nash-Sutcliffe efficiency (NSE). Generally, the implemented coupled models illustrated better results than the standalone SVR in modeling the RDI time series of studied locations. Besides, the Coifflet mother wavelet was found to be the best-performing wavelet. The most accurate results were achieved for RDI-12 modeling via the W-SVR utilizing db4(2) at Tehran station (RMSE = 0.253, MAE = 0.174, WI= 0.888, NSE = 0.934) and Coifflet(2) at Dezful station (RMSE = 0.301, MAE = 0.166, WI= 0.910, NSE = 0.936). As a result, the hybrid models developed in the current study, specifically W-SVR ones, can be proposed as suitable alternatives to the single SVR.

     

A regularization-based deep unsupervised model for affine multimodal co-registration

Extensive network receptive field is key for unsupervised affine registration because instead of deformable registration that takes care of local subtleties, the affine registration is global so that the last layers need to see big patches of the organ-in-interest. To extend the network's receptive field, we need to go for deeper networks, which causes producing complex models. On the other hand, affine transformation is restricted by its low degree-of-freedom (DoF) where larger models increasingly develop the hazard of overfitting. To worsen the situation, the regularizer module cannot be applied to the affine transformation with such a restricted DoF. In this paper, we propose a differentiable computational layer to convert the affine transformation outputted by the network to its corresponding dense displacement field. Such an affine-to-field layer enables us to apply different regularization terms on the outputted transformation in order to avoid the overfitting phenomenon while deepening the network. The proposed approach was evaluated on an annotated hard multimodal dataset containing 1109 pairs of CT/MR images of the brain with different heterogeneity for example, variety in scanners, setups and resolutions. Based on the results, the proposed customized layer is fully successful to handle the overfitting for deeper networks that are able to produce richer transformations than the shallower networks from different evaluation metrics for example, in target registration error the proposed network with seven layers has a 13.3% (or 9.1 mm) improvement in performance. The implementation of the proposed customized affine-to-field layer in the Python, Keras package with the Tensorflow backend can be publically accessed via https://github.com/boveiri/Deep-coReg .     

MODELLING OF TEMPERATURE EFFECTS ON THE PERFORMANCE OF REVERSE OSMOSIS MEMBRANES

This paper investigates the modeling of temperature effects on the performance of reverse osmosis membranes at the level of brackish-water concentrations. A new approach in modeling is employed in which the temperature dependencies of the physical properties of the system (such as diffusivity and viscosity) are taken into account and incorporated into the recently developed modified surface force-pore flow (MD-SF-PF) model. The dimensionless potential function in the model, which describes the solute-membrane interactions, is assumed to be temperature independent, which is justified based on an analogy to the interaction energy for the case of parallel flat plates. The three parameters in the model are determined at 25°C and 2000 ppm NaCI-water solution. Based on these parameters, the temperature-extended model predicts the performance of four thin-film composite, aromatic polyamide, FilmTec FT30 commercial membranes, in a temperature range of 5-60°C and a pressure range of 350-7000 kPa. The extended model truly predicts the performance of the membranes well. The compaction effect has no effect on the prediction of membrane separation and the ratio of solution flux to pure water flux. The compaction effect is modelled empirically which then allows the calculation of the absolute solution flux and pure water flux.     

Electromagnetic field analysis and calculation of the resonancecharacteristics of the loop-gap resonator

The electromagnetic field configuration of the loop-gap resonator is analyzed, and expressions for field distributions are derived. The method involves solving Maxwell's equations for the boundary conditions and matching the internal magnetic fields of the resonator to the evanescent fringing fields by a numerical fitting method. The expressions derived from this analysis are used in the derivation of equations for the resonant frequency and the quality factor of the resonator. The computed results are in good agreement with the measured values for resonant frequency and quality factors     

Growth and pigment production of Synechocystis sp. PCC 6803 under shear stress

Cyanobacteria, such as Synechocystis, have recently become attractive hosts for sustainable production of biofuels and bio-fixation of CO₂ due to their genetic tractability and relatively fast growth. Cultivation of cyanobacteria requires shear stress, which is generated by mixing and air bubbling. In the present work, the impact of shear stress caused by stirring and air bubbling on the growth and pigment production of Synechocystis sp. PCC 6803 is investigated. For this purpose, agitated and airlift bubble column photobioreactors were used. The results showed that the growth and yield production were improved by mixing the culture system. However, there is a limit to this improvement: In the case of air bubbling, increasing shear stress (by rising air bubbling flow rate) to more than 185 mPa did not show any significant growth enhancement, while increasing the shear stress from 40 to 185 mPa improved the yield production up to 85%. At the optimal stirring rate, the yield production in the stirred photobioreactors increased by about 60% as compared to that of unstirred culture. The measurements of chlorophyll_a and carotenoid showed a strong correlation between biomass production and total pigment content. The highest level of cellular pigment (pigment per cell) was detected at the early stages of culture growth when cells were preparing for the rapid exponential growth phase.