Modeling the Interfacial Tension of Water-Based Binary and Ternary Systems at High Pressures Using a Neuro-Evolutive Technique

Optimization of computational intelligence approach for the prediction of glutinous rice dehydration

BACKGROUND

Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution of moisture during the dehydration process of glutinous rice. The hyperparameters of the models were optimized with three strategies: Bayesian optimization, grid search and random search. To understand the parameters that facilitate intelligence model adaptation to the dehydration process, global sensitivity analysis (GSA) was used to compute the impact of the input variables on the model output.

RESULT

The result shows that the optimum computational intelligence techniques include the 3-9-1 topology trained with Bayesian regulation function for ANN, Gaussian kernel function for SVM, Matérn covariance function combined with zero mean function for GPR, boosting method for EoT and 4 minimum leaf size for DT. GPR has the highest performance with R2 of 100% and 99.71% during calibration and testing of the model, respectively. GSA reveals that all the models significantly rely on the variation in time as the main factor that affects the model outputs.

CONCLUSION

Therefore, the computational intelligence models, especially GPR, can be applied for an effective description of moisture evolution during small-scale and industrial dehydration of glutinous rice. © 2024 Society of Chemical Industry.

Harnessing artificial intelligence-driven approach for enhanced indole-3-acetic acid from the newly isolated Streptomyces rutgersensis AW08

Indole-3-acetic acid (IAA) derived from Actinobacteria fermentations on agro-wastes constitutes a safer and low-cost alternative to synthetic IAA. This study aims to select a high IAA-producing Streptomyces-like strain isolated from Lake Oubeira sediments (El Kala, Algeria) for further investigations (i.e., 16S rRNA gene barcoding and process optimization). Subsequently, artificial intelligence-based approaches were employed to maximize IAA bioproduction on spent coffee grounds as high-value-added feedstock. The specificity was the novel application of the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Box (L-BFGS-B) optimization algorithm. The new strain AW08 was a significant producer of IAA (26.116 ± 0.61 μg/mL) and was identified as Streptomyces rutgersensis by 16S rRNA gene barcoding and phylogenetic inquiry. The empirical data involved the inoculation of AW08 in various cultural conditions according to a four-factor Box Behnken Design matrix (BBD) of Response surface methodology (RSM). The input parameters and regression equation extracted from the RSM-BBD were the basis for implementing and training the L-BFGS-B algorithm. Upon training the model, the optimal conditions suggested by the BBD and L-BFGS-B algorithm were, respectively, L-Trp (X1) = 0.58 %; 0.57 %; T° (X2) = 26.37 °C; 28.19 °C; pH (X3) = 7.75; 8.59; and carbon source (X4) = 30 %; 33.29 %, with the predicted response IAA (Y) = 152.8; 169.18 μg/mL). Our findings emphasize the potential of the multifunctional S. rutgersensis AW08, isolated and reported for the first time in Algeria, as a robust producer of IAA. Validation investigations using the bioprocess parameters provided by the L-BFGS-B and the BBD-RSM models demonstrate the effectiveness of AI-driven optimization in maximizing IAA output by 5.43-fold and 4.2-fold, respectively. This study constitutes the first paper reporting a novel interdisciplinary approach and providing insights into biotechnological advancements. These results support for the first time a reasonable approach for valorizing spent coffee grounds as feedstock for sustainable and economic IAA production from S. rutgersensis AW08.

Waste valorization as low-cost media engineering for auxin production from the newly isolated Streptomyces rubrogriseus AW22: Model development

Indole-3-acetic acid (IAA) represents a crucial phytohormone regulating specific tropic responses in plants and functions as a chemical signal between plant hosts and their symbionts. The Actinobacteria strain of AW22 with high IAA production ability was isolated in Algeria for the first time and was characterized as Streptomyces rubrogriseus through chemotaxonomic analysis and 16 S rDNA sequence alignment. The suitable medium for a maximum IAA yield was engineered in vitro and in silico using machine learning-assisted modeling. The primary low-cost feedstocks comprised various concentrations of spent coffee grounds (SCGs) and carob bean grounds (CBGs) extracts. Further, we combined the Box-Behnken design from response surface methodology (BBD-RSM) with artificial neural networks (ANNs) coupled with the genetic algorithm (GA). The critical process parameters screened via Plackett-Burman design (PBD) served as BBD and ANN-GA inputs, with IAA yield as the output variable. Analysis of the putative IAA using thin-layer chromatography (TLC) and (HPLC) revealed Rf values equal to 0.69 and a retention time of 3.711 min, equivalent to the authentic IAA. AW 22 achieved a maximum IAA yield of 188.290 ± 0.38 μg/mL using the process parameters generated by the ANN-GA model, consisting of L-Trp, 0.6%; SCG, 30%; T°, 25.8 °C; and pH 9, after eight days of incubation. An R² of 99.98%, adding to an MSE of 1.86 × 10^-5 at 129 epochs, postulated higher reliability of ANN-GA-approach in predicting responses, compared with BBD-RSM modeling exhibiting an R² of 76.28%. The validation experiments resulted in a 4.55-fold and 4.46-fold increase in IAA secretion, corresponding to ANN-GA and BBD-RSM models, respectively, confirming the validity of both models.

Molecular modelling of the thermophysical properties of fluids: expectations, limitations, gaps and opportunities

This manuscript provides an overview of the current state of the art in terms of the molecular modelling of the thermophysical properties of fluids. It is intended to manage the expectations and serve as guidance to practising physical chemists, chemical physicists and engineers in terms of the scope and accuracy of the more commonly available intermolecular potentials along with the peculiarities of the software and methods employed in molecular simulations while providing insights on the gaps and opportunities available in this field. The discussion is focused around case studies which showcase both the precision and the limitations of frequently used workflows.

Degradation of Azithromycin from aqueous solution using Chlorine-ferrous- oxidation: ANN-GA modeling and Daphnia magna biotoxicity test assessment

Azithromycin (AZM), an antibacterial considered one of the most consumed drugs, especially during the period against the Covid 19 pandemic, and it is one of the persistent contaminants that can be released into aquatic ecosystems. The purpose of this study is to determine the efficacy of a Fenton-like process (chlorine/iron) for the degradation of AZM in an aqueous medium by determining the impact of several factors (the initial concentration of (FeSO₄, NaClO, pollutant), and the initial pH) on the degradation rate. The Response Surface Methodology (RSM) based on the Box-Wilson design as well as the Artificial Neural Network (ANN) modeling combined with a genetic algorithm (GA) approaches were used to determine the optimal levels of the selected variables and the optimal rate of degradation. The quadratic model of multi-linear regression developed indicated that the optimal conditions were a concentration of chlorine of 600 μM, the concentration of AZM is 32.8 mg/L, the mass of the catalyst FeSO₄ is 3.5 mg and a pH of 2.5, these optimal values gave a predicted and experimental yield of 64.05% and 70% respectively, the lack of fit test in RSM modeling (F₀ = 3.31 which is inferior to Fcritic (0.05, 10.4) = 5.96) indicates that the true regression function is not linear therefore, the ANN-GA modeling as non-linear regression indicated that the optimal conditions were a concentration of chlorine of 256 μM, the concentration of AZM is 5 mg/L, the mass of the catalyst FeSO₄ is 9.5 mg and a pH of 2.8, these optimal values gave a predicted and experimental yield of 79.69% and close to 80% respectively, Furthermore, biotoxicity tests were conducted to confirm the performance of our process using bio-indicators called daphnia (Daphnia magna), which demonstrated the efficacy of the like-Fenton process after 4 h of degradation.

Optimization of thermostable proteases production under agro-wastes solid-state fermentation by a new thermophilic Mycothermus thermophilus isolated from a hydrothermal spring Hammam Debagh, Algeria

The present work investigates for the first time the presence and isolation of the thermophilic fungi from hydrothermal spring situated at the locality of Guelma, in the Northeast of Algeria. The production of the thermostable proteases and the optimization of culture conditions under agro-wastes solid-state fermentation to achieve optimal production capacity were explored. A statistical experimental approach consisting of two designs was used to determine the optimum culture conditions and to attain the greatest enzyme production. Besides, different agricultural wastes were initially evaluated as a substrate, whereby wheat bran was selected for enzyme production by the isolate under solid-state conditions. The isolate thermophilic fungi were identified as Mycothermus thermophilus by sequencing the ITS region of the rDNA (NCBI Accession No: MK770356.1). Among the various screened variables: the temperature, the inoculum size, and the moisture were proved to have the most significant effects on protease activity. Employing two-level fractional Plackett-Burman and a Box-Behnken designs statistical approach helped in identifying optimum values of screened factors and their interactions. The analysis showed up 6.17-fold improvement in the production of proteases (~1187.03 U/mL) was achieved under the optimal conditions of moisture content 47%, inoculum 5 × 10⁵ spores/g, and temperature at 42 °C. These significant findings highlight the importance of the statistical design in isolation of Mycothermus thermophilus species from a specific location as well as identifying the optimal culture conditions for maximum yield.

The Fenton-like reaction for Arsenic removal from groundwater: Health risk assessment

In this paper, the heterogeneous Fenton like-reaction for Arsenic-contaminated groundwater remediation based on the performance of FeSO₄ as an efficient and green catalyst and CaO₂ as a source of H₂O₂ was investigated. To intensify the heterogeneous Fenton process, three oxidants were tested: sodium percarbonate (SPC), sodium persulfate (SPS), and calcium peroxide (CP). The results showed that CP and SPC had a synergetic effect on the rate of Arsenic degradation, while SPS had an antagonistic effect. On the other hand, inorganic ions such as Na⁺, Mg²⁺ have a very low impact on the Arsenic removal efficiency, while the anions Cl^- and NO₃^- exhibited significant inhibition of Arsenic degradation. This effect may be imputed to the reaction and conversion of hydroxyl (HO^•) radicals to less reactive. Thus, HCO₃^- and humic acid dramatically raised the degradation rate. Also, the response Surface method based on Box-Behnken design was applied to examine the suitable modeling, and optimized condition of the Fenton like-reaction process, the maximum Arsenic removal efficiency of 94.91% is obtained when [Fe³⁺]₀ = 1.97 mM, [CaO₂]₀ = 1.74 mM and initial pH = 4.67. The obtained results showed that the Fenton-like reaction is an effective and reliable process for arsenic removal from groundwater with low non-carcinogenic risk (HQ) and carcinogenic risk (CR) values.

Valorization and optimization of agro-industrial orange waste for the production of enzyme by halophilic Streptomyces sp

This study underlines the biotechnical valorization of the accumulated and unusable remains of agro-industrial orange fruit peel waste to produce α-amylase under submerged conditions by Streptomyces sp. KP314280 (20r). The response surface methodology based on central composite design (RSM-CCD) and artificial neural network coupled with a genetic algorithm (ANN-GA) were used to model and optimize the conditions for the α-amylase production. Four independent variables were evaluated for α-amylase activity including substrate concentration, inoculum size, sodium chloride powder (NaCl), and pH. A ten-fold cross-validation indicated that the ANN has a greater ability than the RSM to predict the α-amylase activity (R²_ANN = 0.884 and R²_RSM = 0.725). The analysis of variance indicated that the aforementioned four factors significantly affected the α-amylase activity. Additionally, the α-amylase production experiments were conducted according to the optimal conditions generated by the GA. The results indicated that the amylase yield increased by 4-fold. Moreover, the α-amylase production (12.19 U/mL) in the optimized medium was compatible with the predicted conditions outlined by the ANN-GA model (12.62 U/mL). As such, the ANN and GA combination is optimizable for α-amylase production and exhibits an accurate prediction which provides an alternative to other biological applications.

Artificial Neural Networks for Predicting Hydrogen Production in Catalytic Dry Reforming: A Systematic Review

Dry reforming of hydrocarbons, alcohols, and biological compounds is one of the most promising and effective avenues to increase hydrogen (H2) production. Catalytic dry reforming is used to facilitate the reforming process. The most popular catalysts for dry reforming are Ni-based catalysts. Due to their inactivation at high temperatures, these catalysts need to use metal supports, which have received special attention from researchers in recent years. Due to the existence of a wide range of metal supports and the need for accurate detection of higher H2 production, in this study, a systematic review and meta-analysis using ANNs were conducted to assess the hydrogen production by various catalysts in the dry reforming process. The Scopus, Embase, and Web of Science databases were investigated to retrieve the related articles from 1 January 2000 until 20 January 2021. Forty-seven articles containing 100 studies were included. To determine optimal models for three target factors (hydrocarbon conversion, hydrogen yield, and stability test time), artificial neural networks (ANNs) combined with differential evolution (DE) were applied. The best models obtained had an average relative error for the testing data of 0.52% for conversion, 3.36% for stability, and 0.03% for yield. These small differences between experimental results and predictions indicate a good generalization capability.

Data mining for pesticide decontamination using heterogeneous photocatalytic processes

Pesticides are chemical compounds used to kill pests and weeds. Due to their nature, pesticides are potentially toxic to many organisms, including humans. Among the various methods used to decontaminate pesticides from the environment, the heterogeneous photocatalytic process is one of the most effective approaches. This study focuses on artificial intelligence (AI) techniques used to generate optimum predictive models for pesticide decontamination processes using heterogeneous photocatalytic processes. In the present study, 537 valid cases from 45 articles from January 2000 to April 2020 were filtered based on their content collected and analyzed. Based on cross-industry standard process (CRISP) methodology, a set of four classifiers were applied: Decision Trees (DT), Bayesian Network (BN), Support Vector Machines (SVM), and Feed Forward Multilayer Perceptron Neural Networks (MLP). To compare the accuracy of the selected algorithms, accuracy, and sensitivity criteria were applied. After the final analysis, the DT classification algorithm with seven factors of prediction, the accuracy of 91.06%, and sensitivity of 80.32% was selected as the optimal predictor model.

Photocatalytic-persulfate- oxidation for diclofenac removal from aqueous solutions: Modeling, optimization and biotoxicity test assessment

In this paper, the influence of several aquatic factors (the nature of catalyst, the initial pH and the initial concentration of the pollutant) on the photocatalytic degradation of diclofenac (DFC), one of the most widely prescribed anti-inflammatory non-steroidal drug, was studied. Also, in order to examine the intensification process, the variation of the photocatalytic DFC degradation in the presence of sodium persulfate (PPS) was analyzed. It was found that, compared to titanium dioxide (TiO₂), the zinc oxide (ZnO) photocatalyst performed exceptionally well, with a 96.13% DFC degradation efficiency after 150 min. The photodegradation of DFC by ZnO catalyst fitted well the Langmuir-Hinshelwood kinetic model. The maximum efficiency is 97.27% for simulated solar-UVA/ZnO/PPS and 77% for simulated solar-UVA/ZnO. In order to determine the optimal conditions leading to the maximization of DFC removal, an artificial neural network (ANN) modeling approach combined with genetic algorithm (GA) was applied. The best ANN determined had a correlation of 0.999 and it was further used in the process optimization where a 99.7% degradation efficiency was identified as the optimum under the following conditions: DFC initial concentration 37,9 mg L^-1, pH 5,88 and PPS initial concentration 500 mg L^-1. The effectiveness of the process and the toxicity of the pharmaceutical pollutants and their by-products were also evaluated and confirmed by the biological tests using liver and kidney of Mus musculus mice.

Determination of thermodynamic state variables of liquids from their microscopic structures using an artificial neural network

In this work we implement a machine learning method to predict the thermodynamic state of a liquid using only its microscopic structure provided by the radial distribution function (RDF). The main goal is to determine the equation of state of the system. The goal is achieved by predicting the density, temperature or both at the same time using only the RDF. We implement and train a machine learning feed forward artificial neural network (ANN) to address the different cases of interest where single or simultaneous predictions are done. Due to its versatility, in this study the Lennard-Jones (LJ) fluid is used as the reference system. The ANN is trained in a wide range of densities and temperatures, covering the liquid-vapour coexistence, liquid phase and supercritical states. We show that the overall percentage relative error of most of the predictions in different cases of study is around 3%. As a practical case of study we use the ANN predictions to determine the pressure equation of state for different isotherms and we found a very good agreement with respect to the exact results. Our ANN implementation is a versatile and useful tool to predict thermodynamic state variables when some information is unknown and, consequently, to enhance the thermodynamic description of liquids.

Comparative Analysis of Four Neural Network Models on the Estimation of CO2-Brine Interfacial Tension

During the CO₂ injection of geological carbon sequestration and CO₂-enhanced oil recovery, the contact of CO₂ with underground salt water is inevitable, where the interfacial tension (IFT) between gas and liquid determines whether the projects can proceed smoothly. In this paper, three traditional neural network models, the wavelet neural network (WNN) model, the back propagation (BP) model, and the radical basis function model, were applied to predict the IFT between CO₂ and brine with temperature, pressure, monovalent cation molality, divalent cation molality, and molar fraction of methane and nitrogen impurities. A total of 974 sets of experimental data were divided into two data groups, the training group and the testing group. By optimizing the WNN model (I_WNN), a most stable and precise model is established, and it is found that temperature and pressure are the main parameters affecting the IFT. Through the comparison of models, it is found that I_WNN and BP models are more suitable for the IFT evaluation between CO₂ and brine.