Separation Approach Research Articles

Feature Engineering for Physics-informed Evaluation of Electromechanical Impedance Measurements for Sandwich Face Layer Debonding Identification

The present research exploits various physically explainable features for the evaluation of electromechanical impedance (EMI) measurements for sandwich face layer debonding identification using a recently published two-step physics- and machine-learning (ML)-based approach. In the previous work, the ML approach used employs a One-Class Support Vector Machine and a K-Nearest Neighbor model for debonding detection and size estimation, respectively. Feature engineering was used to compensate for the simplifications of the finite element (FE)-based physical model and a simple data calibration step was used to adapt to distribution shifts. This enabled to train both ML models exclusively with FE simulation-based synthetic EMI spectra data. The efficacy of the method was demonstrated on real-world EMI spectra measurements of a circular aluminum sandwich panel by a piezoelectric transducer. The considered face layer debonding damage was idealized and stepwise increased by a milling process. In the present work, we explore opportunities for further optimization of our method with respect to data distillation, where we reduce the computational requirements of both training and inference while at the same time preserving essential information. Furthermore, we investigate the usefulness of a separate approach for debonding detection, formulated as an anomaly detection problem. The data preprocessing and ML models are validated by unseen real-world EMI measurement data and benchmarked with the previously published damage evaluation results, considering both reliability and accuracy. The data and the code used in this study are provided in their entirety to enable reproducibility, enhance comprehensibility, and encourage future research.

A nonlinear dynamic hysteresis model with magnetic–prestress–thermal coupling effect and dynamic electromagnetic losses of a giant magnetostrictive actuator

Compared with traditional actuators, the giant magnetostrictive actuator has the merits of fast response, high accuracy, and high reliability and has been widely applied. However, its performance is affected by the electromagnetic loss and the temperature, prestress, and magnetic coupling effect. In order to accurately analyze its performance, it is necessary to establish a nonlinear dynamic model including the electromagnetic loss and the magnetic–prestress–thermal coupling effect. First, based on the field separation approach, the magnetic fields generated by the eddy current loss and the anomalous loss are obtained and added to the Jiles–Atherton model. Second, the magnetostrictive model is given with the magnetic–prestress–thermal coupling effect. Finally, assuming the transmission of the giant magnetostrictive actuator as a mass–spring–damper system, a nonlinear dynamic hysteresis model with magnetic–prestress–thermal coupling effect and dynamic electromagnetic losses of a giant magnetostrictive actuator is developed. Based on this model, the output displacement curves of the giant magnetostrictive actuators under different driving currents and frequencies are given. The comparison with the experimental results shows that this model agrees well with the experiment.

Water resource sources in the ancient town of Si Mahosot, Thailand

Management of available water resources has been practiced throughout human history. We examine here some aspects of water resource management in the ancient (6th to 13th century) town of Si Mahosot (Thailand). Based on isotopic measurements (2H, 18O, and 222Rn) of both surface water and groundwater samples, we confirmed that groundwater is the main source of water that feeds the town's canal network. Based on a series of shallow wells in the area, we estimated a radon endmember activity of 14,200 Bq/m3 for the groundwater that feeds the canals. We used a radon mass balance model that considers radon inputs via groundwater and losses via decay and atmospheric evasion. Applying our estimated endmember activity, we calculated a water flux into the canal domain studied of 145 ± 36 m3/day, enough to replace the water within this section of the canal within 16–26 days. A separate independent approach using a18O mass balance resulted in a very similar discharge estimate of 154 ± 39 m3/day into the studied canal. The flux may have been higher when the former town was occupied as there are indications that groundwater levels were higher here in the past.

Unveiling Hidden Sources of Dynamic Functional Connectome through a Novel Regularized Blind Source Separation Approach

Abstract The investigation of the brain’s functional connectome and its dynamic changes can provide valuable insights into brain organization and its reconfiguration. However, the analysis of dynamic functional connectivity (dFC) using functional magnetic resonance imaging (fMRI) faces major challenges, including the high dimensionality of brain networks, unknown latent sources underlying observed dFC, and the large number of brain connections that increase the risk of spurious findings. In this paper, we propose a new regularized blind source separation (BSS) method called dyna-LOCUS to address these challenges. dyna-LOCUS decomposes observed dFC measures to reveal latent source connectivity traits and their dynamic temporal expression profiles. By utilizing low-rank factorization and novel regularizations, dyna-LOCUS achieves efficient and reliable mapping of connectivity traits underlying the dynamic brain functional connectome, characterizes temporal changes of the connectivity traits that contribute to the reconfiguration in the observed dFC, and generates parsimonious and interpretable results in identifying whole-brain dFC states. We introduce a highly efficient iterative Node-Rotation algorithm that solves the non-convex optimization problem for learning dyna-LOCUS. Simulation studies demonstrate the advantages of our proposed method. Application of dyna-LOCUS to the Philadelphia Neurodevelopmental Cohort (PNC) study unveils latent connectivity traits and key brain connections and regions driving each of these neural circuits, reveals temporal expressions and interactions of these connectivity traits, and generates new findings regarding gender differences in the neurodevelopment of an executive function-related connectivity trait.

Robust and comprehensive predictive models for methane hydrate formation condition in the presence of brines using black-box and white-box intelligent techniques

Accurate estimation of gas hydrate formation condition is crucial for many reasons. In one hand, the gas hydrate formation is a promising approach for gas separation, cold energy storage, seawater desalination, etc. On the other hand, in some industries, this phenomenon may cause some challenges, such as pipelines blockage. The current study was undertaken to develop trustworthy predictive tools for methane hydrate formation temperature (MHFT) in the presence of brines. To achieve this target, 1051 experimental data pertinent to the methane hydrate equilibrium in 26 single and multiple brines over an extensive range of operating conditions were amassed from published studies. Four simple factors, including pressure, brine concentration, salt molecular weight and salt melting temperature were defined as the input variables, and the black-box intelligent techniques, including gaussian process regression (GPR), multilayer perceptron (MLP) and radial basis function (RBF) were employed to link MHFT to the mentioned factors. A plethora of graphical and statistically-based assessments were performed to determine the accuracy level of the proposed models. While all intelligent models had excellent performances, the one established by the GPR method showed the best agreements with experimental data, and gave the AARE and R2 values of 0.14% and 99.17%, respectively, in the testing step. The foregoing model was capable of predicting MHFT over a broad range of conditions with relative deviations mostly below 0.10%. Additionally, it showed an excellent performance in describing the physical variations of MHFT versus operating factors. The authority of the analyzed databank and the presented model was asserted via the William's plot investigation. Moreover, a sensitivity analysis was undertaken in order to determine the most fundamental factors in controlling MHFT. Eventually, a simple mathematical correlation was also derived based on the white-box intelligent approach of gene expression programming (GEP), which allowed the accurate estimation of MHFT with an AARE of 0.56%.

Assessment of Mycotoxin Exposure and Associated Risk in Pregnant Dutch Women: The Human Biomonitoring Approach.

Mycotoxins are toxic secondary metabolites produced by various fungi that can contaminate food crops, which, in turn, may lead to human exposure. Chronic exposure to mycotoxins can cause adverse health effects including reproductive and developmental toxicity. Pregnant women and their foetuses present a vulnerable group for exposure to mycotoxins that can cross the placenta. Human biomonitoring of mycotoxins provides a real-life approach to estimate internal exposure. In this pilot study, 24-h urine samples from 36 pregnant Dutch women were analysed for aflatoxin M1 (AFM1), total deoxynivalenol (DON), de-epoxy-deoxynivalenol (DOM-1), total zearalenone (ZEN), total α-zearalenol (α-ZEL), total β-zearalenol (β-ZEL) and total zearalanone (ZAN), where 'total' refers to mycotoxins and their conjugated forms. Serum samples from these women were analysed for fumonisin B1 (FB1) and ochratoxin A (OTA). All samples were measured using liquid chromatography-tandem mass spectrometry (LC-MS/MS). The most prevalent mycotoxins were total DON, total ZEN and OTA, with a detection frequency of 100%. DOM-1, total α-ZEL and total β-ZEL were detected but to a lesser extent, while AFM1, total ZAN and FB1 were undetected. Median concentrations were 4.75 μg total DON/L, 0.0350 μg DOM-1/L, 0.0413 μg total ZEN/L, 0.0379 μg total α-ZEL/L, 0.0189 μg total β-ZEL/L, and 0.121 μg OTA/L. The calculated median concentration for total ZEN and its metabolites was 0.105 μg/L. Based on two separate risk assessment approaches, total DON exposure in this group was considered to be of low concern. Similarly, exposure to total ZEN and its metabolites in this group was of low concern. For OTA, the risk of non-neoplastic effects was of low concern based on exposure in this group, and the risk of neoplastic effects was of low concern in the majority of participants in this group. The findings of this pilot study confirm the presence of mycotoxins in the urine and serum of pregnant Dutch women, with total DON, total ZEN, and OTA most frequently detected. Exposure to all measured mycotoxins was considered to be of low concern in this group, except for exposure to OTA, which was of low concern for the majority of participants. The study's findings offer valuable insights but should be confirmed using a larger and more diverse sample of the Dutch general population.

Separation of terbium as a first step towards high purity terbium-161 for medical applications.

Terbium-161 is a medical radiolanthanide that has a beta decay energy and half-life similar to that of lutetium-177, which makes it a promising alternative for therapeutic purposes. The production route using an enriched gadolinium-160 target necessitates the purification of terbium-161 from the untransmuted target material as well as from its stable decay product, dysprosium-161. The separation of neighbouring lanthanides is challenging due to their similar chemical properties and prominent trivalent oxidation states. In this work, the aim is to change the oxidation state of terbium, resulting in the altering of chemical properties that ease the intragroup separation. To this end, a novel separation method is investigated, involving the electrochemical oxidation of terbium (3+) to terbium (4+) followed by anion exchange chromatography. The electrolysis conditions are set to the highest achievable conversion rate, followed by a dilution step during which the pH and electrolyte concentration are slightly lowered to obtain conditions that are compatible with the separation method. XAS analysis is done to characterize the carbonato complex of both oxidation states and to further elucidate the separation mechanism. The results show that the separation approach of combining electrochemical oxidation with anion exchange chromatography is promising for the purification of 161Tb for medical use.

Modelling of CO<sub>2</sub> Removal and Capturing Process Using Different Solvents for Al-Halfaya Oil Field to Reduce the Total Emissions

Since there currently are no financially feasible sources of renewable electricity and since they are readily available and inexpensive, such as coal, fossil fuels; that will remain the primary energy source for decades. Consequently, it is imperative to create technologies that allow for the continued use of fossil fuels whilst reducing the amount of CO<sub>2</sub> released into the environment. In order to lower atmospheric emissions, CO<sub>2</sub> should be captured from sources of emissions. Increased oil recovery, ocean or subsurface storage, or perhaps both, might be accomplished using the recovered CO<sub>2</sub>. Extracting high-purity CO<sub>2</sub> from flue gas, which is present in low concentrations (about 15 percent), is the most difficult step in the CO<sub>2</sub> capture process. The process of a selected separation approach will then be thoroughly examined by modeling it utilizing the Aspen Plus program while employing three solvents, including MEA, DEA, and NH3. Additionally, based on the simulation results provided by Aspen Plus, the present research intends to assess the environmental and economic implications of every solvent in order to choose the solvent with the minimum environmental impact and the best economic performance. Also, look at how the final CO<sub>2</sub> removal efficacy is affected by the pressure and temperature of the chosen solvents and absorber. According to the findings, DEA solvent outperformed NH3 and MEA in terms of CO<sub>2</sub> extraction effectiveness. Additionally, employing NH3 as a chemical solvent does not affect temperature or pressure, but using MEA and DEA negatively influences CO<sub>2</sub> extraction efficiency when the temperature is raised. However, when utilizing DEA and MEA as chemical solvents, the pressure of the solvent enhances the rate of CO<sub>2</sub> collecting.

EXPLORING FACTORS AFFECTING NITROGEN ISOLATION BY CATION EXCHANGE MEMBRANE AND THEIR IMPLICATIONS FOR MICROBIAL FUEL CELL PERFORMANCE IN WASTEWATER TREATMENT

This study explores the utilization of a cation exchange membrane (CEM) in a microbial fuel cell (MFC) system to isolate nitrogen from wastewater influents. While employing a CEM in an MFC system has drawbacks, such as increased internal resistance and reduced power output, it also provides a means for optimal energy recovery from organics while allowing isolated nitrogen to be treated in subsequent steps. This study evaluated the diffusion of ammonium through CEM in a dual-chamber MFC under different operating conditions. Results indicated that the MFC reactor with CEM as a separator isolated 88-93% of the nitrogen input, demonstrating the feasibility of this approach for nitrogen separation in wastewater treatment applications. Factors affecting nitrogen isolation, including COD input at the anode, dissolved oxygen (DO) at the cathode, and external resistance (ER), are identified. Higher COD input at the anode and the DO at the cathode were found to enhance nitrogen separation, while increased ER had an adverse effect on nitrogen isolation capacity. Additionally, changes in the surface characteristics of the CEM during operation could impact nitrogen isolation, emphasizing the need for careful monitoring and maintenance of the CEM to ensure consistent performance over time. In conclusion, this study highlighted the potential of using a CEM in MFC systems for nitrogen isolation, provided insights into the factors affecting the efficacy of nitrogen separation, and underscored the need for monitoring and maintenance of the CEM. These results could significantly impact the development of more efficient and sustainable wastewater treatment using the MFC system.

Simultaneously Selective Separation of Zearalenone and Four Aflatoxins From Rice Samples Using Co-Pseudo-Template Imprinted Polymers With MIL-101(Cr)-NH2 as Core.

A novel approach for the simultaneous separation of zearalenone (ZEN) and four types of aflatoxins (AFB1, AFB2, AFG1 and AFG2) from rice samples was presented. This approach utilized modified MIL-101(Cr)-NH2 as core, with molecularly imprinted polymers (MIPs) serving as the shell. The MIL-101(Cr)-NH2 was prepared via ring-opening reaction, while the imprinted polymers were synthesized using warfarin and 4-methylumbelliferyl acetate as co-pseudo template, ethylene glycol dimethacrylate as the cross-linker and azobisisobutyronitrile as initiator. The resulting co-pseudo-template-MIPs (CPT-MIPs) were thoroughly characterized and evaluated. Adsorption studies demonstrate that the adsorption process of CPT-MIPs follows a chemical monolayer adsorption mechanism, with imprinted factors ranging from 1.24 to 1.52 and selective factors ranging from 1.29 to 1.52. Self-made columns were prepared, and the method for separation was developed and validated. The limit of detections ranged from 0.12 to 2.09μg/kg, and the limit of qualifications ranged from 1.2 to 6.25μg/kg. To assess the reliability of the method, ZEN and AFs were spiked at three different levels, and the recoveries ranged from 79.53 to 94.58%, with relative standard deviations of 2.90-5.78%.

Thiol-functionalized cellulose adsorbents for highly selective separation of palladium over platinum in acidic aqueous solutions

The selective separation of palladium (Pd) over platinum (Pt) remains a challenge in metal recycling, because of their similar electronic configuration and chemical properties. This study explored their selective separation using three new adsorbents by grafting sulfur-donor ligands onto cellulose, namely 2-aminothiophenol (Cell-AP), 2-mercaptopyridine (Cell-MP), and 2-mercaptobenzothiazole (Cell-MBT). These adsorbents exhibited excellent adsorption capacity for Pd(II), reaching 163.3 ± 2.5 mg/g (at pH 1), 92.5 ± 1.2 mg/g (at pH 1), and 27.5 ± 0.5 mg/g (at pH 2.5), respectively. Isotherm studies showed that the adsorption process followed Freundlich isotherm, indicating a multilayer adsorption that takes place on a heterogenous surface. Kinetic results fit best with pseudo-second-order and intra-particle diffusion model, suggesting that the rate-limiting process involves chemisorption and intra-particle diffusion. Thermodynamic studies showed that adsorption by Cell-AP and Cell-MP was a spontaneous exothermic reaction. The materials also showed superior selectivity of Pd(II) over Pt(IV) with a maximum separation factor (SFPd/Pt) of 64.50, which improves over most previous studies. The mechanism of selectivity was further investigated by XPS, FTIR, SEM and DFT calculations, which showed that PdCl42- has smaller size, shorter HOMO-LUMO gap, and lower binding energy to ligands as compared to PtCl62-. This was used to explain the higher affinity for Pd(II) over Pt(IV) of these sulfur-modified adsorbents. This work provides a practical approach for the selective separation of Pd over competing ions that could improve the efficiency for overall metal recovery or recycling processes.

British surveillance of postwar Soviet radio jamming: US–UK intelligence relations and interference detection at BBC Tatsfield, 1948-1949

ABSTRACT Following World War II, the BBC, better known for radio programme broadcasts, continued its long-standing work of radio spectrum surveillance at the specialized receiving and measurement facility located at Tatsfield. Both before and after Soviet jamming of US and British Russian-language broadcasts escalated in April 1949, Tatsfield catalogued the technical characteristics of jamming signals. BBC engineers, experienced in interpreting types and sources of radio interference, issued fortnightly summaries with interpretations of these technical observations. US intelligence agencies knew of Tatsfield’s findings, but differing perspectives in Washington and London resulted in divergent responses to the technical intelligence data. With rising tensions in wider Anglo-American intelligence relations, fueled by the Soviet weapons program and security breaches, such differences presaged separate approaches to Soviet communications threats. US agencies received greatly increased funding, while the BBC’s budget struggles persisted. Even so, interference detection was a high-water mark in Britain’s early Cold War intelligence work.

Unsupervised separation of nonlinearly mixed event-related potentials using manifold clustering and non-negative matrix factorization

Event-related potentials (ERPs) can quantify brain responses to reveal the neural mechanisms of sensory perception. However, ERPs often reflect nonlinear mixture responses to multiple sources of sensory stimuli, and an accurate separation of the response to each stimulus remains a challenge. This study aimed to separate the ERP into nonlinearly mixed source components specific to individual stimuli. We developed an unsupervised learning method based on clustering of manifold structures of mixture signals combined with channel optimization for signal source reconstruction using non-negative matrix factorization (NMF). Specifically, we first implemented manifold learning based on Local Tangent Space Alignment (LTSA) to extract the spatial manifold structure of multi-resolution sub-signals separated via wavelet packet transform. We then used fuzzy entropy to extract the dynamical process of the manifold structures and performed a k-means clustering to separate different sources. Lastly, we used NMF to obtain the optimal contributions of multiple channels to ensure accurate source reconstructions. We evaluated our developed approach using a simulated ERP dataset with known ground truth of two components of ERP mixture signals. Our results show that the correlation coefficient between the reconstructed source signal and the true source signal was 92.8 % and that the separation accuracy in ERP amplitude was 91.6 %. The results show that our unsupervised separation approach can accurately separate ERP signals from nonlinear mixture source components. The outcomes provide a promising way to isolate brain responses to multiple stimulus sources during multisensory perception.

PH-sensitive spontaneous decay of functionalized carbon dots in solutions.

Carbon quantum dots have become attractive in various applications, such as drug delivery, biological sensing, photocatalysis, and solar cells. Among these, pH sensing via luminescence lifetime measurements of surface-functionalized carbon dots is one application currently investigated for their long lifetime and autonomous operation. In this article, we explore the theoretical connection between excitation lifetimes and the pH value of the surrounding liquid via the protonation and deprotonation of functional groups. Example calculations applied to m-phenylenediamine, phloroglucinol, and tethered disperse blue 1 are shown by applying a separation approach treating the electronic wave function of functional groups separately from the internal electronic structure of the (large) carbon dot. The bulk of the carbon dot is treated as an environment characterized by its optical spectrum that shifts the transition rates of the functional group. A simple relationship between pH, pKa, and mixed fluorescence lifetime is derived from the transition rates of the protonated and deprotonated states. pH sensitivity improves when the difference in the transition rates is greatest between protonated and deprotonated species, with the greatest sensitivity found where the pKa is close to the pH region of interest. The introduced model can directly be extended to consider multicomponent liquids and multiple protonation states.

Recent 10-year development on surface modification of polymeric hollow fiber membranes via surface coating approach for gas separation: a review

Recent 10-year development on surface modification of polymeric hollow fiber membranes via surface coating approach for gas separation: a review

The Effect of the Independent Learning Strategy on the Achievement of Grammar Subject for Students of the College of Islamic Sciences

The present analysis targets to recognize the influence of the separate teaching approach on the accomplishment of grammar for scholars of the College of Islamic Sciences. The target of attaining this target led the investigations developing the subsequent null theories: 1. No statistically substantial variance is happened at the consequence level of 0.05 between the mean scores of the scholars in the investigational category who learnt consistent with the separate learning approach and the mean scores of the scholars in the control category who learnt in the conventional method in the accomplishment test. 2. No statistically substantial variance has been observed at the consequence level of 0.05 in the mean differences between the scores of the pre-tests and post-tests in the accomplishment test among the scholars of the investigational assemblage. The present investigation was restrained to a sample of third-stage scholars in the Arabic Language Department at the College of Islamic Sciences, University of Baghdad, for the academic year 2022-2023 AD. The pre-test (separate learning) was utilized to the first-stage scholars in the department, who numbered (120) male and female scholars. They were allocated between two categories: an investigational category with (60) male and female scholars and a control category with (60) male and female scholars. The investigational category examined benefiting the separate learning approach, while the control category studied benefiting the conventional method. At the finish of the investigation, a t-test was utilized for two separate and interconnected samples. The outcomes presented what follows: 1. A statistically major variance was noticed between the mean scores of the investigational collection scholars who learned grammar based on the separate learning approach and the averages of the control category scholars who learned the same topic in the traditional manner in the post-test and in support of the investigational category. 2. A statistically substantial variance was recorded between the mean scores of the investigational category scholars who learned grammar consistent with the separate learning approach and the scores of the investigational category scholars in the pre-test and their scores in the post-test, and this requires higher accomplishment among the investigational category scholars.

Influence of graphene oxide additives on the NF separation of triazine-based H2S scavenging compounds using advanced membrane technology

This work proposes an innovative approach for the membrane separation of spent and unspent H2S scavengers (SUS) derived from the application of MEA-triazine in offshore oil and gas production. Modified nanofiltration membranes were fabricated by incorporating graphene oxide (GO) and polyvinyl alcohol (PVA) into a thin film composite (TFC) to obtain a thin film nanocomposite (TFN) with enhanced permeability. In addition, various immobilization strategies for GO were investigated. The performance of the membranes and the effect of the GO loading were evaluated in terms of permeability, fouling propensity, and rejection of key components of the SUS, i.e., MEA-triazine (unspent scavenger), dithiazine (spent scavenger), and monoethanolamine, operating on a sample of SUS wastewater obtained from an offshore oil and gas platform. Various characterization techniques, such as contact angle, FTIR, XRD, SEM, TGA, and AFM, were employed to evaluate the structure, composition, and hydrophilicity of the membrane. The results show a remarkable increase in permeability (from 0.22 Lm-2 h−1 bar−1 for the TFC to 5.8 Lm-2 h−1 bar−1 for the TFN membranes), due to the enhanced hydrophilicity from GO incorporation. The strong interfacial interaction between GO and PVA within the TFN membrane results in negligible nanofiller leaching. The incorporation of GO moderately increases the rejection of the unspent scavenger (63%–73%, 62%–79%, 62%–80%, and 68%–76%), while drastically increasing the rejection of the spent scavenger, which is approximately null for the TFC membrane without GO and increases up to 58% in the TFN membrane with GO. Therefore, while the proposed membranes cannot be used for the selective separation of the unspent form the spent scavenger, they can achieve substantial recovery of all the key components contained in the SUS to avoid their discharge into the sea.

Fusion and fission phenomena in a (2+1)-dimensional Sawada-Kotera type system

In this study, we extend the generalized multilinear variable separation approach to a fifth-order nonlinear evolution equation. By performing asymptotic analysis on the variable separation solution, which is composed of three lower-dimensional functions, we identify a resonant regime governing dromion-dromion/solitoff interactions. In the case of two-dromion interactions, elastic, inelastic, and completely inelastic collisions are possible, while for the dromion-solitoff interaction only inelastic and completely inelastic collisions are permitted. Furthermore, we derive two types of semi-rational solutions from the quadratic function ansatz. In particular, in the scenario of a completely resonant collision between a lump and a line-soliton pair, the lump separates from one line soliton and exists briefly before merging with the other soliton, forming a localized lump in both time and space dimensions. The fusion or fission phenomena between the dromion-dromion/solitoff interaction and the lump-line soliton interaction are shown graphically.

Spatially resolved air quality index prediction in megacities with a CNN-Bi-LSTM hybrid framework

Monitoring pollution in megacities is challenging due to their vast urban expanses and numerous pollution sources. To address this, cutting-edge deep learning models are proposed for monitoring, managing, and forecasting pollution levels. In this study, data concerning six pollutants (O3, NO2, CO, SO2, PM2.5, PM10) and Air Quality Index (AQI) values were collected over a five-year period from three distinct zones within the Tehran megacity. The gathered data were incorporated into a dataset comprising 37,044 records, encompassing the concentrations of examined pollutants and the related AQI across various study points. The primary aim was to enhance the precision of deep learning models using a regional strategic separation approach. A frequency domain filter method was employed to address data noise. Four models—Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Convolutional Neural Network with LSTM (CNN-LSTM), and Convolutional Neural Network with Bidirectional LSTM (CNN-Bi-LSTM)—were developed to predict AQI values. Evaluation showed disparities in pollution levels among the studied areas. The CNN-Bi-LSTM model exhibited the highest accuracy at 97 %, but challenges in predicting sudden fluctuations reduced accuracy to 95 % in some cases. However, the model consistently captured the underlying pattern of changes. Segregating megacity regions enhances accuracy in forecasting air pollution conditions.

Decomposition solutions and Bäcklund transformations of the B-type and C-type Kadomtsev–Petviashvili equations

This paper introduces a modified formal variable separation approach, showcasing a systematic and notably straightforward methodology for analyzing the B-type Kadomtsev–Petviashvili (BKP) equation. Through the application of this approach, we successfully ascertain decomposition solutions, Bäcklund transformations, the Lax pair, and the linear superposition solution associated with the aforementioned equation. Furthermore, we expand the utilization of this technique to the C-type Kadomtsev–Petviashvili (CKP) equation, leading to the derivation of decomposition solutions, Bäcklund transformations, and the Lax pair specific to this equation. The results obtained not only underscore the efficacy of the proposed approach, but also highlight its potential in offering a profound comprehension of integrable behaviors in nonlinear systems. Moreover, this approach demonstrates an efficient framework for establishing interrelations between diverse systems.