Operational Features Research Articles

Metal Recovery from Wastewater Using Electrodialysis Separation

Electrodialysis is classified as a membrane separation process in which ions are transferred through selective ion-exchange membranes from one solution to another using an electric field as the driving force. Electrodialysis is a mature technology in the field of brackish water desalination, but in recent decades the development of new membranes has made it possible to extend their application in the food, drug, and chemical process industries, including wastewater treatment. This work describes the state of the art in the use of electrodialysis (ED) for metal removal from water and wastewater. The fundamentals of the technique are introduced based on the working principle, operational features, and transport mechanisms of the membranes. An overview of the key factors (i.e., the membrane properties, the cell configuration, and the operational conditions) in the ED performance is presented. This review highlights the importance of studying the inter-relation of parameters affecting the transport mechanism to design and optimize metal recovery through ED. The conventional applications of ED for the desalination of brackish water and demineralization of industrial process water and wastewater are discussed to better understand the key role of this technology in the separation, concentration, and purification of aqueous effluents. The recovery and concentration of metals from industrial effluents are evaluated based on a review of the literature dealing with effluents from different sources. The most relevant results of these experimental studies highlight the key role of ED in the challenge of selective recovery of metals from aqueous effluents. This review addresses the potential application of ED not only for polluted water treatment but also as a promising tool for the recovery of critical metals to avoid natural resource depletion, promoting a circular economy.

Comparative Study of Degradation Features in Proton Exchange Membrane Water Electrolysis: Irregular Renewable Energy Vs Regular Steady-State/Dynamic Loads

Green hydrogen production is currently on the rise, and it is reshaping the future of the energy sector. Numerous hydrogen roadmaps and projects are scaling up this technology in various target sectors, which necessitates cost reduction for green hydrogen implementation. Proton exchange membrane water electrolysis coupled with the renewable energy source (PEMWE-ReS) is a promising technology that offers notable advantages to decrease the electricity cost by using wind generation and solar photovoltaic system. However, to meet the growth of green hydrogen technology, accurate lifetime assessment and subsequent development of durable materials should be considered. In this regard, this presentation will discuss a comparative analysis of stability test results based on various load-ranges. In particular, to consider the PEMWE-ReS coupling, a realistic solar profile was simulated and applied for PEMWE cell measurement. The results were then compared to previous steady-state and dynamic loads to gain insight into the differences in degradation patterns at field and laboratory scale. For this purpose, the degradation features were systematically analyzed with electrochemical, microscopic, and spectrochemical analyses to see the dynamic of overpotential changes, membrane chemical degradation, catalyst dissolution/migration/diffusion, and Ti porous transport layer passivation. Notably, a realistic solar profile that simulates PEMWE-ReS conditions is featured by the increased fluoride release rate due to cycling to low load, and Pt dissolution/diffusion to the anode. Given the degradation features of the realistic solar operation, it was determined that a combined pattern of specific steady-state and dynamic cycling loads can induce the degradation features of solar operation the most. The findings can provide useful insights for establishing accelerated stress test to diagnose system durability and for setting design guidance for durable materials.

Psychophysiological components of the activities of operators of nuclear power plants as a factor of accidents in the conditions of the threat of social catastrophe

The purpose of the study is to establish the peculiarities of operator’s work and the leading factors of the formation of its psychophysiological tension at nuclear power plants in the conditions of the threat of social catastrophe in connection with military operations. The study was conducted at the Zaporizhzhya and Khmelnytsky nuclear power plants for the period of 2020-2021. To study the dynamics of the psychophysiological state of operators of nuclear power plants, a verbal-communicative diagnostic method was used to collect information about the operators investigated using Google Form and traditional physiological, psychological and psychophysiological methods. The socio-demographic features of the investigated operators of the block control panel were analyzed. It was established that men only (100%) aged 24-49 and with work experience from 4 to 20 years were among the examined. All surveyed operators (41 people) are residents of the city, with completed higher education and are family members. The methods of psychological (reactive anxiety, mood, activity, mood, attention), physiological (cardiography, blood pressure) and psychophysiological (simple sensorimotor and psychophysical) research methods were used to empirically assess the intensity of activity of the operators of the block control panel of nuclear power plants. There were examined operators, while on duty when control errors and pre-accident situations were recorded. It was established that the psychological, physiological and psychophysiological characteristics of these operators are followed by increased reactive anxiety, decreased indicators of well-being, activity, mood, reduction in functional reserves of the cardiorespiratory system, mental and physical capacity. These indicators are considered as criteria for the development of regulatory measures. It is proposed to take into account not only technological factors, but also the psychophysiological features of operators in the dynamics of their manifestation when developing measures for the optimal selection and personnel placement. The complex of methods for researching the functional state of operators can be used to optimize their professional selection and retraining, which can lead to reducing accidents and costs for professional training. The expected effect is an increase in the efficiency and quality of operator’s activity, the productivity and reliability of the performance of production tasks, an increase in professional longevity, a decrease in rate and occupationally-related morbidity of these specialists.

Discourse markers in Spanish in the Tijuana-San Diego border area

Abstract This study examines the use of discourse markers among speakers of Spanish residing in Tijuana, Mexican immigrants in San Diego, and heritage Spanish speakers in San Diego. We find a core set of discourse markers that is common to all speakers, as well as subsets of discourse markers for Tijuana, San Diego immigrant, and San Diego heritage speakers. Four English discourse markers are attested in the border: okay as a general, established borrowing; so only among immigrant and heritage speakers; and like and you know only among heritage speakers. In a language-contact situation, discourse markers whose lexical content is less analyzable and whose functions are more operational detach first from the pragmatically-dominant language (Matras 1998). We find that the operational properties of okay, like, and you know make them borrowable into the Spanish of the border. However, so is borrowed in San Diego with operational and content-related features by heritage speakers, and with content-related features only by immigrant speakers.

Operational Control Model Based on Integrated Failure Analysis and Risk Assessment in Sustainable Technological Processes

The simultaneous fulfillment of quality, environmental, and occupational safety requirements is a difficult task. The process flow is influenced by numerous factors, and different operational objectives are pursued in different ways. Methodologies reflecting the use of various models, methods, and tools in the integration and implementation of operational goals dedicated to sustainable operation are becoming increasingly important. The subject of the study is an operational control model considering the integrated risk and the steps taken under the conditions of “supervised risk” ensured by the monitoring of the operational criteria. The method was developed for coherent risk management, covering its identification, analysis, assessment, and acceptability estimation in the technological process. The methodology for the assessment, considering the quality, environmental, and occupational safety criteria, and based on the application of the unit risk ratio, allows for the determination of the key operational features, and the methodology of the identification of the key technological parameters applying the integrated risk ratio ensures that the crucial technological parameters are highlighted. The application of the algorithm in the heat treatment process confirms both the effectiveness of the proposed model and the correctness of the thesis: the different requirements set for the technological processes can be simultaneously fulfilled via the application of integrated operational control.

Optimization Of a Sustainable Closed Loop Supply Chain Network (SCLSCN): A Modified NSGA-III Method

For a generic closed-loop supply chain network (CLSCN), a mixed-integer Linear programing (MILP) Model was developed that simultaneously optimizes three of the fundamental elements of sustainability: cost, social impact, and environmental effect. Many real-world features of SC operations, which includes multiple products types, multiple echelons, multiple production technologies, and multiple modes of transportation, were all incorporated into the model during its development. As a result of the complexity of the model and need to provide Pareto front for decision maker, a novel hybrid NSGA III (HNSGA-III) was developed to solve the model. The Relative Gap was used result of the model was validated using the ε-constraint method. the algorithm parameters were tuned using Taguchi design then the performance of HNSGA III as compared to NSGA III, HypE and MOEA/D was assessed using RNS, SNS, IGD, CPU times and HC index. The result clearly shows the HNSGA III outperforms the other meta-heuristic algorithms. Keywords: Closed loop supply chain network, Sustainability, CO2 Emission, Multi-objective model, HNSGA III, NSGA III, MOEA/D, HypE Victor Jinn, Harold Ugochukwu Nwosu & Matthew Uzoma Shadrach (2023): Optimization Of a Sustainable Closed Loop Supply Chain Network (SCLSCN): A Modified NSGA-III Method. Journal of Advances in Mathematical & Computational Science. Vol. 10, No. 4. Pp 45-70. dx.doi.org/10.22624/AIMS/MATHS/V11N4P4. Available online at www.isteams.net/mathematics-computationaljournal.

Xenon behavior modeling for molten salt reactors by using multiple transport mechanisms

Molten Salt Reactor (MSR) is a liquid fueled reactor, in which the sparingly soluble fission gases including xenon continuously circulate with the fuel salt in the primary loop, and meanwhile are removed by helium bubbling. This unique operation feature introduces multiple mechanisms and in turn complicates the behavior of xenon, necessitating being accurately modeled. In this study, a migration model of 135Xe and 135mXe in the primary loop for MSR is established based on the equations that describe the nuclide concentration balance and mass transfer among the helium bubbles, fuel salt and graphite. The developed model is validated with the experimental data of Molten Salt Reactor Experiment (MSRE), and presents a better agreement compared with the previous xenon migration model. Sensitivity analysis of some key parameters including injected void fraction, bubble size, mass transfer coefficient, temperature and pressure, on the xenon poison under steady state are then analyzed. The results demonstrate that the injected void fraction, mass transfer coefficient and core operation pressure would impose a significant influence on the xenon poison, which should be paid particular attention in the core design and safety analysis.

A conformal multi-port MIMO patch antenna for 5G wireless devices

This paper presents a multiple-input-multiple-output (MIMO) antenna array with low-profile and flexible characteristics. Multiple microstrip patches are arranged in the E-plane configuration and decoupled by shorted quarter-wavelength stubs. The antenna has a small element spacing of 0.032 λ, where λ is a free-space wavelength at the center frequency. To demonstrate the feasibility of the proposed concept, a 1 × 4 MIMO array prototype is fabricated. The measured results on the fabricated prototype demonstrate that the MIMO antenna has good operation features at 4.8 GHz with a reflection coefficient of less than –10 dB and an isolation of better than 20 dB. Besides, good radiation patterns and broadside gain of around 4.5 dBi are also attained. The antenna also works in the bending mode and has the capability of extending to large-scale MIMO arrays. Such attractive features prove the utility of the proposed antenna in various modern electronic devices.

Основні питання створення моделі процесу технічної експлуатації повітряного судна військового призначення

The subject of the research in this article is the creation of a mathematical model of the process of technical operation (PTO) of a military aircraft in the system of information support for the operation of an aircraft. The aircraft is a complex technical system that includes many systems, subsystems, and elements for reliable and error-free functioning, which require constant monitoring of its technical condition to determine the possibility of its intended use. It is proposed to promote PTO in the system of information support for the operation of aircraft operating in real time and to create a mathematical model of the process. We will construct a graph of states and transitions using the transition matrix to describe the PTO of a military aircraft. The purpose of this study is to create a mathematical model of the PTO of a military aircraft in a system of information support for the operation of the aircraft operating on a real time scale. The task: to determine the role and advantage of using the mathematical model of the PTE of a military aircraft in the information support system for the operation of a CMMS-type aircraft operating in real time for its use in forecasting and managing the effectiveness of the PTE. The scientific and practical novelty of the obtained results is as follows: the advantages of the PTE mathematical model of a military aircraft in the CMMS-type aircraft operation information support system, which works in real time before the PTO model by resource and the model when decisions are made at the moment, have been determined state changes. The conclusion of this study is that the use of the proposed PTO model will allow us to evaluate complex reliability indicators in real time, that is, continuously. The considered PTO model of a military aircraft considers all the features of military aircraft operation at the current stage. This allows us to assume the possibility of its use for the entire aircraft fleet of the Air Force Base of the Armed Forces of Ukraine.

Carbon Footprint and Energy Recovery Potential of Primary Wastewater Treatment in Decentralized Areas: A Critical Review on Septic and Imhoff Tanks

The present work is a critical review on the carbon footprint and energy recovery potential of septic and Imhoff tanks for primary wastewater treatment. From an online search of research papers, a lack of up-to-date research about gas emissions from Imhoff tanks emerged. Additionally, available literature data should be extended to incorporate the effect of seasonal variations, which may be relevant due to the fact that both systems work under environmental conditions. The literature generally agrees on the positive effect of temperature increase on biogas and methane production from both septic and Imhoff tanks. Additionally, sludge withdrawal is an important operational feature for gas production in these reactors. More recently, the application of electrochemical technologies and the installation of photovoltaic modules have been studied to enhance the sustainability of these decentralized solutions; in addition, sludge pretreatment has been investigated to raise the obtainable methane yields due to limited sludge biodegradability. Further research is needed to assess the effective sustainability of biogas collection and valorization from existing septic and Imhoff tanks, considering the limited biogas generation and the implementation of these systems in decentralized wastewater treatment scenarios (rural or mountain areas). Contrary to the intensive research on greenhouse gas mitigation strategies applied to centralized systems, solutions specifically designed for gas emission mitigations from septic and Imhoff tanks have not attracted the same scientific interest up to now. More generally, given the widespread application of these two options and their potential significant contribution to the overall carbon footprint of wastewater treatment technologies, much more research must be performed in the future both on the quantification of gas production and on the applicable strategies to reduce their carbon footprint.

INTERACTION OF THE ARMED FORCES OF UKRAINE AND CIVIL SOCIETY IN COUNTERING RUSSIAN PROPAGANDA

This article examines the interaction problem between the Armed Forces of Ukraine and civil society in countering Russian propaganda. The idea that civil society in Ukraine is a permanent participant in public and political processes and performs a compensatory function against the background of the limited internal potential of state-management influence and institutions of state power in matters of ensuring national security is substantiated. The article clarifies the specifics of the interaction between the Armed Forces and civil society within the framework of conventional warfare and against the background of hybrid, informational warfare. It was found out that Ukrainian civil society has significant experience in protecting national interests and helping the defense forces of Ukraine since 2014. During the entire period of the hybrid war, the possibilities and effectiveness of interaction between the Armed Forces of Ukraine and civil society in matters of state defense have significantly increased and reached their peak against the background of a full-scale invasion in 2022. The article discusses the topic of Russian propaganda against Ukrainian civil society and reveals the main stages of the periodization of Russia’s information war against Ukraine, the features of special information operations, and their effectiveness since 2014. It is established that Ukraine, having no productive means of combating the enemy at the beginning of the modern confrontation with Russian propaganda, today has accumulated a significant arsenal of resources, including the capabilities of mass media, state defense forces, and civil society. Based on the study of the possibilities of interaction between the Armed Forces of Ukraine and civil society in countering Russian propaganda, the author concluded that today, Ukraine has rich but scattered, unsystematized experience in combating propaganda. An essential task in the framework of the interaction of the Armed Forces of Ukraine and civil society in this matter is the creation of a single concept that will help coordinate the interaction between all the bodies of the Armed Forces of Ukraine involved in the information struggle and its defense departments, mass media, as well as civil society. It was established that the Armed Forces should cooperate with mass media, public organizations, and society on joint steps to counter Russian propaganda, as well as to improve the level of their interaction with civil society.

Analog monolayer SWCNTs-based memristive 2D structure for energy-efficient deep learning in spiking neural networks

Advances in materials science and memory devices work in tandem for the evolution of Artificial Intelligence systems. Energy-efficient computation is the ultimate goal of emerging memristor technology, in which the storage and computation can be done in the same memory crossbar. In this work, an analog memristor device is fabricated utilizing the unique characteristics of single-wall carbon nanotubes (SWCNTs) to act as the switching medium of the device. Via the planar structure, the memristor device exhibits analog switching ability with high state stability. The device’s conductance and capacitance can be tuned simultaneously, increasing the device's potential and broadening its applications' horizons. The multi-state storage capability and long-term memory are the key factors that make the device a promising candidate for bio-inspired computing applications. As a demonstrator, the fabricated memristor is deployed in spiking neural networks (SNN) to exploit its analog switching feature for energy-efficient classification operation. Results reveal that the computation-in-memory implementation performs Vector Matrix Multiplication with 95% inference accuracy and few femtojoules per spike energy efficiency. The memristor device presented in this work opens new insights towards utilizing the outstanding features of SWCNTs for efficient analog computation in deep learning systems.

Identification of CXCL16 as a diagnostic biomarker for obesity and intervertebral disc degeneration based on machine learning

Intervertebral disc degeneration (IDD) is the primary cause of neck and back pain. Obesity has been established as a significant risk factor for IDD. The objective of this study was to explore the molecular mechanisms affecting obesity and IDD by identifying the overlapping crosstalk genes associated with both conditions. The identification of specific diagnostic biomarkers for obesity and IDD would have crucial clinical implications. We obtained gene expression profiles of GSE70362 and GSE152991 from the Gene Expression Omnibus, followed by their analysis using two machine learning algorithms, least absolute shrinkage and selection operator and support vector machine-recursive feature elimination, which enabled the identification of C-X-C motif chemokine ligand 16 (CXCL16) as a shared diagnostic biomarker for obesity and IDD. Additionally, gene set variant analysis was used to explore the potential mechanism of CXCL16 in these diseases, and CXCL16 was found to affect IDD through its effect on fatty acid metabolism. Furthermore, correlation analysis between CXCL16 and immune cells demonstrated that CXCL16 negatively regulated T helper 17 cells to promote IDD. Finally, independent external datasets (GSE124272 and GSE59034) were used to verify the diagnostic efficacy of CXCL16. In conclusion, a common diagnostic biomarker for obesity and IDD, CXCL16, was identified using a machine learning algorithm. This study provides a new perspective for exploring the possible mechanisms by which obesity impacts the development of IDD.

Application of fermatean fuzzy weight operators and MCDM model DIBR-DIBR II-NWBM-BM for efficiency-based selection of a complex combat system

The use of complex automated combat systems is a basic feature of every modern combat operation, and all modern armies strive to implement such systems in their units. This paper investigates the choice of a complex combat system based on the efficiency criteria that condition it. The Defining Interrelationships Between Ranked criteria (DIBR) and the Defining Interrelationships Between Ranked criteria II (DIBR II) methods were used to determine the weight coefficients of the criteria, which proved to be effective in assessing the importance of each criterion in the context of making complex decisions. Aggregation of expert opinions, for each of the methods, was performed using the Normalized Weighted Bonferroni Mean (NWBM) operator. After the weight coefficients for both methods were obtained, the aggregation of the obtained values was performed using the Bonferroni Mean (BM) operator, which resulted in the final values of the weight coefficients of the criteria. In order to choose the optimal alternative, the Fermatean Fuzzy Weight Operators (FFWO) and BM operator were used. These operators contributed to the precise evaluation and ranking of alternatives, taking into account their characteristics and specificities. Furthermore, the paper analyzed the sensitivity of the output results to changes in the weight coefficients of the criteria. This is important in order to assess the stability of the Multiple Criteria Decision Making (MCDM) model and ensure its reliability in different scenarios. This work represents a significant contribution to the field of decision-making in this context and provides a useful framework for the selection of complex combat systems, and the combination of different methods and operators enables a comprehensive analysis and optimization of the research problem.

Effectiveness criteria of suspicious transaction reporting for early detection of terrorist financing activities

Purpose This study aims to evaluate the suspicious transaction reporting (STR) as a financial intelligence tool to identify the potential strengths and limitations of STR and to come up with the criteria, which will make this tool an effective one in early detection of terrorist financing activities. Design/methodology/approach Considering the research aim, this research uses the funnelling method for identifying effectiveness criteria. Funnelling is a method of literature review that helps find pertinent literature by refining the search through filtering the available research (Ridley, 2008). Using this method, the researcher first applied the criteria of actionable intelligence to filter the financial intelligence tools to select the most promising and important tool (suspicious transaction reporting) for early detection of terrorist financing activities. The funnelling method was also applied to derive the effectiveness criteria from the operational features, and corresponding limitations, of the suspicious transaction reporting system. The funnelling method was also used to identify those operational features and limitations of suspicious transaction reporting that have the most direct relevance to the early detection problem of suspicious transaction reporting. Findings There are some operational features of STR that give rise to certain limitations that undermine its effectiveness in terms of early detection of terrorist financing activities. The limitations of STR necessitate a search for criteria that will make STR effective in early detection of terrorist financing activities. Based on the operational features and their corresponding limitations, effectiveness criteria for STR have been derived in this study. It is shown how these effectiveness criteria can remove the limitations of STR. Research limitations/implications The list of operational features and the corresponding limitations based on which the effectiveness criteria have been derived may not be exhaustive. There may have other operational features, and corresponding limitations that also make STR largely ineffective in the early detection of terrorist financing activities, and for which more effectiveness criteria should also be derived. Practical implications The limitations and the effectiveness criteria will pave the way for redesigning STR in such a way that will make it highly useful for detecting financing activities relating to imminent terrorist attacks. Social implications The society will experience fewer terrorist attacks that will make the society peaceful, happy and vibrant. Originality/value In this study, the effectiveness criteria of STR for early detection of terrorist financing activities have been derived in an innovative way by deducing them from the operational features of STR and the corresponding limitations.

Combining finite element and reinforcement learning methods to design superconducting coils of saturated iron-core superconducting fault current limiter in the DC power system.

A saturated iron-core type superconducting fault current limiter (SI-SFCL) can effectively restrict the magnitude of the fault current and alleviate the strain on circuit breakers in DC power systems. Design of a superconducting coil (SC), which is one of the key tasks in the SI-SFCL design, requires guaranteeing a sufficient magnetic field, ensuring optimization of the shape and size, minimizing the wire cost, and satisfying the safety and stability of operation. Generally, finite element method (FEM) is used to calculate and evaluate the operating characteristics of SCs, from which it is possible to determine their optimal design parameters. When the coil is complex and large, the simulation time may range from hours to days, and if input parameters change even slightly, the simulations have to be redone from scratch. Recent advances in deep learning represent the ability to be effective for modeling and optimizing complex problems from training data or in real-time. In this paper, we presented a combination of the FEM simulation and deep Q-network (DQN) algorithm to optimize the SC design of a lab-scale SI-SFCL for a DC power system. The detailed design process and options for the SC of SI-SFCL were proposed. In order to analyze the characteristics related to the electromagnetic properties and operational features of the SC, a 3D FEM model was developed. Then, a DQN model was constructed and integrated with the FEM simulation for training and optimizing the design parameters of the SC in real-time. The obtained results of this study have the potential to effectively optimize the design parameters of large-scale SI-SFCL development for high-voltage DC power systems.

Electrochemical Pixels: Semi-open electrochemical cells with a vertically stacked design

A novel electrochemical cell design in a vertically stacked configuration is presented. Through a layered structure using a top macroporous working electrode, a polyelectrolyte, and a bottom metallic conductor a standalone electrochemical cell with an internal reference electrode is built. This sensor allows monitoring an electrochemical property of an external solution with only one electrode in direct contact with the sample. Using paper-based platinum electrode for the porous top electrode and Nafion as polyelectrolyte material, the self-powered detection of hydrogen peroxide is performed. The system can be operated in multiple modes. In a capacitive way, the open circuit potential is measured. Alternatively, in a self-powered current mode, the system emulates a fuel cell. Additionally, a potential-current switched mode is also demonstrated. Because of this unique design and operational features this sensor is considered as an electrochemical pixel. To further demonstrate the advantages of this device, the detection of glucose is performed by building an array of sensors using a single back (reference) electrode and multiple working electrodes. These results lay the groundwork for the development of a new generation of simple and low cost biochemical sensors and electrochemical sensing arrays.

Risk-informed design of advanced nuclear reactor: A target unavailability approach

Incorporating specified safety and production targets during the design phase of an engineered facility can effectively support reductions in construction and operation costs of nuclear power plants. In addition, this supports efforts toward making nuclear power technology more competitive and profitable than other electric power production forms by incorporating operational and design features into the design phase that directly support the increased likelihood of meeting such originating targets. Unavailability is the key parameter to establish plant-level capabilities that cascade down to function, system, and component levels to ensure that all sources of unavailability are addressed in the facility's design phases. In this article, two methods are presented to propose unavailability targets for nuclear reactor systems to risk-inform and optimize the design features, from an availability perspective: the first method is a simple method, and the second is a non-dominated sorting genetic algorithm III (NSGA-III) multi-objective optimization. These iterative methods are demonstrated in this paper for a hypothetical facility with a design maturity such that there is knowing the main components to comply with the engineering and security functions of the systems. With an assumed mature design, it is implied that generic data to execute quantitative reliability, and availability analyses are available at the systems levels that are sufficient to support a design-specific probabilistic risk assessment (PRA). The proposed methods modify the probabilities of basic events within the fault tree structures that model system and component unavailability sources that will be required for the facility’s operating license. The methods provided are applied to visualize the characteristics of the problem and the quantitative results. This work forms the basis for future work in which design alternatives affecting unavailabilities can be estimated and compared to their associated unavailability targets at different levels of granularity.

SLAPP: Subgraph-level attention-based performance prediction for deep learning models

The intricacy of the Deep Learning (DL) landscape, brimming with a variety of models, applications, and platforms, poses considerable challenges for the optimal design, optimization, or selection of suitable DL models. One promising avenue to address this challenge is the development of accurate performance prediction methods. However, existing methods reveal critical limitations. Operator-level methods, proficient at predicting the performance of individual operators, often neglect broader graph features, which results in inaccuracies in full network performance predictions. On the contrary, graph-level methods excel in overall network prediction by leveraging these graph features but lack the ability to predict the performance of individual operators. To bridge these gaps, we propose SLAPP, a novel subgraph-level performance prediction method. Central to SLAPP is an innovative variant of Graph Neural Networks (GNNs) that we developed, named the Edge Aware Graph Attention Network (EAGAT). This specially designed GNN enables superior encoding of both node and edge features. Through this approach, SLAPP effectively captures both graph and operator features, thereby providing precise performance predictions for individual operators and entire networks. Moreover, we introduce a mixed loss design with dynamic weight adjustment to reconcile the predictive accuracy between individual operators and entire networks. In our experimental evaluation, SLAPP consistently outperforms traditional approaches in prediction accuracy, including the ability to handle unseen models effectively. Moreover, when compared to existing research, our method demonstrates a superior predictive performance across multiple DL models.

Development and testing of a mechanistic model for wetland treatment of neutral and polar organic contaminants in oil sands process-affected water

A mechanistic model of the fate of neutral and polar organic contaminants in a free water surface flow wetland was developed to assess the removal efficiency of polycyclic aromatic hydrocarbons (PAHs) and naphthenic acids (O2-NAs), which are chemicals primarily responsible for oil sands process-affected water (OSPW) toxicity. The model simulates wetland mechanisms of chemical removal based on physicochemical properties, environmental conditions, and wetland design and operation. Good agreement between model estimated and observed concentrations of PAHs and O2-NAs in OSPW in the Kearl Treatment Wetland (Alberta, Canada) was observed over time. Model simulations indicate that the removal of PAHs and O2-NAs from OSPW is highly sensitive to biotransformation rates and that sustained wetland treatment is feasible with robust PAH and NA degrading microbial communities in the wetland. Wetland treatment efficiency is greatest for substances with a log KOW or log D between 3.0 and 5.5 whereas substances with a log KOW or log D >6.0 are not suitable for wetland treatment, even if they can be biodegraded. The log KOW of PAHs and log D for O2-NAs range from 0.7 to 6.7 suggesting most organic contaminants in OSPW are suitable for wetland treatment. Chemical removal via evapotranspiration is not significant pathway of chemical removal from wetlands for PAHs and O2-NAs due to their very low log KAW (less than −1.6). The treatment wetland model presented is the first model to evaluate the fate of both neutral and polar organic contaminants in a flow-through treatment wetland operation, making it a helpful tool to assess the feasibility of these treatment systems for the oil sands industry. The model is particularly useful in evaluating chemical removal efficiency of OSPW contaminants, whether specific water quality objectives can be achieved after treatment, and to assess trade-offs in wetland design and operation to balance treatment performance with design and operational features.