Simulation-based Methods Research Articles

A rapid element pressure field simulation method for transcranial phase correction in focused ultrasound therapy

Transcranial focused ultrasound ablation has emerged as a promising technique for treating neurological disorders. The clinical system exclusively employed the ray tracing method to compute phase aberrations induced by the human skull, taking into account computational time constraints. However, this method compromises slightly on accuracy compared to simulation-based methods. This study evaluates a fast simulation method that simulates the time-harmonic pressure field within the region of interest for effective phase correction. Experimental validation was carried out using a 512-element, 670 kHz hemispherical transducer for four ex vivo skulls. The ray tracing method achieved a restoration ratio of 64.81% ± 4.33% of acoustic intensity normalized to hydrophone measurements. In comparison, the rapid simulation method demonstrated improved results with a restoration ratio of 73.10% ± 7.46%, albeit slightly lower than the full-wave simulation which achieved a restoration ratio of 75.87% ± 5.40%. The rapid simulation methods exhibited computational times that were less than five minutes for parallel computation with 8 threads. The incident angle was calculated, and a maximum difference of 6.8 degrees was found when the fixed position of the skull was changed. Meanwhile, the restoration ratio of acoustic intensity was validated to be above 70% for different target positions away from the geometrical focus of the transducer. The favorable balance between time consumption and correction accuracy makes this method valuable for clinical treatment applications.

Entrepreneurial Management for Students

Entrepreneurship is one of the important pillars in the Indonesian economy. Entrepreneurship can create jobs, increase competitiveness, and boost economic growth. Students are one of the groups that have the potential to become entrepreneurs. Students have high enthusiasm and creativity, and have access to technology and information. The purpose of this study is to examine entrepreneurial management for students. This study used qualitative research methods. Data collection techniques in this study were carried out with literature studies. The data that has been collected is then analyzed in three stages, namely data reduction, data presentation and conclusions. The results showed that the skills and knowledge needed by students to start and manage a business include technical skills, managerial skills, and entrepreneurial skills. Effective methods and approaches in providing entrepreneurial education and training to students include case-based methods, project-based methods, and simulation-based methods. Entrepreneurial education and training can equip students with the skills and knowledge needed to start and manage a business.

Simulation-based inference for model parameterization on analog neuromorphic hardware

The BrainScaleS-2 (BSS-2) system implements physical models of neurons as well as synapses and aims for an energy-efficient and fast emulation of biological neurons. When replicating neuroscientific experiments on BSS-2, a major challenge is finding suitable model parameters. This study investigates the suitability of the sequential neural posterior estimation (SNPE) algorithm for parameterizing a multi-compartmental neuron model emulated on the BSS-2 analog neuromorphic system. The SNPE algorithm belongs to the class of simulation-based inference methods and estimates the posterior distribution of the model parameters; access to the posterior allows quantifying the confidence in parameter estimations and unveiling correlation between model parameters. For our multi-compartmental model, we show that the approximated posterior agrees with experimental observations and that the identified correlation between parameters fits theoretical expectations. Furthermore, as already shown for software simulations, the algorithm can deal with high-dimensional observations and parameter spaces when the data is generated by emulations on BSS-2. These results suggest that the SNPE algorithm is a promising approach for automating the parameterization and the analyzation of complex models, especially when dealing with characteristic properties of analog neuromorphic substrates, such as trial-to-trial variations or limited parameter ranges.

Conative gamification model for psychological diagnostics and identification of risk zones of deviant behavior in educational institutions

Introduction. In the modern world, new methods of teaching and upbringing in the educational process are being created, new technologies are associated with the creation of digital methods of modeling the environment: interactive tools. Simulation-based learning methods are more common, which is a new tool that can potentially replace and enhance the real experience in a fully interactive way. The central trend in the educational institution is the transition to new methods that are integrated into the digital environment. The purpose of the article is to create a model of gamification of psychological diagnostics and identification of risk zones of deviant behavior in educational institutions. Methods. Within the framework of the strategic academic leadership program «Priority 2030», we conducted studies of deviant behavior of schoolchildren (n=85) and students (n=125). The following methods are used: diagnostics of the level of empathic abilities of V. V. Boyko; methodology of T. Adorno, E. FrenkelBrunswick, D. Levinson, R. Sanford «Scale of fascism»; methodology for identifying the «bullying structure» of E. G. Norkina. Methods of mathematical statistics: factor analysis by the method of principal components, regression analysis. Research results. Six components that make up the conative model of identifying risk zones of deviant behavior are identified: «Self-destruction», «Tendency to violate norms», «Susceptibility to right-wing extremism», «Cognitive distortion», «External aggression», «Pathological personality». A regression equation has been compiled, which gives the probability of prediction, where 94% accuracy of prediction, thereby determining that the scale of fascism is determined by two variables: authoritarian aggression and authoritarian submission. Other empirical facts have also been established to explain the model based on cognitive empathy. The management of the Penetrating ability in empathy can change the structure of bullying, reduce the number of aggressor's assistants, because it is positively interrelated with the role of defenders of victims (r=0.19; p<0.05). Conclusion. The components that reflect the diagnostic potential of the gamification model for identifying risk zones in the educational institution of students are fixed. Based on the selected components, you can create a program using the regulatory framework.

Comparison of electrical load forecast methods validated on the hourly consumption profiles of 10 heat pumps located in Switzerland

The integration of variable renewable energy in the electrical grid necessitates the exploitation of load flexibility. The high contribution of space heating to the residential sector, thereby, puts the balancing of heat pumps in focus. The paper compares three different approaches to predict the heat demand of 10 Swiss residential buildings on 9 winter days. We compare two different simulation based grey-box models and an elementary statistical model approach. Unexpectedly, the statistical approach almost always performs better than the others, although the anticipated advantages of the simulation-based approaches could be seen in several cases. The comparison between the simulation-based methods shows that the one requiring more detailed, higher data quality clearly outperformed the simplified version. The work led to the conclusion that in the used setup too little system information was available to fully exploit the potential of a simulation-based approach at one hour resolution.

Probabilistic finite element-based reliability of corroded pipelines with interacting corrosion cluster defects

The random distribution of pitting corrosion defects in pipelines normally leads to interacting cluster defects that behave noticeably different from single metal loss defects. Generally, the probabilistic approaches employ explicit burst pressure limit states for corroded pipelines subjected to only internal pressure. However, a significant level of conservatism is typically associated with the probabilistic assessments of corroded pipelines using the closed-form explicit limit state functions, which presents considerable challenges in maintenance planning and risk management. Therefore, this paper proposes a pathway for developing efficient performance functions for the assessment of interacting pipeline corrosion clustering defects using probabilistic finite element-based reliability method. This seven-stage framework combines multiple uncertainty representation schemes to evaluate the probability of failure. The impact of the critical design variables such as the elastic and plastic material properties, corrosion features, and interacting cluster defect characterisations are identified to guide the burst pressure design, operations and maintenance optimisation. The employed surrogate-based active learning reliability approach yielded an efficient probability estimate at a lesser computational cost than the simulation-based reliability methods. The proposed framework reduces the conservatism and computational cost related with explicit burst pressure limit state functions for corroded pipelines and offers informed decision-making on risk and maintenance management.

Tail Risks in Corporate Finance: Simulation-Based Analyses of Extreme Values

Recently, simulation-based methods for assessing company-specific risks have become increasingly popular in corporate finance. This is because modern capital market theory, with its assumptions of perfect and complete capital markets, cannot satisfactorily explain the risk situation in companies and its effects on entrepreneurial success. Through simulation, the individual risks of a company can be aggregated, and the risk effect on a target variable can be shown. The aim of this article is to investigate which statistical methods can best assess tail risks in the overall distribution of the target variables. By doing so, the article investigates whether extreme value theory is suitable to model tail risks in a business plan independent of company-specific data. For this purpose, the simulated cash flows of a medium-sized company are analyzed. Different statistical ratios, statistical tests, calibrations, and extreme value theory are applied. The findings indicate that the overall distribution of the simulated cash flows can be multimodal. In the example studied, the potential loss side of the cash flow exhibits a superimposed, well-delimitable second distribution. This tail distribution is extensively analyzed through calibration and the application of extreme value theory. Using the example studied, it is shown that similar tail risk distributions can be modeled both by calibrating the simulation data in the tail and by using extreme value theory to describe it. This creates the possibility of working with tail risks even if only a few planning data are available. Thus, this approach contributes to systematically combining risk management and corporate finance and significantly improving corporate risk management. Based on these findings, further analyses can be performed in terms of risk coverage potential and rating to improve the risk situation in a company.

Simulation and optimization of transfer system for ore terminal with complex waterways

Terminal towing and barging operations play a critical role in cargo transfer within ports, especially in complex waterways. Scheduling of barges and tugs is influenced by various factors, such as speed, and the operation planning must consider the constraints of channel traffic. Additionally, the transfer system involves constructing and operating berths, transshipment equipment, barges, tugboats, and other resources. Effective scheduling and resource planning are crucial for achieving sustainability. To illustrate this point, we analyze the estuary barging process in a real-world case. We utilize the Anylogic platform to simulate the entire process of ore terminal loading, river transportation, and sea transshipment. Furthermore, we employ simulation-based optimization methods to enhance the system’s performance. Our case study has yielded valuable management insights, including: (1) Key variables related to shipping speeds and resource allocation are identified and optimized; (2) A specific tug dispatch rule has been verified to outperform other options in terms of efficiency and emissions; (3) The potential benefits of constructing and enabling an additional terminal have been identified. Our exploration provides quantitative support for decision-making related to vessel scheduling and resource planning in engineering projects for ore terminals.

Importance of Integrated Simulation Approaches in Medical Education when Teaching Therapy Disciplines to Students of Medical Faculty

The article is devoted to reviewing the main methods of practice-oriented teaching of medical students at the Department of Internal Medicine No. 1, Clinical Immunology and Allergology named after Academician Y. M. Neyko of Ivano-Frankivsk National Medical University (Ukraine). The significance of not only theoretical but also practical training of medical students in the conditions of blended learning is highlighted. The impact of new teaching methods on the level of future doctors' professionalism has been analyzed. Another important aspect of training is the introduction of simulation training, which allowed for obtaining a high level of knowledge without harming the patient. The article focuses on the role of the “virtual patient” in supervision, as this method, regardless of the form of study, allowed the student to be acquainted with a standardized patient, improve communication skills and choose the right method of diagnosis or treatment by the European guidelines. The article describes prospective systems for simulating clinical cases, which allow the creation of interactive training cases of various complexity levels depending on the goals set or the level of a specialist's training. The article presents the main online platforms for creating the most realistic cases with photographs of the affected body area and protocols of instrumental examinations, which allow you to reproduce the order of the doctor's actions and modify the intensity of the patient's condition if the prescription was incorrect. Moreover, the article highlights the positive impact of interactive teaching methods on student motivation and encouragement to deepen knowledge in a particular discipline, as an essential aspect is the discussion of examination results and prescription of therapy based on modern guidelines. It additionally outlines actions to be taken for ensuring efficient handling of new “virtual patient” cases and for inputting data on previously created clinical cases into the system. The article describes the main advantages of simulation-based teaching methods in comparison with traditional forms of teacher-student interaction. It is noted that training with the help of ”virtual patients” allows us to evaluate the acquired practical skills and competencies of future doctors.

Neonatal airway management training using simulation-based educational methods and technology

Airway management is a fundamental component of neonatal critical care and requires a high level of skill. Neonatal endotracheal intubation (ETI), bag-mask ventilation, and supraglottic airway management are complex technical skills to acquire and continually maintain. Simulation training has emerged as a leading educational modality to accelerate the acquisition of airway management skills and train interprofessional teams. However, current simulation-based training does not always replicate neonatal airway management needed for patient care with a high level of fidelity. Educators still rely on clinical training on live patients. In this article, we will a) review the importance of simulation-based neonatal airway training for learners and clinicians, b) evaluate the available training modalities, instructional design, and challenges for airway procedural skill acquisition, especially neonatal ETI, and c) describe the human factors affecting the transfer of airway training skills into the clinical environment.

A multiclass simulation-based dynamic traffic assignment model for mixed traffic flow of connected and autonomous vehicles and human-driven vehicles

Connected and Autonomous Vehicles (CAVs) may exhibit different driving and route choice behaviours compared to Human-Driven Vehicles (HDVs), which can result in a mixed traffic flow with multiple classes of route choice behaviour. Therefore, it is necessary to solve the Multiclass Traffic Assignment Problem (TAP) for mixed traffic flow. However, most existing studies have relied on analytical solutions. Furthermore, simulation-based methods have not fully considered all of CAVs’ potential capabilities. This study presents an open-source solution framework for the multiclass simulation-based TAP in mixed traffic of CAVs and HDVs. The proposed model assumes that CAVs follow system optimal with rerouting capabilities, while HDVs follow user equilibrium. It also considers the impact of CAVs on road capacity at both micro and meso scales. The proposed model is demonstrated through three case studies. This study provides a valuable tool that can consider several assumptions for better understanding the impact of CAVs on mixed traffic flow.

Chaotic behavior learning via information tracking

Chaotic time series are often encountered in real-world applications, where modeling and understanding such time series present a significant challenge. Existing simulation-based methods for characterizing chaotic behavior may be sensitive to the respective model settings, while data-driven methods cannot adapt well to irregularities and aperiodicity in chaotic time series during the prediction stage, leading to nonlinearly aggregated forecasting errors after a finite number of time steps. In our preliminary work (Ren et al., 2023), we introduced a data-driven method that incorporates the idea of information tracking to capture and adapt to the chaotic changes over time, and tested its effectiveness on a real-world task—decadal temperature prediction. While the practical usefulness of the method has been initially validated on one domain-specific application scenario, a set of open questions is yet to be answered: Is the concept of information tracking generalizable to model and solve a broad spectrum of learning tasks that involve chaotic behavior? If yes, what are the underlying principles and learning behaviors that make the general method work well? Moreover, how can we assess the efficacy of the method in different scenarios? This study constitutes a significant step forward by systematically investigating and addressing the questions mentioned above. Specifically, we first provide a rigorous definition of the formalism and computational mechanism of the general method, with all necessary variables, symbols, and formulations. More importantly, we theoretically characterize and understand the generalizability of the method by mathematically uncovering the fundamental principles and behavior of information tracking-based chaotic behavioral learning, as prescribed by two chaotic behavioral indexes, namely, the Lyapunov and the Hurst exponents. Further, we comprehensively demonstrate the generalizability and robustness of the method by empirically examining a variety of chaotic behavioral learning problems generated by three representative chaotic systems: The logistic map, the double pendulum, and the Lorenz system.

Influence of Sheet Covers on Filling Behavior in Electrochemical Joining of Additively Manufactured Components

This paper focuses on the electrochemical joining of additively manufactured components using simulation-based and experimental methods. The study investigates the influence of cover screens on the filling behavior of the joining zone. Experimental methods involving additive manufacturing and electroplating are combined with simulation models to provide a realistic representation of the joining process. The results show a good agreement between the simulated and experimental findings, indicating the applicability of the simulation model. The parameter study reveals that higher cover factors result in a decrease in the excess material ratio, indicating reduced material deposition outside the joining zone. The filling time required to completely fill the joining zone is influenced by both the cover size and the opening angle of the joining zone. The optimal parameter combinations depend on whether the filling time or the excess material volume is to be minimized. Cavity formation within the joining zone was identified as a critical factor affecting the completeness of the filling. The study provides insights into the influence of cover screens on the electrochemical joining process and offers guidance for optimizing the design of the joining zone.

General provisions of the substantiation of functional safety of intelligent systems in railway transportation

Aim. The paper aims to solve the problem of objective and confident functional safety (FS) evaluation of intelligent control systems (ICS). As regards ICS, the conventional methods, due to their particular features, do not allow for a sufficiently confident estimation of the actual state of FS. The above features include primarily the nondistinct architecture of ICS and the changing connections between the system elements.Methods. Substantiating ICS FS requires using the complete arsenal of known methods and means recommended in GOST 33432-2015 [1], including managerial measures defined by the requirements for the safety policy, program and case. The authors have analysed the capability to prove ICS FS using experimental, expert, analytical, technological, and simulation-based methods. The limitations of some methods as regards ICS FS substantiation have been established.Results. The authors suggest a heuristic graph-based semi-Markov (Markov) method of proving system FS. For the purpose of substantiating ICS FS, it is recommended using the heuristic graph-based method combined with the technological method defined in GOST R IEC 61508 [2–4]. They don’t only allow confidently evaluating the FS of intelligent systems, but developing recommendations for achieving acceptable safety levels of such systems.

CFD simulation and optimization of ventilation for the layout of community architecture inspired by fishbone form

The rise in urbanization has led to an increase in high-density communities. Our study drew inspiration from the fishbone structure and applied a bionic architectural layout to optimize the wind environment within the pedestrian areas of these communities. Additionally, our study delved into the intrinsic principles and simulation-based optimization methods for the wind environment in the pedestrian areas of the fishbone bionic architectural complex. Using Computational Fluid Dynamics (CFD) simulation technology, our study simulated the building models both before and after the community renovation. Furthermore, our study simulated nine architectural complex models proposed by our study, considering the architectural layout and facade height within the community. By verifying and comparing the simulation results, our study observed that the fishbone bionic architectural form significantly improved the wind environment within the community’s pedestrian areas. Regarding the facade height, our study discovered that taller architectural units should be positioned away from the prevailing wind direction to enhance the airflow within the architectural complex. This research carries substantial implications for the renovation and planning of residential communities, particularly in large urban settings with a substantial population.

Fast marching method assisted permeability upscaling using a hybrid deep learning method coupled with particle swarm optimization

Geo-cellar models contain millions of gridblocks and are very time-consuming to simulate. This challenge necessitates upscaling geo-cellular models to obtain fit-for-purpose models for simulation. Simulation-based upscaling methods are computationally demanding, especially if there is a large number of geological realizations. On the other hand, static methods do not take into account the dynamics of the flow. In this paper, a novel hybrid deep learning-based upscaling method is proposed that can handle highly channelized and layered reservoir models. The proposed method combines the ConvLSTM network with the fast marching method (FMM), which is a computationally efficient method to get the dynamic response of the reservoir without the need for full-physics flow simulation. Since reservoir models have deposited during different geological periods, they have a temporal distribution along the third dimension. ConvLSTM layers can simultaneously extract spatiotemporal dependencies that other networks in the literature were not able to do so. The proposed method follows a two-step training process. In the first step, a variational autoencoder with ConvLSTM blocks (ConvLSTM-VAE) is trained and validated unsupervised using 10,000 permeability realizations. This network learns the data-generating distribution of the realizations and improves the overall upscaling process. Then, the acquired weights are used to initialize the ConvLSTM-FMM network, which is fine-tuned by the particle swarm optimization to accomplish the upscaling task by minimizing the difference between the pressure drop of the fine-scale and upscaled realizations calculated by the FMM. Validity of the FMM to estimate the BHP drop of the wells was verified on the utilized reservoir model. The advantage of the proposed data-driven method is that it can be trained once and used to upscale new realizations, contrary to conventional simulation-based methods that require running the entire process whenever the fine realizations change. The proposed network was applied to upscaling permeability realizations since absolute permeability is one of the most challenging properties to upscale because of its directional nature. Results showed the outstanding performance of the proposed method with a mean absolute percentage error, mean squared error, and coefficient of determination of 15.38, 0.18, and 0.81 on the test realizations, and outperformed the geometric mean and the simulation-based upscaling methods.

Inhibition of cMYC-MAX transcription factors hetero-dimerization with structurally engineered omoMYC to downregulate oncogenic pathways in renal carcinoma

In the current study, we employed, structural informatics, and molecular simulation-based methods to engineer OmoMyc, a c-Myc dominant negative protein, to design novel mutants that could abrogate the c-MYC-MAX complex in Renal Carcinoma (RC). Among the total 472 mutations, only six mutations A61Q, Q64E, Q64K, N77R, Q64E-N77R, and Q64K-N77R were reported to increase the binding affinity and subjected to subsequent analysis such as protein-protein docking. The docking results revealed that the predicted mutants improve the functionality of the OmoMyc by not only increasing the binding affinity but also vdW and electrostatic energy in each complex that consequently increase the binding of the engineered OmoMyc by establishing extra hydrogen bonds, salt-bridges, and non-bonded contacts. Molecular simulation revealed a more stable behavior by the mutant complexes in contrast to the native OmoMyc however structural perturbations were reported in the regions, DBD (DNA-binding domain), loop region, and minor deviations at CTD (C terminal domain). Moreover, the hydrogen bonding and binding free energy results further validated the promising activity of our predicted mutants of OmoMyc. The results for TBE (total binding energy) revealed that the for each complex the TBE was calculated to be −87.88 ± 0.16 kcal/mol (WT OmoMyc-MAX), −91.89 ± 0.21 kcal/mol (A61Q OmoMyc-MAX), −91.55 ± 0.20 kcal/mol (Q64E OmoMyc-MAX), −95.17 ± 0.24 kcal/mol (Q64K OmoMyc-MAX), −96.49 ± 0.22 kcal/mol (N77R OmoMyc-MAX), −97.76 ± 0.22 kcal/mol (Q64E-N77R OmoMyc-MAX), and −95.31 ± 0.20 kcal/mol (Q64K-N77R OmoMyc-MAX) respectively. The results for TBE revealed promising results that allow the mutants to competitively inhibit the c-Myc-MAX complex more swiftly. Additionally, the internal motion and energy landscape were altered. These findings provide important insights into the potential of the mutants of OmoMyc as a therapeutic candidate for cancer treatment, particularly renal carcinoma, and could pave the way for the development of more effective clinical versions of OmoMyc.

Developing a supervised learning-based simulation method as a decision support tool for rebalancing problems in bike-sharing systems

Bike-Sharing Systems (BSSs) have exploded in popularity worldwide because of their beneficial impacts on traffic, pollution levels, and public health, which has resulted in moving toward a green city. The rebalancing problem, as one of the most important operational problems of such systems, deals with planning bike distribution at different stations. Regarding conducted studies, simulation models are the most common tool for analyzing BSSs and decision-making. This popularity is based on simulation’s capabilities in modeling complexities of systems and uncertainty. Despite their advantages, lack of quickness is a significant drawback of simulation-based methods, making them inefficient for real-time decision-making processes, especially in large-scale and complex systems. In this regard, this paper introduces a Supervised Learning-Based Simulation (SLBS) method as an alternative to the conventional simulation-based methods dealing with rebalancing problems. SLBS is a huge step toward developing a real-time Decision Support System (DSS) for BSSs. For developing SLBS, firstly, we have developed a simulation model based on real-world assumptions of station-based BSSs and big data analysis of CitiBike, a well-known BSS located in New York City. The simulation model is able to calculate the number of unsatisfied demands (either number of failed pick-ups (FPs) or failed drop-offs (FDs)) as a result of different rebalancing plans. Then, the developed simulation model was used to generate quality and quantity training datasets to train Machine Learning (ML) algorithms involved in SLBS. While these ML models are trained once, SLBS will be capable of predicting the number of unsatisfied demands without running highly time-intensive simulations replications. The results obtained from a wide range of conducted experiments indicate that SLBS, up to 300 times faster than simulation models, can provide predictions with over 90% of R2 Score.

Simulation-based quantitative methods for vehicle emissions and a CO2 charging policy

With the worsening vehicle emissions, carbon emission charges are becoming an increasingly popular policy to reduce emissions. This paper proposes a policy to charge for the additional CO2 emissions due to the increasing traffic flow for each vehicle, thereby extending traditional travel time-based traffic assignment to emissions-charged traffic assignment. Considering that vehicle movements in the network are affected by signal timings and the car-following together with lanechanging interactions of different types of vehicles, microscopic traffic flow simulation is combined with a CO2 emission model to formulate the relations between link flow and emissions of different types of vehicles. Accordingly, the additional CO2 emissions due to increasing traffic flow are quantified and charged for each vehicle, leading to multi-vehicle-type and multi-criteria traffic assignment. Through an example network, the proposed flow-emissions model is verified and the impacts of different CO2 charging prices in the morning peak hour are investigated. Analysis of the results shows monotone increasing relations between price and reduced total emissions as well as increased revenue within the price range. In addition, the charging policy also leads to traffic assignment that achieves a system-optimal assignment since the CO2 pricing aligns with the general concept of pricing externality, thereby reducing the total travel time.

Modelling capture efficiency of single-cell RNA-sequencing data improves inference of transcriptome-wide burst kinetics.

Gene expression is characterized by stochastic bursts of transcription that occur at brief and random periods of promoter activity. The kinetics of gene expression burstiness differs across the genome and is dependent on the promoter sequence, among other factors. Single-cell RNA sequencing (scRNA-seq) has made it possible to quantify the cell-to-cell variability in transcription at a global genome-wide level. However, scRNA-seq data are prone to technical variability, including low and variable capture efficiency of transcripts from individual cells. Here, we propose a novel mathematical theory for the observed variability in scRNA-seq data. Our method captures burst kinetics and variability in both the cell size and capture efficiency, which allows us to propose several likelihood-based and simulation-based methods for the inference of burst kinetics from scRNA-seq data. Using both synthetic and real data, we show that the simulation-based methods provide an accurate, robust and flexible tool for inferring burst kinetics from scRNA-seq data. In particular, in a supervised manner, a simulation-based inference method based on neural networks proves to be accurate and useful when applied to both allele and nonallele-specific scRNA-seq data. The code for Neural Network and Approximate Bayesian Computation inference is available at https://github.com/WT215/nnRNA and https://github.com/WT215/Julia_ABC, respectively.