Table of Contents
Overview
Definitions of Modeling and Simulation
Modeling and Simulation (M&S) involves transforming expert knowledge into dynamic models to simulate and understand complex systems. This process tests theories and hypotheses about system behavior using various models, such as physical, mathematical, behavioral, or logical representations, which serve as the basis for simulations that generate data for decision-making.[5.1] [6.1] Simulation has evolved significantly, becoming essential across disciplines by shifting from a "model-based" to a "simulation-based" paradigm, crucial for tackling complex challenges.[10.1] In healthcare, the reliability of simulation models is vital for ensuring consistent and accurate simulation settings, which are necessary for understanding and predicting disease trajectories and informing clinical and policy decisions.[11.1] [13.1] The integration of artificial intelligence (AI) and machine learning is transforming M&S by enhancing the accuracy, efficiency, and applicability of simulation models. AI techniques enable intelligent optimization and fine-tuning through training with real or live data, fostering model verification and validation.[27.1] [31.1] AI programming methods contribute to developing more realistic and robust models, aiding users in conducting and interpreting simulation experiments.[32.1] The synergy between traditional methodologies and emerging technologies like AI highlights M&S's role in optimizing resource allocation and enhancing predictive accuracy in contemporary analysis and decision-making.[30.1]Importance in Decision Making
Modeling and simulation are indispensable tools that enhance decision-making across various fields by allowing professionals to analyze complex systems, predict outcomes, and make informed choices. These techniques enable the visualization and analysis of intricate systems in real-time, which is particularly valuable in today's fast-paced environment where rapid decision-making is crucial.[2.1] Simulation, defined as mimicking real-world processes through computational models, plays a vital role in disciplines such as engineering and healthcare.[3.1] By facilitating a deeper understanding of complex systems, simulations help reduce risks, optimize resource use, and provide opportunities for improvement.[4.1] In healthcare, simulation modeling addresses intricate system problems that are often too complex for analytic solutions, reflecting the dynamic interactions and interdependencies within the healthcare system.[8.1] The increasing prevalence of simulation models in medical research and healthcare management is evident, as these models effectively address complex challenges that traditional decision support systems cannot resolve.[9.1] Computational modeling and simulation (CM&S) significantly enhance the safety, quality, and compliance of medical devices. Case studies illustrate that CM&S has been successfully employed in the development of various medical technologies, including MRI systems, ablation technology, implant safety, and wearables, ultimately leading to cost reductions and improved device efficacy.[15.1] This growth in the use of CM&S underscores its critical role in advancing healthcare solutions and optimizing medical device design. In healthcare systems, modeling and simulation play a crucial role in enhancing decision-making. Discrete-event simulation (DES) is a prominent stochastic modeling approach that effectively addresses the complexities of dynamic healthcare environments. For instance, a discrete-event simulation model has been developed to support strategic decisions regarding hospital bed capacity, demonstrating its utility in optimizing service quality in outpatient settings.[25.1] This approach has been recognized for its effectiveness in improving healthcare outcomes, as evidenced by various case studies that highlight its application in real-world scenarios.[25.1] These examples underscore the significant impact of modeling and simulation on decision-making processes in healthcare, illustrating their importance in navigating the challenges of modern healthcare delivery.In this section:
History
Early Developments in Modeling and Simulation
The early developments in modeling and simulation (M&S) are significantly marked by the introduction of SIMULA I, a specialized derivative of ALGOL 60 designed for discrete systems simulation. By May 1962, Ole-Johan Dahl and Kristen Nygaard established the core concepts of SIMULA I, which became operational by early 1965. This language previewed key features of what would evolve into object-oriented programming, notably the combination of data structures with associated procedures, facilitating organized modular code.[49.1] SIMULA I's groundbreaking concepts have profoundly influenced the evolution of programming languages and software development methodologies, solidifying its legacy as the birthplace of object-oriented programming.[47.1] Although SIMULA is not widely used in contemporary practice, it opened the door for object-oriented abstractions that are now fundamental across nearly all modern programming languages and platforms. The principles of dynamic binding, inheritance, and encapsulation introduced by SIMULA remain essential even five decades later.[50.1] In parallel, the Monte Carlo method, which has its origins at Los Alamos National Laboratory in the 1940s, represented another significant advancement in simulation techniques. This method was developed by mathematicians Stanislaw Ulam and John von Neumann, alongside physicists like Enrico Fermi and Nicholas Metropolis, primarily for applications related to the atomic bomb project.[52.1] The Monte Carlo method employs statistical sampling to solve complex problems, and its implementation on early computers like ENIAC marked a transformative moment in computational simulation.[58.1] The collaboration between Stanislaw Ulam and John von Neumann significantly influenced the development of the Monte Carlo method. On March 11, 1947, von Neumann recognized the relevance of Ulam's suggestions and sent a handwritten letter to Robert Richtmyer, the Theoretical Division leader at Los Alamos, which included a detailed outline of a possible statistical approach to problem-solving.[53.1] Following their initial work, a series of Monte Carlo transport codes began to emerge from Los Alamos in the 1950s, reflecting the method's growing effectiveness in various applications.[56.1] Notably, the first computerized Monte Carlo simulation was executed on the ENIAC in April 1948 by a team that included John and Klara von Neumann and Nick Metropolis. This simulation not only marked the first use of the Monte Carlo method in a computerized format but also represented the first code written in the modern paradigm associated with the "stored program concept".[60.1] The development of ENIAC and similar early electronic computers also played a crucial role in shaping M&S methodologies. These computers allowed for the execution of complex simulations that bridged theoretical models and experimental data, establishing a new paradigm for computational research.[58.1] Early applications included reactor simulations and the modeling of nuclear weapons, which underscored the practical utility of M&S in addressing real-world challenges.[59.1] Thus, the early developments in modeling and simulation were characterized by groundbreaking programming innovations and the advent of powerful computational methods, setting the stage for future advancements in the field.Evolution of Simulation Technologies
The evolution of simulation technologies has undergone significant transformations since its inception, marked by key developments that have shaped the field. In the mid-1940s, the construction of the first general-purpose electronic computers, such as the ENIAC, laid the groundwork for the rapid growth of simulation. This period also saw the pioneering work of Stanislaw Ulam and John von Neumann, who utilized the Monte Carlo method on electronic computers to address complex problems in neutron diffusion related to hydrogen bomb design, which were analytically intractable at the time.[44.1] As the field progressed into the 1960s, various modeling techniques emerged, including those for online estimation of state variables and the carbon evolution rate (CER).[43.1] The introduction of user-friendly software for modeling and simulation further democratized access to these technologies, eliminating the need for advanced programming skills that had previously restricted their use to experts.[43.1] This shift has been pivotal in enabling a broader range of professionals to engage with simulation tools. In recent years, the integration of artificial intelligence (AI) and machine learning (ML) into simulation and modeling tools has revolutionized the analysis and optimization of complex systems. The rise of cloud-based simulation solutions has also transformed how organizations access and utilize modeling software, enhancing interoperability and sustainability.[61.1] These advancements have led to a growing demand for sophisticated simulation tools across various industries, as organizations seek to optimize processes, reduce costs, and improve decision-making.[63.1] The evolution of simulation technologies has progressed significantly from earlier languages like SIMULA I to more advanced systems such as SIMAN IV and CINEMA IV. The SIMAN language is recognized as a general-purpose Simulation ANalysis program used to model complex systems.[72.1] Accompanying SIMAN is Cinema, a flexible animation module that allows for the design and execution of realistic graphical depictions of SIMAN models.[72.1] The SIMAN IV environment integrates essential features such as model building, running, animation, and data analysis, which are critical for modern modeling and simulation practices.[73.1] Furthermore, the SIMAN/Cinema V system is designed to model discrete event, continuous, and combined discrete-continuous systems, highlighting the advancements in modeling capabilities that have emerged from this evolution.[74.1]In this section:
LanguageObject-oriented ProgrammingProgramming LanguagesDevelopment MethodologiesMonte Carlo Method
Recent Advancements
Integration of Machine Learning in M&S
Recent advancements in modeling and simulation (M&S) have increasingly incorporated machine learning (ML) techniques, particularly in the field of heat exchangers. Notable applications of ML methods include predicting heat transfer coefficients, pressure drops, and overall heat exchanger performance, facilitating real-time analysis of complex systems.[95.1] These machine learning-based surrogate models are crucial for modeling complex systems at a reduced computational cost. However, they require periodic re-evaluation and adaptation to ensure validity on future data, highlighting the importance of continuous assessment in integrating ML into traditional modeling approaches.[104.1] This ensures that the benefits of enhanced accuracy and efficiency are maintained across diverse datasets. Moreover, the role of artificial intelligence (AI) in M&S has proven transformative, enabling smarter combinatorial design of materials and the extraction of patterns at spatiotemporal scales previously unattainable with conventional computational methods.[100.1] The development of high-performance computing has further facilitated the testing of deep learning models with extensive parameters, overcoming limitations inherent in traditional computational techniques.[101.1] The adaptability of machine learning-based surrogate models is crucial as industries increasingly rely on these models to optimize processes and enhance decision-making capabilities, necessitating their periodic re-evaluation to ensure ongoing validity.[104.1]Advances in Multiscale Modeling Techniques
Recent advancements in multiscale modeling techniques have significantly influenced the design and production processes in additive manufacturing (AM). These advancements are particularly evident in the development of computational models for metal additive manufacturing (MAM) processes, which utilize particle methods to enhance the theoretical understanding of fundamental mechanisms at the powder or melt pool scale. This progress has improved the predictability of physics-based modeling approaches, thereby facilitating more efficient design and production workflows in AM.[98.1] Recent advancements in the field of design for additive manufacturing (DFAM) have highlighted the importance of simulation technologies and topology optimization. The main objective of these innovations is to provide insights into current trends that enhance the design and production processes within this domain.[97.1] Specifically, the application of simulation and optimization methods at various stages, particularly in part and process design, has proven to be significant. These methods do not require raw materials, machine tools, sample preparation, or special characterization techniques, which can lead to a reduction in resource exploitation.[96.1] Thus, the integration of these technologies is essential for improving efficiency and fostering innovation in additive manufacturing. Additionally, modeling and simulation are central to the evolution of smart manufacturing, which incorporates advanced technologies such as cloud computing, digital twins, and enhanced sensing and control systems. These technologies work in concert to create a more responsive and efficient manufacturing environment, further demonstrating the transformative potential of multiscale modeling techniques in the additive manufacturing sector.[99.1]In this section:
Applications
Use in Systems Engineering
Modeling and simulation (M&S) play a crucial role in systems engineering by providing a structured approach to analyze and optimize complex systems. M&S involves the use of various models—physical, mathematical, behavioral, or logical representations of systems—to facilitate simulations that inform managerial and technical decision-making.[124.1] This methodology has evolved significantly, particularly since its early applications in industrial control processes, which demonstrated the synergies between simulation, experimentation, and analysis techniques to solve typical engineering problems.[125.1] The development of simulation technology has its origins in World War II, a period that marked the beginning of its application in military contexts. This historical backdrop is crucial as it highlights key milestones in the evolution of simulation, including advancements in modeling languages and graphical interfaces.[129.1] In contemporary settings, simulations are widely recognized for their utility in training and technological development, particularly within military frameworks where they operate without the involvement of actual military forces.[128.1] This integration of simulation technology into various sectors underscores its significance in enhancing operational analysis and training methodologies. In systems engineering, the challenges associated with testing materials, processes, and equipment in the manufacturing industry can be significant and resource-intensive. To address these challenges, industry leaders increasingly turn to multiphysics modeling and simulation (M&S) for development, testing, and verification.[134.1] This reliance on M&S allows for more efficient exploration of complex interactions within systems, ultimately facilitating better decision-making and enhancing the overall development process.[134.1] By employing these advanced techniques, organizations can effectively navigate the difficulties of physical testing, leading to improved outcomes in manufacturing operations.[134.1] The application of modeling and simulation (M&S) has grown significantly, spanning numerous fields such as engineering, manufacturing, military operations, weather forecasting, and environmental management.[127.1] This comprehensive tool is essential for addressing complex challenges across various industries, as it relies on mathematical models to represent the behavior of real-world systems.[132.1] In today's fast-paced environment, innovative applications of M&S are transforming how experts approach these challenges, significantly enhancing design and analysis processes.[130.1] By embracing these advanced techniques, organizations can elevate their operational efficiency and improve their strategic decision-making capabilities.[130.1]In this section:
Tools And Techniques
Types of Models Used in M&S
Modeling and simulation (M&S) encompasses various types of models that serve as representations of systems, entities, phenomena, or processes. These models can be categorized based on their characteristics and the specific applications they are designed for. One primary distinction in modeling techniques is between static and dynamic models. Static models do not change over time, while dynamic models account for changes and interactions within the system over time.[170.1] Additionally, models can be classified as deterministic or stochastic. Deterministic models produce the same output for a given set of inputs, whereas stochastic models incorporate randomness and variability, often exemplified by Monte Carlo simulations.[170.1] Another important classification is between discrete and continuous models. Discrete models represent systems where changes occur at distinct intervals, while continuous models depict systems that change fluidly over time.[170.1] Furthermore, models can be categorized as discrete-event or time-stepped, which relates to how they simulate the progression of time and events within the modeled system.[170.1] In ecological modeling, one of the primary challenges is the confusion surrounding model validation, particularly when these models are utilized for decision support in areas such as pesticide regulation.[175.1] To ensure that simulation results are useful, researchers must demonstrate the reliability of model outputs by providing comprehensive information about model adequacy, limitations, prediction accuracy, and the likelihood of various scenarios.[173.1] This complexity underscores the importance of addressing the challenges associated with validating ecological models, as effective application hinges on overcoming these validation issues. In organizational contexts, scenario modeling is a vital technique that enables businesses to simulate various potential outcomes and assess their implications on financial, operational, or strategic decisions. By leveraging data, organizations can develop financial models based on several possible outcomes, which helps them prepare for potential challenges in a controlled and analytical manner.[177.1] Scenario planning allows decision-makers to identify a range of potential outcomes and estimated impacts, facilitating the evaluation of responses to both positive and negative possibilities.[180.1] It is crucial for organizations to integrate scenario modeling into their regular decision-making processes, as this practice not only aids in crisis aversion but also enhances responsiveness during stable periods.[178.1] Furthermore, what-if scenario-based modeling involves creating hypothetical situations to visualize and analyze potential impacts on project portfolios, thereby increasing the intelligence of project management.[179.1] In manufacturing environments, modeling and simulation techniques are employed to enhance efficiency and productivity. Real-time data models, for instance, facilitate better monitoring and control of manufacturing processes, helping to identify areas for optimization despite the challenges of implementation in complex systems.[182.1]Challenges And Limitations
Issues in Model Validation
Model validation in the context of modeling and simulation presents several significant challenges that can impact the reliability and credibility of the results produced. One of the primary issues is the methodological pitfalls associated with cross-validation and the effects of data structure on performance metrics. For instance, reusing test data during model selection can inflate performance estimates, highlighting the necessity for a proper separation of training, validation, and test sets to avoid evaluation bias.[211.1] This bias can lead to discrepancies between estimated performance and true generalization performance, which can only be approximated through extensive evaluation on unseen data.[211.1] Moreover, the complexity of models can further complicate validation efforts. As models become more intricate, they often require more data, which can introduce additional challenges in ensuring both model and simulation correctness.[208.1] The lack of universal methodologies for verification and validation, coupled with the unavailability of reliable real-world data, exacerbates these issues.[221.1] Additionally, different perspectives among stakeholders can lead to varying interpretations of model validity, complicating consensus on model reliability.[221.1] Validation processes must also consider the conceptual models that underpin simulation studies. These models encompass research questions, requirements, inputs, outputs, and assumptions, all of which provide essential context for evaluating the simulation's outcomes.[214.1] The need for thorough validation is underscored by the increasing reliance on simulation models for decision-making in various sectors, including business and government.[219.1] However, the balance between the urgency of decision-making and the rigorous validation processes required for credible modeling remains a critical challenge.[220.1]Computational Constraints
The complexity of modeling and simulation in engineering systems is significantly influenced by computational constraints. This paper aims to compare the complexity and computational efficiency of co-simulation and closure modeling techniques, which are employed in complex system modeling and simulation applications that seek to capture multi-scale and multi-domain dynamics.[235.1] While both techniques share similar goals, the differences in their methods result in varying levels of complexity and computational efficiency for simulation models developed using each technique.[236.1] Therefore, understanding these differences is crucial for effectively balancing model accuracy and computational efficiency in engineering applications. Co-simulation and closure modeling techniques, while aiming for similar outcomes, exhibit distinct differences in their methodologies, which in turn affect the complexity and computational efficiency of the resulting simulation models.[236.1] For instance, electrochemistry-based battery models, commonly used in battery management systems, exemplify this challenge due to their inherent computational complexity. Research has highlighted the impact of model simplifications on the trade-off between accuracy and computation time, specifically in the context of the Doyle-Fuller-Newman (DFN) model.[237.1] Moreover, the evolution of computational platforms has introduced new challenges in the design and execution of simulations. These platforms have undergone significant changes, which necessitate adaptations in modeling approaches to effectively manage the increased complexity of the systems being simulated.[238.1] Thus, addressing computational constraints remains a critical aspect of advancing modeling and simulation practices in complex systems.In this section:
Future Directions
Emerging Trends in M&S
Emerging trends in modeling and simulation (M&S) are significantly reshaping various fields, driven by advancements in technology and the increasing complexity of systems. One notable trend is the integration of artificial intelligence (AI) and machine learning (ML) into simulation tools, which is revolutionizing the analysis and optimization of complex systems. This integration enhances decision-making capabilities and allows for more sophisticated modeling approaches, thereby meeting the rising demand for advanced simulation tools across industries.[245.1] In the realm of space exploration, NASA's Entry Systems Modeling (ESM) project exemplifies the application of these advancements. Established in 2013, the ESM project focuses on developing validated tools and frameworks for planning and optimizing Entry, Descent, and Landing (EDL) missions. This initiative aims to improve the reliability of simulations related to reentry, which is crucial for addressing the unique challenges posed by different planetary atmospheres.[269.1] The project emphasizes the need for continuous evolution of modeling and simulation capabilities to support the next generation of planetary EDL missions.[268.1] Moreover, recent advancements in computational methods have enabled the modeling, simulation, and optimization of complex systems in various engineering fields, including materials and energy systems. These developments are increasingly validated against experimental data, confirming the efficacy of AI algorithms in optimizing energy systems.[244.1] The shift towards cloud-based simulation tools has also transformed access to modeling software, facilitating collaboration and interoperability among users.[245.1] Additionally, innovative applications of M&S are emerging across diverse industries, enhancing design and analysis processes. These applications are not only improving organizational efficiency but also enabling more informed decision-making.[246.1] For instance, AnyLogic's integration with NVIDIA Omniverse allows for realistic 3D animations in simulation models, which can be applied in sectors ranging from manufacturing to logistics.[247.1]Potential Impact of Artificial Intelligence
The integration of artificial intelligence (AI) and machine learning (ML) into modeling and simulation is poised to significantly transform various industries by enhancing predictive capabilities and automating decision-making processes. AI and ML technologies are becoming essential tools for companies, unlocking new potentials in existing processes and fostering innovative approaches to simulation.[250.1] As these technologies evolve, they are expected to drive greater levels of automation, optimization, and predictive capabilities in engineering design, thereby revolutionizing the design process.[260.1] Recent advancements in simulation technology, particularly through the use of multiphysics simulation tools, allow engineers to evaluate a broader range of options more rapidly, which improves product performance while simultaneously reducing development time and costs.[252.1] The incorporation of AI into simulation software is anticipated to yield faster time to market and enhanced product performance, marking a significant shift in user priorities towards advanced engineering simulation tools.[252.1] Furthermore, AI-enhanced simulations are particularly beneficial in industries where accuracy and efficiency are critical, such as automotive, aerospace, and materials science.[253.1] A notable trend in simulation-based optimization is the integration of AI and ML algorithms, which enhance simulations by automating solution discovery and processing large datasets to uncover hidden patterns.[254.1] This integration not only improves the efficiency of simulations but also embeds real-time predictive capabilities into the software, allowing for dynamic systems to operate independently and make strategic decisions without human intervention.[255.1] The use of digital twins, which simulate entire production lines and urban infrastructures, exemplifies how AI can refine resource utilization and minimize waste.[255.1] Moreover, the combination of modeling and simulation (M&S) with AI methods has been shown to create hybrid models that are more powerful than either approach alone, enhancing predictive accuracy and efficiency.[256.1] In the realm of healthcare, advanced AI and ML algorithms have demonstrated their potential in unlocking clinically relevant information from large datasets, leading to accurate predictions and valuable insights for various applications.[258.1] Similarly, in hydrology, AI-driven models are becoming crucial for addressing global water challenges, emphasizing the importance of AI in enhancing predictive capabilities across diverse fields.[259.1] The future of engineering and manufacturing is poised for transformation through the convergence of artificial intelligence (AI), machine learning (ML), and simulation technologies. These advancements are expected to drive significant improvements in efficiency, innovation, and sustainability within the industry.[261.1] As AI algorithms become increasingly sophisticated and simulation software evolves, we anticipate enhanced levels of automation, optimization, and predictive capabilities in design processes.[260.1] Emerging trends, such as the integration of ML with the Internet of Things (IoT) and digital twins, will facilitate the development of dynamic, predictive systems, including self-learning supply chains.[261.1] This evolution underscores the potential for AI-powered simulations to revolutionize the way we approach modeling and simulation in engineering design.[260.1]In this section:
References
[2] Innovative Applications of Modeling and Simulation in Expert Fields — In today's fast-paced world, innovative applications of modeling and simulation are transforming how experts approach complex challenges across various industries. These advanced techniques not only enhance accuracy but also significantly speed up the decision-making process, allowing teams to visualize and analyze intricate systems in real-time. Imagine being able to predict the behavior of
[3] Exploring the Scope of Simulation: Methods, Diverse Applications, and ... — Simulation, the act of mimicking real-world processes, systems, or phenomenon through computational models, plays a significant role in various disciplines such as engineering, healthcare
[4] The Role of Simulation in Informed Decision-Making — Simulation plays a critical role by enabling better informed and confident decision-making across many different domains and industries. They help us to better understand complex systems, reduce risks, enable efficient use of resources, and provide opportunities for optimization.
[5] Modeling and Simulation - an overview | ScienceDirect Topics — Modeling and Simulation refers to the process of converting expert knowledge into dynamic models and simulating them to understand systems better. It involves creating meaningful simulation models based on existing knowledge to test theories and hypotheses about how a system works.
[6] Modeling and simulation - Wikipedia — Modeling and simulation Modeling and simulation (M&S) is the use of models (e.g., physical, mathematical, behavioral, or logical representation of a system, entity, phenomenon, or process) as a basis for simulations to develop data utilized for managerial or technical decision making. A collection of applicative modeling and simulation method to support systems engineering activities in provided in. Department of Scientific Computing, Modeling and Simulation (M.Tech (Modelling & Simulation)) (Savitribai Phule Pune University, India) Modeling and Simulation Body of Knowledge[edit] ^ "Department of Defense INSTRUCTION NUMBER 5000.61: Modeling and Simulation (M&S) Verification, Validation, and Accreditation" (PDF). ^ "Department of Defense DIRECTIVE NUMBER 5000.59: DoD Modeling and Simulation (M&S) Management" (PDF). Modeling and Simulation-Based Systems Engineering Handbook (1st ed.).
[8] Simulation modeling to assess performance of integrated healthcare ... — Simulation modeling techniques can use system thinking and evaluate performance emphasizing the complex relations between system components, in topics of relevance for integrated healthcare systems. By using simulation models to complement the performance assessment of integrated health systems, managers can correctly attribute causality to
[9] Simulation Modelling in Healthcare: Challenges and Trends — Introduction A proliferation in simulation models in the domain of medical research and management of healthcare services is evident. This growth is driven by the leveraging capability of these simulation models in addressing complex problems that cannot be addressed by decision support systems.
[10] The Evolution of Simulation and Its Contribution to Many Disciplines — The aims of this chapter are: (1) To provide a comprehensive view of the stages of the evolution of simulation . (2) To emphasize the phenomenal developments in many aspects of simulation which made it an important and even a vital infrastructure for many disciplines. (3) To underline the fact that the transition from "model-based" paradigm to "simulation-based" paradigm may be
[11] Reliability in Healthcare Simulation Setting: A Definitional Review — In other words, in HPE more broadly, reliability refers to the consistency and accuracy of the measurement tool, while in the specific case of simulation design, it refers to the consistency and accuracy of the simulation setting developed . Yet, uses of these concepts and terms of simulation reliability do not appear to be fixed across
[13] Credible practice of modeling and simulation in healthcare: ten rules ... — The complexities of modern biomedicine are rapidly increasing. Thus, modeling and simulation have become increasingly important as a strategy to understand and predict the trajectory of pathophysiology, disease genesis, and disease spread in support of clinical and policy decisions. In such cases, inappropriate or ill-placed trust in the model and simulation outcomes may result in negative
[15] Medical Device R&D: Simulation Success Stories - Engineering.com — In healthcare, computational modeling and simulation (CM&S) enhance medical device safety, quality, and compliance. This eBook highlights four teams using CM&S to create effective devices and reduce costs, covering MRI systems, ablation technology, implant safety, wearables, and design optimization. In this eBook, you will learn how four teams from around the world are using CM&S to create
[25] Discrete-Event Simulation Modeling in Healthcare: A Comprehensive ... — Discrete-Event Simulation Modeling in Healthcare: A Comprehensive Review Discrete-event simulation (DES) is a stochastic modeling approach widely used to address dynamic and complex systems, such as healthcare. Keywords: discrete-event, simulation, modeling, healthcare, hospital, review, literature 183.Devapriya P., Strömblad C.T.B., Bailey M.D., Frazier S., Bulger J., Kemberling S.T., Wood K.E. StratBAM: A Discrete-Event Simulation Model to Support Strategic Hospital Bed Capacity Decisions. 195.Mohammed M.A., Mohsin S.K., Mohammed S.J. The Effectiveness of Using Discrete Event Simulation to Optimize the Quality of Service of Outpatient in Iraq: A Case Study. 225.Demirli K., Al Kaf A., Simsekler M.C.E., Jayaraman R., Khan M.J., Tuzcu E.M. Using lean techniques and discrete-event simulation for performance improvement in an outpatient clinic.
[27] Artificial Intelligence in Modeling and Simulation - MDPI — The Special Issue on "Artificial Intelligence in Modeling and Simulation" presents a collection of papers demonstrating the significant impact of artificial intelligence (AI) on various aspects of modeling and simulation (MS). This reprint features 11 selected papers that focus on integrating AI techniques to improve simulation models' accuracy, efficiency, and applicability across different
[30] The role of simulation and modeling in artificial intelligence: A ... — Our review highlights how AI leverages simulation and modeling to improve predictive accuracy, optimize resource allocation, and enhance decision-making processes across diverse sectors. We also discuss the potential future directions in the integration of simulation and modeling with AI, emphasizing its significance in various fields.
[31] Artificial Intelligence in Modeling and Simulation - MDPI — AI and machine learning techniques enable the intelligent optimization and fine-tuning of simulation models, for example by training models with real system data or by effectively synchronizing models with live data, fostering both model verification and validation.
[32] Artificial Intelligence, Simulation, and Modeling - JSTOR — Artificial intelligence programming methods permit more realistic and robust simulation models and help the user develop, run, and interpret simulation experiments.
[43] History and Evolution of Modeling in Biotechnology: Modeling ... — The development of novel and readily accessible software for modeling and simulation furthermore eliminated the necessity of advanced programming skills which were so far restricted to ... Different model techniques for online estimation of state variables were developed over time: (i) 1960s ... and the carbon evolution rate (CER).
[44] PDF — 3 THE FORMATIVE PERIOD (1945–1970) In the mid-1940s two major developments set the stage for the rapid growth of the field of simulation: • The construction of the first general-purpose electronic computers such as the ENIAC (Burks and Burks 1981); and 310 978-1-4244-5771-7/09/$26.00 ©2009 IEEE Goldsman, Nance, and Wilson • The work of Stanislaw Ulam, John von Neumann, and others to use the Monte Carlo method on electronic comput-ers in order to solve certain problems in neutron diffusion that arose in the design of the hydrogen bomb and that were (and still are) analytically intractable (Cooper 1988).
[47] The Enduring Influence Of Simula: The Birth Of Object-oriented Programming — Simula's groundbreaking concepts have had a profound impact on the evolution of programming languages and software development methodologies. Its influence can be seen in numerous modern programming languages, solidifying its legacy as the birthplace of object-oriented programming. Simula's principles of encapsulation, inheritance
[49] Simula: The Pioneering Object-Oriented Programming Language — By May 1962, Nygaard and Dahl established the core concepts of what they termed SIMULA I - a specialized ALGOL 60 derivative for discrete systems simulation.. Operational by early 1965, Simula I already previewed hallmarks of what would become object-oriented programming - combining data structures with associated procedures for organized modular code.
[50] Simula: The World's First Object-Oriented Programming Language — So while no longer used much in practice, Simula opened the door for object-oriented abstractions taken for granted now across nearly all modern programming languages and platforms. Conclusion In the end, Simula pioneered almost all the basic object-oriented concepts still essential five decades later - dynamic binding, inheritance, classes
[52] Monte Carlo - History and People - UW Faculty Web Server — The Monte Carlo method has its roots in statistical sampling, computing, and the Manhattan project. The major players in its invention and initial use were mathematicians Stanislaw Ulam and John von Neumann and physicists Enrico Fermi and Nicholas Metropolis. Here's some history written by some of the people who participated in its early days:
[53] PDF — John von Neumann saw the relevance of Ulam's suggestion and, on March 11, 1947, sent a handwritten letter to Robert Richtmyer, the Theoretical Division lead-er (see "Stan Ulam, John von Neumann, and the Monte Carlo Method"). His let-ter included a detailed outline of a pos-sible statistical approach to solving the
[56] PDF — In the fifties, shortly after the work on the Monte Carlo method by Ulam, von Neumann, Fermi, Metropolis, Richtmyer, and others, a series of Monte Carlo transport codes began emerging from Los Alamos.
[58] Computer Simulations Then and Now: an Introduction and Historical ... — He argued that they gave rise to an "artificial reality" at the border of theory and experiment. The Monte Carlo method and its implementation on the ENIAC computer, in this view, constituted not only a paradigmatic simulation, but also a template upon which later computer simulations were built.
[59] ENIAC Tries Its Luck | Eniac in Action: Making and Remaking the Modern ... — It finishes with an exploration of further Monte Carlo work run on ENIAC, including reactor simulations, simulation of uranium-hydride bombs, and in 1950 simulation of the "Super" concept for a hydrogen weapon. Keywords: Von Neumann, Klara, Von Neumann, John, Monte Carlo method, Los Alamos, Flow diagram, Nuclear fission Subject
[60] PDF — Mark Priestley Crispin Rope From rich archival sources, the authors reconstruct the evolution of a program first run on ENIAC in April 1948 by a team including John and Klara von Neumann and Nick Metropolis. This was not only the first computerized Monte Carlo simulation, but also the first code written in the modern paradigm, usually associated with the "stored program concept," ever
[61] Trends in the Development of Simulation and Modeling Tools — Trends in the Development of Simulation and Modeling Tools Trends in the Development of Simulation and Modeling Tools Trends in the Development of Simulation and Modeling Tools As organizations seek to optimize processes, reduce costs, and improve decision-making, the demand for sophisticated simulation and modeling tools continues to rise. The integration of artificial intelligence (AI) and machine learning (ML) into simulation and modeling tools is revolutionizing how complex systems are analyzed and optimized. The shift toward cloud-based simulation tools has transformed how organizations access and utilize modeling software. The development of simulation and modeling tools is rapidly evolving, driven by trends such as enhanced user interfaces, the integration of AI and machine learning, the rise of cloud-based solutions, a focus on interoperability, and a commitment to sustainability.
[63] Improving Usability and Broadening Adoption of Simulation With ... — Industries that require engineering design and manufacturing increasingly adopt advanced modeling and simulation (M&S) tools to accelerate their ability to deliver products and innovate quickly in response to market demands. These tools provide transformative scientific and engineering insights at a previously unattainable rate, which in turn provide immense opportunities such as reduced
[72] Introduction to SIMAN/Cinema - ACM Digital Library — The SIMAN language (Pegden 1982) is a general-purpose Simulation ANalysis program used to model complex systems. Accompanying SIMAN is Cinema (Systems Modeling 1985), a flexible animation module used to design and run realistic graphical depictions of a SIMAN model. Although many applications of SIMAN/Cinema have
[73] Introduction to SIMAN IV - computer.org — The SIMAN IV environment integrates model building, running, animation, and data analysis. The authors discuss the SIMAN IV simulation environment and the concepts and methods for simulating manufacturing systems using the SIMAN IV simulation language.
[74] (PDF) Introduction to SIMAN/Cinema - Academia.edu — SIMAN/Cinema V is a general-purpose simulation language and animation system designed to model discrete event, continuous, and combined discretel continuous systems. This paper presents an overview of the SIMAN/Cinema V modeling capabilities and ... 91 6.6.1 The main features of the language 91 6.6.2 The syntax of the SLIM language 6.6.3 Output
[95] Recent advances in the applications of machine learning methods for ... — In recent years, there have been notable advances in the application of machine learning methods in the field of heat exchangers, such as using machine learning to predict heat transfer coefficients (Section 3.2.1), pressure drop (Section 3.2.2), and heat exchanger performance (Section 3.2.3) performing real-time analysis of complex
[96] Simulation and Its Use in Additive Manufacturing — Based on the classification by Wiberg et al. (), it can be perceived that the application of simulation and optimization methods at different stages, especially in part and process design, is meaningful.3.1 Simulation Process. Modeling and simulation do not require raw materials, machine tools, sample preparation, and special characterization methods, which can reduce resource exploitation
[97] Optimization and Simulation of Additive Manufacturing Processes ... — The main objective of this chapter is to provide the current trends and innovations in the field of design for additive manufacturing (DFAM), topology optimization, and simulation technologies.
[98] Full article: Modelling and simulation of metal additive manufacturing ... — In this paper, we review recent advances in developing computational models for metal additive manufacturing (MAM) processes using particle methods, in the theoretical understanding of the fundamental mechanisms that control such processes at the powder (or melt pool) scale, and in the predictability of physics-based modelling approaches.
[99] Computational Modelling and Simulation for Additive Manufacturing - Nature — Modeling and simulation are also central to recent trends in smart manufacturing, which integrate emerging technologies—such as advanced sensing and control, cloud computing, and digital twins
[100] Artificial intelligence in computational materials science — The impact of AI/ML is not limited to just smarter combinatorial design of materials. It is now also possible to train AI and ML models to gain fundamental understanding and extract patterns at spatiotemporal scales that were previously impossible with conventional computational materials modeling or with the best available theories.
[101] Artificial Intelligence in Material Engineering: A review on ... — The role of artificial intelligence (AI) in material science and engineering (MSE) is becoming increasingly important as AI technology advances. The development of high-performance computing has made it possible to test deep learning (DL) models with significant parameters, providing an opportunity to overcome the limitation of traditional computational methods, such as density functional
[104] Efficient learning of accurate surrogates for simulations of complex ... — Machine learning-based surrogate models are important to model complex systems at a reduced computational cost; however, they must often be re-evaluated and adapted for validity on future data
[124] Modeling and simulation - Wikipedia — Modeling and simulation Modeling and simulation (M&S) is the use of models (e.g., physical, mathematical, behavioral, or logical representation of a system, entity, phenomenon, or process) as a basis for simulations to develop data utilized for managerial or technical decision making. A collection of applicative modeling and simulation method to support systems engineering activities in provided in. Department of Scientific Computing, Modeling and Simulation (M.Tech (Modelling & Simulation)) (Savitribai Phule Pune University, India) Modeling and Simulation Body of Knowledge[edit] ^ "Department of Defense INSTRUCTION NUMBER 5000.61: Modeling and Simulation (M&S) Verification, Validation, and Accreditation" (PDF). ^ "Department of Defense DIRECTIVE NUMBER 5000.59: DoD Modeling and Simulation (M&S) Management" (PDF). Modeling and Simulation-Based Systems Engineering Handbook (1st ed.).
[125] History and Background of Modeling and Simulation - GradesFixer — This historical milestone opened the doors for the application of simulation in the field of industrial control processes. It also highlighted the synergies generated by simulation based on experimentation and analysis techniques to discover exact solutions to typical industry and engineering problems (Lander, 2008). ... History and Background
[127] Simulation and its application | PPT - SlideShare — The document provides some historical background on the growth of simulation and its applications. Examples of simulation applications are discussed in various fields like engineering, manufacturing, military, weather forecasting, and more. ... The presentation topic is introduced as simulation, modeling, its applications, advantages, and
[128] PDF — Background and Information Much of the literature on the use of simulations pertains to its utility in training or for technological development. The most agreed upon definition of a modern-day military simulation is a model or simulation whose operation does not involve the use of actual military forces and whose
[129] (PDF) A Comprehensive Review of Simulation Technology: Development ... — Secondly, the article traces the development of simulation technology from its origins in World War II to the present, summarizing key milestones such as modeling languages, graphical interfaces
[130] Innovative Applications of Modeling and Simulation in Expert Fields — Innovative Applications of Modeling and Simulation in Expert Fields - Simultech Innovative Applications of Modeling and Simulation in Expert Fields Innovative Applications of Modeling and Simulation in Expert Fields In today’s fast-paced world, innovative applications of modeling and simulation are transforming how experts approach complex challenges across various industries. Innovative Applications of Modeling and Simulation Advanced techniques in modeling and simulation significantly enhance design and analysis across multiple industries. Embracing innovative applications of modeling and simulation can significantly elevate your organization’s efficiency and decision-making capabilities. Posted in Modeling and simulation techniques Modeling is a crucial tool in today’s decision-making landscape, whether you’re optimizing a business process, simulating the behavior of a… Innovative Applications of Modeling and Simulation in Expert Fields
[132] PDF — This comprehensive tool spans numerous fields, from engineering and natural sciences to social sciences and economics. Here's a detailed look at the fundamental aspects of computer simulation, its applications, benefits, and limitations. Simulations rely on mathematical models to represent the behavior of real-world systems.
[134] Modeling and Simulation in the Manufacturing Industry - COMSOL — Modeling and Simulation Across Industries Manufacturing Materials, processes, and equipment used in the manufacturing industry can be challenging or resource intensive to test physically. This is why industry leaders turn to multiphysics modeling and simulation for development, testing, and verification.
[170] PDF — An Introduction to the Use of Modeling and Simulation Throughout the Systems Engineering Process 10 Modeling and Simulation Techniques Technique decisions to be made, based on application -Static vs. dynamic -Deterministic vs. stochastic ("Monte Carlo") -Discrete vs. continuous -Discrete-event vs. time-stepped
[173] Uncertainty analysis in ecological studies: an overview — If simulation results are to be useful, researchers must show the reliability of the model output by providing information about model adequacy and limitations, prediction accuracy, and the likelihood of scenarios (Clark et al. 2001, Katz 2002). Citation Li, Harbin; Wu, Jianguo. 2006. Uncertainty analysis in ecological studies: an overview.
[175] Merging validation and evaluation of ecological models to 'evaludation ... — Confusion about model validation is one of the main challenges in using ecological models for decision support, such as the regulation of pesticides. ... Verification and validation of simulation models. Proceedings of the 2005 Winter Simulation Conference, Syracuse NY, USA, Orlando, Florida (2005) Google Scholar.
[177] Four Best Practices for Scenario Modeling - insightsoftware — By leveraging data, organizations can simulate various scenarios to better understand the financial, operational, or strategic implications of decisions. ... and prepare for potential challenges in a controlled, analytical way. Scenario modeling is the practice of developing financial models based on several possible outcomes, and developing
[178] Future-Proof Your Strategies with Scenario Modeling - Meisterplan — Best Practices for Successful Scenario Modeling. The biggest mistake organizations make with scenario modeling is failing to integrate it into their regular decision-making process. While scenario modeling is incredibly useful in looking for ways to avert crises, the important part is to keep it up even when things appear calm.
[179] PMO Best Practices: What-If Scenario-Based Modeling Tools - Sciforma — What-if scenario-based modeling involves creating hypothetical situations or scenarios to assess their potential impact on project portfolios. By simulating various scenarios, PMOs can visualize and analyze potential outcomes based on different sets of assumptions and variables. Because it increases the responsiveness and intelligence of project portfolio management, scenario modeling is
[180] Scenario Planning: Strategy, Steps and Practical Examples — For businesses, scenario planning enables decision-makers to identify ranges of potential outcomes and estimated impacts, evaluate responses and manage for both positive and negative possibilities. We recommend that all companies perform at least rudimentary scenario planning, even if it's in the context of a business continuity exercise. The fundamentals of scenario planning are the same, even if the particulars across industries and within businesses vary. The leadership team hadn't undertaken any scenario planning, but its CFO had lived through both the dot-com bubble(opens in new tab) and the Great Recession(opens in new tab) and was ready to act quickly to protect Gimbloo's runway. Strategies to Manage Scenario Planning Projects Here are some key issues in managing scenario planning scope creep: Strategies to Manage Scenario Planning Projects
[182] Real-Time Models for Manufacturing Processes: How to Build ... - MDPI — New data science and real-time modeling techniques facilitate better monitoring and control of manufacturing processes. By using real-time data models, industries can improve their processes and identify areas where resources are being wasted. Despite the challenges associated with implementing these data models in transient and multi-physical processes, they can significantly optimize
[208] What are the main challenges and limitations of simulation for process ... — A third challenge of simulation is to manage the complexity of the model and the simulation. As the process becomes more complex, the model may also become more complicated, requiring more data
[211] Common pitfalls in evaluating model performance and strategies for ... — This study addresses two central issues in model evaluation – methodological pitfalls in cross-validation (CV) and data-structure effects on performance metrics – across five simulation experiments supplemented by real-world data. Second, we demonstrate that reusing the test data during model selection (e.g., feature selection, hyperparameter tuning) inflates performance estimates, reinforcing the need for proper separation of training, validation, and test sets. However, there is always an evaluation bias between the estimated performance E[gˆ] and the true generalization performance G, which can only be approximated by evaluating the same model on an infinite number of unseen data. A high evaluation variance suggests that the performance is sensitive to the choice of data folds, and a small size or an over-complex model can lead to a high evaluation variance.
[214] Potential and Challenges of Assurance Cases for Simulation Validation — Simulation studies require thorough validation to ensure model accuracy, reliability, and credibility. While validation typically focuses on the simulation model itself, additional artifacts also influence study outcomes. Conceptual models, comprising research questions, requirements, inputs and outputs, model content, assumptions, and simplifications, provide context information for
[219] Modeling and simulation verification and validation challenges — Modeling and simulation results provide vital information for decisions and actions in many areas of business and government. Verification and validation (V&V) are processes that help to ensure that models and simulations are correct and reliable.
[220] Verification and validation of computer simulation models — Verification and validation of computer simulation models is conducted during the development of a simulation model with the ultimate goal of producing an accurate and credible model. "Simulation models are increasingly being used to solve problems and to aid in decision-making.The developers and users of these models, the decision makers using information obtained from the results of
[221] Simulation models verification and validation: Recent development and ... — As a challenge of verification and validation processes, lack of universal methodologies, lack of reliable real-world data for validation, inaccuracy of real-world data for the intended purpose, different world views by different individuals, and the rapid growth and complexity of simulation modeling are identified as the hindering factors of
[235] Comparing the Complexity and Efficiency of Composable Modeling ... - MDPI — The goal of this paper is to compare the complexity and computational efficiency of the co-simulation and closure modeling techniques for complex system modeling and simulation applications that seek to capture multi-scale and/or multi-domain dynamics.
[236] Comparing the Complexity and Efficiency of Composable Modeling ... — While the two techniques have similar goals, differences in their methods lead to differences in the complexity and computational efficiency of a simulation model built using one technique or the other.
[237] Model simplifications and their impact on computational complexity for ... — Abstract Using electrochemistry-based battery models in battery management systems remains challenging due to their computational complexity. In this paper, we study for the first time the impact of several types of model simplifications on the trade-off between model accuracy and computation time for the Doyle-Fuller-Newman (DFN) model.
[238] Computational challenges in modeling & simulation of complex systems ... — Modeling and simulation faces many new computational challenges in the design of complex engineered systems. The systems that need to be modeled are increasingly interconnected and interdependent, achieving unprecedented levels of complexity. The computational platforms upon which simulations execute have undergone dramatic changes in recent years. Position statements by leading researchers
[244] Advanced Computational Methods for Modeling, Prediction and ... — This paper provides a comprehensive review of recent advancements in computational methods for modeling, simulation, and optimization of complex systems in materials engineering, mechanical engineering, and energy systems. Since this paper reviews recent developments in artificial intelligence and computational methods focusing on the modeling, simulations, and optimization of complex systems in materials science, we should start by discussing emerging trends in AI, as now we can conduct virtual simulations that provide us with a depiction of the information landscape based on current knowledge. The modeling studies conducted in the works mentioned above, validated based on the experimental data sets, confirm the possibility of using practical artificial intelligence algorithms as advanced techniques for optimizing energy systems.
[245] Trends in the Development of Simulation and Modeling Tools — Trends in the Development of Simulation and Modeling Tools Trends in the Development of Simulation and Modeling Tools Trends in the Development of Simulation and Modeling Tools As organizations seek to optimize processes, reduce costs, and improve decision-making, the demand for sophisticated simulation and modeling tools continues to rise. The integration of artificial intelligence (AI) and machine learning (ML) into simulation and modeling tools is revolutionizing how complex systems are analyzed and optimized. The shift toward cloud-based simulation tools has transformed how organizations access and utilize modeling software. The development of simulation and modeling tools is rapidly evolving, driven by trends such as enhanced user interfaces, the integration of AI and machine learning, the rise of cloud-based solutions, a focus on interoperability, and a commitment to sustainability.
[246] Innovative Applications of Modeling and Simulation in Expert Fields — Innovative Applications of Modeling and Simulation in Expert Fields - Simultech Innovative Applications of Modeling and Simulation in Expert Fields Innovative Applications of Modeling and Simulation in Expert Fields In today’s fast-paced world, innovative applications of modeling and simulation are transforming how experts approach complex challenges across various industries. Innovative Applications of Modeling and Simulation Advanced techniques in modeling and simulation significantly enhance design and analysis across multiple industries. Embracing innovative applications of modeling and simulation can significantly elevate your organization’s efficiency and decision-making capabilities. Posted in Modeling and simulation techniques Modeling is a crucial tool in today’s decision-making landscape, whether you’re optimizing a business process, simulating the behavior of a… Innovative Applications of Modeling and Simulation in Expert Fields
[247] Simulation modeling trends to follow in 2025 - anylogic.com — AnyLogic’s integration with NVIDIA Omniverse brings realistic 3D animation to simulation models, making it a powerful asset across various industries, from manufacturing to logistics. In one of our blog posts, we explain how ChatGPT can assist you in building and enhancing simulation models in AnyLogic. AnyLogic also supports reinforcement learning (RL) integration through Python and Java APIs, allowing users to link simulation models with popular RL libraries. Integrating MQTT with simulation models allows AnyLogic users to create highly dynamic, real-time connected environments where models respond instantly to incoming IoT data. In 2024, we shared blog posts covering AnyLogic updates, practical tips, real-world use cases, and the latest trends in simulation modeling. AnyLogic advances 3D animation in simulation modeling with NVIDIA Omniverse
[250] AI and Machine Learning in Simulation - Dassault Systèmes — Artificial intelligence (AI) and machine learning (ML) have become crucial tools within companies across many industries, unlocking new potential of existing processes and allowing entirely new forms of innovation. AI and ML offer significant benefits for users when implemented in the simulation process.
[252] Engineering simulation in the age of AI | McKinsey - McKinsey & Company — Engineering simulation in the age of AI | McKinsey Engineering simulation in the age of AI Multiphysics simulation tools allow engineers to evaluate more options more quickly, improving product performance while reducing development time and costs. Today, artificial intelligence and machine learning (AI/ML) technologies have the potential to change the game again, promising faster time to market, better product performance, and disruptive improvements in simulation speed. In 2023, a McKinsey survey conducted in partnership with NAFEMS showed that technological advances, changing market conditions, and increased confidence in advanced engineering simulation tools are shifting user priorities. That survey also revealed a high level of interest in the use of AI/ML simulation tools. Article Article
[253] The Intersection of AI and Simulation Technology - Ansys — Why Ansys Become An Ansys Partner Ansys is committed to setting today's students up for success, by providing free simulation engineering software to students. Battery Simulation Collection Overview Ansys is committed to setting today's students up for success, by providing free simulation engineering software to students. Ansys Learning Hub Simulation Topics Ansys is committed to setting today's students up for success, by providing free simulation engineering software to students. Today, AI-enhanced simulations speed up design and optimization across industries, especially those in which accuracy and efficiency are critical, such as automotive, aerospace, electronics, and materials science. An example of the combination of AI and simulation is a recent addition to the Ansys product family.
[254] Transforming the Future of Simulation-Based Optimization | Simio — 1. Integration with Artificial Intelligence (AI) and Machine Learning (ML) A growing trend in simulation-based optimization (SBO) is the integration of AI and machine learning (ML) algorithms, which enhance simulations by automating solution discovery, processing large datasets, and uncovering hidden patterns.
[255] The Future of Simulation- Trends and Innovations | Simio — Simulation technology has evolved dramatically over the years, becoming an indispensable tool for modern industries seeking to optimize workflows, reduce costs, and improve decision-making. Artificial intelligence (AI) is at the forefront of transforming simulation technologies by embedding real-time predictive capabilities into simulation software. Coupled with autonomous systems and continuous data feeds from digital twins, real-time simulations enable dynamic systems to function independently and make strategic choices without human intervention. By simulating entire production lines, distribution centers, supply chains, healthcare networks, logistics systems, and urban infrastructures, digital twins enable manufacturers, city planners, and other industry professionals to refine resource utilization and reduce waste. Its state-of-the-art platform integrates AI-driven analytics, cloud-based functionality, AR/VR visualization, and real-time simulation, ensuring that users can meet today’s challenges while preparing for the future.
[256] Hybrid Modeling Integrating Artificial Intelligence and Modeling ... — This paper discusses the complementary relationship between Modeling and Simulation (M&S) and Artificial Intelligence (AI) methods like machine learning. While M&S uses algorithms to model system behavior from input parameters, AI learns patterns from correlation in data. The paper argues that hybrid models combining M&S and AI can be more powerful than either alone. It provides a conceptual
[258] Explainable Artificial Intelligence for Predictive Modeling in ... — These successful predictive modeling examples have proven that advanced artificial intelligence and machine learning algorithms are promising in unlocking clinically relevant information hidden in the large volume of healthcare data, making accurate predictions, and discovering valuable insights for various healthcare applications.
[259] Revolutionizing the future of hydrological science: Impact of machine ... — Revolutionizing the future of hydrological science: Impact of machine learning and deep learning amidst emerging explainable AI and transfer learning - ScienceDirect Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are revolutionizing hydrology, driving significant advancements in water resource management, modeling, and prediction. As hydrology faces escalating challenges due to human-induced climate change and growing water demands, the continued evolution of AI-integrated models and innovations in data handling and stakeholder engagement will be imperative. In conclusion, the findings emphasize the critical role of AI-driven hydrological modeling in addressing global water challenges, including climate change adaptation, sustainable water resource management, and disaster risk reduction. For all open access content, the relevant licensing terms apply.
[260] Revolutionizing Design: How AI, ML, and Simulation Work Together — 5. The Future of AI, ML, and Simulation in Engineering Design. The future of engineering lies in the convergence of AI, ML, and simulation. As AI algorithms become more advanced and simulation software continues to evolve, we can expect to see even greater levels of automation, optimization, and predictive capabilities in the design process.. AI-powered simulations will soon become the
[261] Harnessing AI/ML & Simulation for a Smarter Industry 4.0 Transformation — The Future of ML and Simulation Technologies ML and simulation technologies are revolutionizing manufacturing by driving efficiency, innovation, and sustainability. Emerging trends, such as the integration of ML with IoT and digital twins, enable dynamic, predictive systems like self-learning supply chains.
[268] PDF — these systems in a flight-relevant environment. NASA's state-of-the-art modeling and simulation ca-pability must continually evolve to meet the needs of the next generation of planetary EDL. To accomplish this aim, NASA's Entry Systems Modeling (ESM) Project was formed in 2013 and is funded by the Space
[269] Entry Systems Modeling (ESM) - NASA — The Entry Systems Modeling (ESM) project aims to develop validated tools and frameworks that enable planning and optimization of Entry, Descent and Landing (EDL) missions. The aerosciences technical area focuses on making improvements to the state-of-the-art in simulating reentry, with an application to increased reliability, reduced