The journal welcomes contributions that present high-quality experiments with particular attention to the reproducibility of the results. The papers must have a detailed and complete description of the experimental set-up and should include dispersion or uncertainty assessment information. They should also be completed with the datasets of the presented results in standard editable format.

Papers that focus on validation must involve assessment of computational models through comparison to experiments and should be accompanied by relevant measures of uncertainty from both sources. These papers should also include code verification, i.e. the assurance that code outputs converge to analytical solutions, particularly in terms of the rate of reduction of discretization errors.

The Journal of Sustainable Construction Materials and Project Management (JSCMPM) acts as a leading international platform for advancing knowledge and innovation in the sustainable use of construction materials and the effective management of construction projects. It aims to promote evidence-based solutions to urgent challenges in resource efficiency, environmental stewardship, climate resilience, and equitable development in the built environment. By encouraging interdisciplinary research and practice, the journal supports the University’s research agenda and contributes to the UN SDGs: SDG 9 (Industry, Innovation, and Infrastructure), SDG 11 (Sustainable Cities and Communities), SDG 12 (Responsible Consumption and Production), and SDG 13 (Climate Action). Through rigorous academic exchange and knowledge sharing, the journal seeks to advance sustainable development in the built environment and related fields.

JSCMPM welcomes original research articles, technical notes, review papers, and case studies that present novel insights, systematic analyses, and practical applications in the following key areas of interest, including, but not limited to: 

Sustainable and Alternative Construction Materials: Research on recycled aggregates, quarry dust, fly ash, calcined earthen resources, industrial by-products, innovative admixtures, and composite materials that reduce environmental impact and improve construction efficiency; including life-cycle assessment, durability studies, and circular economy practices.

Project Management: Advances in construction productivity, resource optimization, quality and safety management, sustainable procurement, risk and contract management, logistics, digital transformation (e.g., BIM, digital twins), and waste minimization in project delivery, and other related areas such as Project Planning, System Design and Engineering, Project Scheduling and Resource Management, Monitoring, Evaluation, and Performance Optimization, Environmental and Safety Compliance. 

Transportation Engineering: Studies addressing sustainable transportation infrastructure, encompassing innovative pavement and roadway materials, traffic flow analysis and modeling, smart and green mobility solutions, safety and logistics management, and other strategies that enhance efficiency, resilience, and environmental sustainability of transportation networks, particularly in developing and climate-vulnerable regions, in alignment with the SDGs.

Infrastructure Systems and Applications: Sustainable approaches for roads, bridges, railways, ports, harbors, airports, and other critical infrastructure, integrating new materials and methods to improve resilience, climate adaptation, and low-carbon development.

Policy, Economics, and Education for Sustainability: Insights on regulatory frameworks, financing models, incentives, educational initiatives, and capacity-building strategies that promote the adoption of sustainable materials and project management practices in the construction industry.

By providing a platform for rigorous research and knowledge exchange across academia, industry, and government, JSCMPM supports evidence-based innovations that advance the construction and transportation sector’s contribution to sustainable development.

JSCMPM Template and Manuscript Submission Guidelines

Under the Information section on the right, please follow the submission guidelines carefully. Manuscripts must be prepared in the IMRAD format and submitted as Microsoft Word (.docx) files, not as PDFs. Please download the JSCMPM Template on the link: https://docs.google.com/document/d/1l87nG1cH6OySMRln-68DhnkC-LbUx0_Q/export?format=docx

Ensure that all tables and figures are fully editable and not inserted as images. In addition, authors are required to provide their ORCID ID, which uniquely identifies researchers and facilitates the attribution of their scholarly contributions across publications, datasets, and institutional affiliations.

Plagiarism and AI Content Screening Policy

All work submitted to the Journal of Sustainable Construction Materials and Project Management (JSCMPM) will be checked for plagiarism using Turnitin or a similar tool. Manuscripts must meet the JSCMPM standard of not more than fifteen percent (≤15%) similarity, not including reference lists, properly cited quotations, or common academic or procedural phrases. If it exceeds this limit or contains copied content, it will be returned to the authors for editing or may be rejected by the Editorial Team.

The JSCMPM has strict rules governing the proper use of Artificial Intelligence (AI) tools, including AI text-editing or translation apps and image-generation tools. Authors must: 

     •  Clearly state if they used AI tools while making the paper, like in the Acknowledgments section or a specific part called Use of AI Tools, naming the tool and what it was used for.

    •  Be responsible for all information, like text and pictures that could have been helped or made by AI tools, and ensure all is accurate, truthful, original, and correctly cited.

    •  Make sure the AI tools used do not cause copying, false data, or fake pictures. If AI misuse that breaks the rules or harms research honesty is found, it will be treated as academic misconduct and handled in accordance with the Journal's or SCIPEDIA’s ethical guidelines.

     •  Papers that violate the Journal's rules on copying or AI use may be refused or retracted, and the Editorial Board might take other actions.

Publication Frequency

The Journal of Sustainable Construction Materials and Project Management (JSCMPM) is published biannually (twice a year), with issues released in:

     •  June (First Issue)

     •  December (Second Issue)

Special issues may be organized on emerging themes and collaborative research projects with academic and industry partners.

Copyright and Licensing

The corresponding author must submit a duly signed Author Declaration and Publishing Agreement, affirming that the manuscript is original, has not been previously published or concurrently submitted elsewhere, and that all listed co-authors have reviewed and approved the submission. Please download the Author Declaration Form from the link: https://docs.google.com/document/d/10YfsAVymN0vE_SIJ-pA-_d9X5JXONIKu/export?format=docx

Authors retain full copyright to their published work. The Journal of Sustainable Construction Materials and Project Management (JSCMPM) is granted the right of first publication, after which the article is distributed under the Journal’s open-access license:

Creative Commons Attribution–NonCommercial–ShareAlike 4.0 International (CC BY-NC-SA 4.0)
https://creativecommons.org/licenses/by-nc-sa/4.0/

This license allows others to copy, distribute, display, perform, and adapt the work for non-commercial purposes, provided that:

     • ​ Proper attribution is given to the original authors and to JSCMPM as the original publisher; and

     •  Any adapted or derivative works are distributed under the same CC BY-NC-SA 4.0 license.

All articles published in JSCMPM are freely and immediately accessible to the public upon publication. The JSCMPM currently does not charge any submission fees or article processing charges (APCs). If the JSCMPM introduces any future costs, this page will be updated in advance with a clear description of the types and amounts of the fees and the exact stage at which they are applied.

Publisher and Hosting Information

Published by Cagayan State University, Carig Campus. The Journal of Sustainable Construction Materials and Project Management (JSCMPM) is hosted and disseminated online via the SCIPEDIA publishing platform, ensuring broad, open access and global scholarly reach.

Indexing and Abstracting Status

The Journal of Sustainable Construction Materials and Project Management (JSCMPM) currently assigns Zenodo-registered Digital Object Identifiers (DOIs) to ensure long-term preservation, discoverability, and stable archival access. These outputs are already indexed in OpenAIRE and Google Scholar, providing persistent visibility and reliable citation tracking. As part of its development roadmap, JSCMPM plans to transition to Crossref-issued DOIs, either through a future upgrade of its SCIPEDIA hosting plan or through institutional Crossref membership under Cagayan State University.

In parallel, JSCMPM is proactively pursuing inclusion in additional reputable indexing and abstracting services such as DOAJ, Semantic Scholar, OpenAlex, ROAD, and BASE to further expand the global reach, discoverability, and accessibility of its published works. Aligned with its long-term strategic vision, the JSCMPM is also progressively positioning itself to meet the standards required for coverage in leading international databases, particularly Scopus and the Web of Science (WoS).

Peer Review Process

The Journal of Sustainable Construction Materials and Project Management (JSCMPM) employs a strict double-blind peer-review process to ensure that all published articles are scientifically sound, new, and valuable. The average time from when a paper is sent out to when an editor makes a decision is 8 to 16 weeks.

(1) First Screening by the Editor-in-Chief

All new papers first go to the Editor-in-Chief and/or Section Editors. Here, the paper is checked for:

     • If it fits the goals of JSCMPM; If it meets the journal template and style; And if ethical issues or some documents are missing.

Papers that fail these checks may be returned to the authors or rejected without external review.

(2) Plagiarism and AI Use Check

All papers are checked for text similarity using plagiarism-detection software before being sent to external reviewers. The journal also looks for improper or hidden use of AI tools as outlined in the Plagiarism and AI Screening Policy. Papers with high similarity or serious ethical concerns may be rejected at this stage.

(3) Assigned to Peer Reviewers

Papers that pass the first check are sent to two or more qualified peer reviewers with expertise in the paper's subject. This peer review is double-blind, meaning:

     • Reviewers do not know who the authors are, and Authors do not know who the reviewers are.

(4) Review Questions

Reviewers are asked to check the paper for, but not limited to:

     • Its originality and new information or ideas; 

     • Its technical and methodical soundness; 

     • How clearly it states its goals, methods, findings, and answers; 

     • Its relevance to sustainable construction materials, project management, and related fields.

     • Its quality in figures, tables, and sources; 

     • Its overall clarity, structure, and ease of reading.

(5) Making a Decision

Based on the reviews and advice, the Editor-in-Chief and/or Section Editors will choose one of:

     • To accept with no changes; To accept with minor modifications; To ask the author to make significant changes and send it back; To decline the paper.

The final decision and the anonymous reviewer comments will be provided to the corresponding author.

(6) Fixing and Sending Back the Paper

Authors who have been asked to fix their paper need to send:

     • The fixed paper, and a list that responds point-for-point to what the reviewers and editors indicated.

Revised papers may be returned to the same reviewers or forwarded to the Editor-in-Chief for further review, particularly if significant changes are requested.

(7) Getting the Paper Accepted and Published

Once accepted, the paper undergoes editing, layout, and proofreading. Authors can check the page proofs for minor fixes before the paper is published online.

(8) Privacy and Ethical Rules

All papers and reviews are kept private. Reviewers must disclose any conflicts of interest and adhere to ethical guidelines, such as those of the Committee on Publication Ethics (COPE). The editors promise that decisions will be fair, transparent, and based solely on the quality of the work.

SCIPEDIA and Institutional Stewardship

Maintained and supervised by Cagayan State University, Carig Campus, in partnership with SCIPEDIA, the Journal of Sustainable Construction Materials and Project Management (JSCMPM) upholds rigorous standards of quality and ethical publishing. This stewardship ensures academic integrity, alignment with international publishing protocols, and the open-access dissemination of high-quality, impactful research.

Note to Readers

For optimal readability and full appreciation of the figures, tables, and text layout in this article, we strongly recommend downloading and viewing the PDF in double-column format. The double-column PDF layout provides clearer font scaling and a more organized academic presentation than the single-column PDF view.

-------------------------

Office Address

The fields of mechanics and materials science are undergoing a profound transformation, driven by the convergence of high-fidelity computational methods and groundbreaking advances in artificial intelligence (AI). Accurately describing the mechanical behavior of materials is of great significance for their engineering applications. Traditional computational techniques, such as the Finite Element Method (FEM), Meshfree Methods (MM), Discrete Element Method (DEM), and Molecular Dynamics (MD), have long been the cornerstone for simulating complex physical phenomena. However, they often face significant challenges in dealing with multi-scale problems, inverse design, and extreme computational costs.

With the rapid development of artificial intelligence (AI), advanced techniques such as neural networks are expected to bridge the gap in mechanical behavior in different scales, driving traditional material mechanics research from a "physics-driven" paradigm to a "data-physics hybrid-driven" paradigm. AI technologies not only accelerate the modeling and simulation of complex systems but also show great potential in uncovering underlying physical laws, predicting mechanical behaviors, and optimizing material structures. In particular, methods such as neural networks and graph learning provide novel approaches to address challenges in multi-physics coupling, spatiotemporal predictions, and nonlinear behavior characterization.

Despite the widespread application of neural network technologies in material mechanics, numerous challenges remain. Many data-driven computational methods lack explicit constraints on physical laws such as constitutive relationships and energy conservation, leading to predictions that violate fundamental mechanical principles. Additionally, these methods suffer from strong data dependency, high costs of obtaining high-quality material data, poor interpretability, and limited generalization capabilities. Although physics-informed neural networks (PINNs) partially alleviate these issues by incorporating physical constraints, they still face challenges such as limited adaptability to complex scenarios and the absence of robust theoretical validation frameworks. These technical bottlenecks highlight the urgent need for breakthroughs in both theory and practice within the field of intelligent computation for material mechanics.

This special issue aims to bring together cutting-edge research at the intersection of AI, computational mechanics, and materials science, addressing the core challenges of the current "data-physics hybrid-driven" paradigm. We encourage original research that overcomes the limitations of traditional computational mechanics models, enhances physical constraints, and improves the generalization and interpretability of AI models. Priority topics include:

Exploring methods to enhance model transparency and interpretability, and establishing a quantitative evaluation framework for computational mechanics and AI-based mechanics models.

Addressing the scarcity of high-quality material data by investigating small-sample learning methods and data augmentation strategies in AI mechanics.

Leveraging generative AI technologies to design novel materials with specific microstructures, molecular configurations, or macroscopic structures based on target performance requirements, enabling AI-driven inverse material design.

Integrating traditional physical simulations (e.g., finite element methods, meshfree methods) with AI surrogate models to construct efficient hybrid analysis frameworks for accelerating the solution of complex nonlinear dynamics problems in materials.

We invite submissions from theoretical, computational, and applied research in material mechanics, computational science, and artificial intelligence, particularly those demonstrating methodological rigor, experimental validation, and engineering applicability. Topics of interest include, but are not limited to:

Advanced Computational Methods: Material mechanics, Multi-scale and multi-physics modeling (such as FEM, MM, DEM, MD, etc.), phase-field modeling and fracture mechanics, contact mechanics and large deformation analysis, as well as uncertainty quantification and probabilistic modeling, and so on.

Physics-informed AI algorithms: Advances in physics-informed neural networks for material mechanics and other methods embedding physical constraints.

Automated scientific discovery: Applications of symbolic regression, tensor networks, and other methods for automatically discovering or identifying material constitutive relationships and physical laws.

Intelligent microstructure characterization and generation: Graph neural networks for microstructure characterization and damage evolution, and generative models for virtual microstructure reconstruction and optimization.

AI-enabled multiscale modeling: Constructing efficient surrogate models to replace computationally expensive microscale simulations by learning from high-fidelity simulation data and coupling information across scales.

Intelligent multiphysics coupling: AI solvers and hybrid modeling strategies for complex coupled problems such as thermo-mechanical-chemical-electrical interactions.

Data-driven mechanics models: Data-driven paradigms for crystal plasticity, phase-field models, and damage mechanics.

AI technologies for additive manufacturing: Real-time simulation of 3D printing processes, defect prediction, and AI-based optimization of process parameters.

Intelligent performance evaluation and health monitoring: AI-based predictions of material fatigue life, fracture behavior analysis, and intelligent evaluation of structural health.

Inverse design of new structures and materials: Searching for optimal structures or material compositions to achieve given performance targets, such as odd elasticity theory, functionally graded materials, plate and shells, metamaterials mechanics.

AI-driven digital twins: Developing AI surrogate models for real-time prediction, decision support, and performance optimization in material and structural systems.

This Special Issue aims to gather these frontier studies to provide powerful computational tools for addressing major challenges in advanced materials, accelerating the innovation cycle from material mechanics to engineering application.

The goal of the repository is to widely disseminate the results of the research performed at CIMNE, by sharing the preprints or postprints -depending on the article sharing policies of the original publisher- of the papers published in scientific journals by CIMNE's scientists.

Structural Membranes 2021 aims to be a forum for discussing recent progress and identifying future research directions in the field of textile composites and inflatable structures.

Structural Membranes 2021 will be supported by the IASS. It will also be a Thematic Conference of the European Community on Computational Methods in Applied Sciences (ECCOMAS) and a Special Interest Conference of the International Association for Computational Mechanics (IACM).

Conference organized by CIMNE Congress Bureau.

The goal of the repository is to widely disseminate the results of the research performed at CIMNE, by sharing those presentations made by CIMNE's scientists.

COMPLAS 2017 is one of the Thematic Conferences of the European Community on Computational Methods in Applied Sciences (ECCOMAS). It is also an International Association for Computational Mechanics (IACM) Special Interest Conference.

COMPLAS conferences are organized by CIMNE Congress Bureau.

The next edition of this series of conferences (COMPLAS 2019) will be held in Barcelona, Spain, 3-5 September 2019 (https://congress.cimne.com/complas2019)

El alcance de esta publicación comprende los sistemas de ingeniería que dan apoyo y sirven para el diseño de la infraestructura civil, y a los desastres naturales y accidentes de origen humano que pueden afectar esa infraestructura. La revista publica contribuciones que se refieran a la conjunción de más de una de las áreas temáticas definidas en el título, o a una de ellas. El término infraestructura civil se usa aquí para designar al conjunto de instalaciones físicas que permiten movilizar o almacenar bienes, materias primas, agua, residuos, energía, información o personas. En general, se incluyen aquí puentes, puertos, canales, aeropuertos, ferrocarriles, sistemas de tránsito urbano, carreteras, líneas de comunicación y energía, tuberías, represas, plantas de tratamiento de aguas, tanques, silos, etc. El énfasis en desastres naturales está en el estudio de acciones de huracanes, tornados, terremotos, inundaciones, sequías, fuego, deslizamientos, y otros. Asimismo la revista publica temas relacionados con accidentes y eventos producidos por causas humanas, incluyendo fallas por diseño o construcción, colisiones con vehículos, explosiones, entre otras.
 

Indexing and Abstracting: SCIE (Web of Science): 2024 Impact Factor 0.4, JCR Q4; Scopus: 2024 CiteScore 0.6; DOAJ; Wikidata; Crossref; Title DOI; ROAD; ZDB; EZB; OpenAlex; SuDoc; FATCAT; The Keepers, etc.

RIMNI is published by Scipedia, officially supported by International Centre for Numerical Methods in Engineering (CIMNE). RIMNI is in collaboration with Tech Science Press from July 2024.

The imperative for achieving carbon neutrality and fostering sustainable resource and environmental systems has catalyzed the integration of artificial intelligence (AI) and advanced computational technologies into modeling, optimization, and decision-making processes. AI-driven innovations—including machine learning, deep learning, agent-based modeling, system dynamics, and intelligent optimization algorithms—are increasingly pivotal in understanding complex resource-environment interactions, enhancing system efficiency, and facilitating the transition to a low-carbon future. This Special Issue invites high-quality contributions that explore AI-driven technological innovations in the context of resource and environmental system modeling, optimization, and carbon neutrality applications. We welcome submissions employing diverse methodological approaches, such as AI and machine learning, big data analytics, simulation modeling, optimization algorithms, digital twins, and other computational or empirical methods. Papers may address, but are not limited to, AI applications in energy systems, environmental monitoring, carbon emission forecasting, policy simulation, sustainable resource management, and cross-sectoral integration for carbon neutrality. The Special Issue aims to provide a comprehensive platform for advancing research and practice at the intersection of AI technology, system modeling, and carbon neutrality strategies, contributing to intelligent, resilient, and sustainable socio-environmental systems. Topics of interest include, but are not limited to: AI and Machine Learning for Environmental System Modeling Intelligent Optimization of Resource Allocation and Energy Systems Digital Twins and Simulation for Carbon Neutrality Scenarios Big Data Analytics in Environmental Monitoring and Forecasting AI-Driven Policy Simulation and Impact Assessment Sustainable Resource Management through Intelligent Systems Integration of Renewable Energy and Smart Grids with AI Technologies Climate Change Mitigation and Adaptation via Computational Innovations

Introduction:

The accurate modeling and prediction of complex behaviors in dynamical systems remain critical challenges across various science and engineering disciplines. Recent advancements in computational and numerical methods have significantly enhanced the ability to simulate, analyse, and control these systems with greater precision and efficiency. This Special Issue aims to explore cutting-edge computational techniques that address key challenges in system behaviour, advancing both theoretical understanding and practical applications.

Aims and Scope:

The objective of this Special Issue is to provide a platform for original research on computational and numerical techniques with various applications related to modeling, analysis, optimization, etc., in dynamical systems to understand the behavior and design of these challenging systems. Contributions that advance the understanding of dynamical systems, while also addressing critical aspects such as performance optimization, system reliability, and long-term sustainability, will be of particular interest. Contributors are encouraged to emphasize both theoretical innovation and practical relevance.

Specific areas of interest include, but are not limited to:

Mechanical vibration, stability, and structural health monitoring

Dynamic modelling of composite, adaptive, and smart materials

Simulation of robotic manipulators and flexible mechanical systems

Hybrid numerical and AI-based methods for system analysis

Optimization of dynamical systems for performance and reliability

Stability, bifurcation, and transient analysis in complex dynamical systems

Fuzzy logic, uncertainty quantification, and stochastic analysis

Applications in biomechanics, environmental dynamics, and epidemiological modeling

Fracture and damage mechanics play a critical role in engineering, materials science, and applied mechanics, where accurate prediction of crack initiation, propagation, and progressive material degradation is essential for ensuring the safety and reliability of structures and components.

Recent advances in numerical and computational methods have enabled the modeling of complex, nonlinear, and multiscale phenomena associated with fracture and damage, including corrosion effects, hydrogen embrittlement, dynamic loading, and multiphysical behaviors. This Special Issue focuses on innovative and robust computational strategies for predictive modeling of fracture and damage, encompassing both methodological developments and practical applications in structural and materials engineering.

Contributions are invited on advances in numerical formulations and algorithms, finite element and meshfree methods, cohesive zone models, phase-field fracture models, multiphysics couplings, high-performance computing strategies, and data-driven or machine learning approaches. The goal is to provide an updated overview of computational tools for the accurate prediction of fracture and damage in complex materials and engineering structures.

Potential topics include but are not limited to:

Finite element and extended finite element methods (FEM/XFEM) for fracture and damage analysis

Cohesive zone and phase-field models for crack initiation and propagation

Continuum and non-local damage mechanics formulations

Hydrogen embrittlement and corrosion-induced damage modeling

Multiscale and multiphysics computational approaches

Dynamic fracture and high-rate crack propagation simulations

Adaptive mesh refinement and meshfree/particle-based methods

Predictive modeling for lifetime assessment and structural reliability

Data-driven and machine learning techniques in fracture and damage prediction

Benchmark studies, verification, and validation of computational fracture models

With the advancement of technology, the methods for measuring and analyzing engineering data are constantly being innovated and improved. This enables the engineering data to deliver greater value, allowing analysis results to more closely reflect real-world situations. Emerging technologies such as Artificial Intelligence (AI), Big Data, Cloud Computing, and Machine Learning (ML) have a wide range of applications in the practice of design, control, planning, decision-making, and management activities in engineering manufacturing and services. These technologies can help expand, automate, and enhance the collection and processing of engineering data, and improve engineers' ability to formulate strategies and value-added analysis and insights, thereby enhancing engineering performance and quality. We expect the submitted papers to present solutions and examples based on mathematical modelling and optimization, algorithms for application domains, software implementation, and other formal approaches or technologies. We are inviting submissions to this Special Issue entitled “Advanced Approaches and Applications in Engineering”. Both original research and reviews will be considered. The following subtopics are the particular interests of this special issue, including but not limited to:​

• Artificial intelligence for data analytics in engineering;
• Big data in engineering;
• Machine learning/deep learning applications in engineering;
• Statistics in engineering;
• Performance evaluation in engineering;
• System/process optimization in engineering;
• Data analysis methods in engineering;
• Uncertainty in engineering;
• Decision-making in engineering.

Modern engineering systems such as manufacturing networks, energy systems, transportation infrastructures, communication networks, and reliability-driven industrial processes exhibit complex dynamical behavior influenced by uncertainty, memory effects, time delays, and nonlinear interactions. Classical integer-order and deterministic models often fail to capture these features accurately, motivating the use of advanced computational and mathematical modelling techniques.

This Special Issue aims to bring together recent advances in fractional-order, stochastic, delayed, fuzzy, and hybrid computational models with a strong emphasis on engineering applications and interdisciplinary engineering research. The focus is on the development, analysis, and numerical simulation of models that enhance the understanding, prediction, optimization, and control of complex engineering systems. Contributions addressing engineering-inspired dynamical systems, innovative numerical algorithms, high-performance computing implementations, and data-assisted computational frameworks are particularly encouraged. The Special Issue welcomes both theoretical developments supported by engineering relevance and applied studies motivated by real-world engineering problems.

The following subtopics are of particular interest, including but not limited to:

Fractional-order and memory-dependent models in engineering systems

Stochastic modelling of engineering processes and reliability systems

Delay differential models in control systems, production networks, and communication systems

Hybrid deterministic–stochastic frameworks for complex engineered systems

Quantum-inspired and computationally enhanced methods for engineering optimisation

Numerical algorithms for engineering dynamics (NSFD, Runge–Kutta, spectral and meshless methods)

Stability, bifurcation, and control analysis of nonlinear engineering models

Data-driven, AI-assisted, and machine-learning-enhanced computational engineering models

Applications to manufacturing systems, logistics, transportation, energy networks, and industrial processes

Software tools, simulation platforms, and high-performance computing for engineering modelling

Fractional-order differential equations (FODEs) have emerged as a powerful tool for modeling complex systems in both engineering and biological sciences. Unlike traditional integer-order models, FODEs incorporate memory effects and non-local interactions, making them particularly suited to describe phenomena that exhibit long-term dependence or hereditary properties. As a result, they have gained increasing attention in areas such as disease dynamics, material science, and engineering systems, where traditional integer-order models fall short. However, solving these equations presents significant computational challenges due to the non-local nature of fractional derivatives and the complexity of high-dimensional systems.

This special issue aims to explore advanced computational techniques and numerical methods for solving fractional-order differential equations. We seek to highlight the latest developments in this area, focusing on both theoretical advances and real-world applications. The issue will cover the computational challenges inherent in FODEs, the role of high-performance computing, and the integration of machine learning techniques to tackle these complex models. We invite contributions from researchers working on innovative numerical schemes, parallel computing approaches, and software tools for efficiently solving FODEs across various domains. The scope of the special issue will encompass both the theoretical underpinnings of fractional calculus and its practical implementation, with an emphasis on engineering systems and disease dynamics. We aim to foster collaboration between computational mathematicians, engineers, and biologists, contributing to a more unified approach to modeling complex systems.

• We invite papers on, but not limited to, the following topics:
• Numerical methods for solving fractional-order differential equations.
• Computational challenges and solutions for FODEs, including stability and convergence analysis.
• Applications of fractional-order models in engineering systems, such as materials modeling, diffusion, and fluid dynamics.
• Use of fractional-order differential equations in disease dynamics and epidemiological modeling.
• The integration of machine learning and AI techniques with fractional-order models.
• Development and optimization of computational tools and software for solving FODEs.
• High-performance computing and parallelization techniques for large-scale simulations of fractional-order systems.

The proliferation of massive Internet of Things (IoT) devices and emerging beyond-5G/6G services demands scalable connectivity, ultra-reliability, and energy-efficient communication. Cooperative transmission technologies, including active relays, passive reflecting structures, and distributed aerial platforms, are becoming fundamental enablers for extending coverage, improving spectral efficiency, and supporting intelligent wireless environments.

This Special Issue (SI) aims to present recent advances in cooperative communication technologies for IoT and next-generation wireless networks. It covers both active and passive cooperation mechanisms, intelligent propagation control, and distributed networking architectures. Contributions addressing theoretical modeling, signal processing, protocol design, optimization, machine learning integration, and experimental validation are encouraged. The issue welcomes terrestrial and non-terrestrial scenarios focusing on performance enhancement, energy sustainability, security, and scalability in dense heterogeneous deployments. The objective is to bridge theory and practice toward ubiquitous 6G connectivity.

The following themes illustrate representative research directions and application domains aligned with the above objectives, while the Special Issue remains open to other innovative cooperation-based wireless technologies.

Cooperative and multi-hop relay communications (AF/DF, full-duplex, cell-free, massive, distributed MIMO)

Reconfigurable Intelligent Surfaces (RIS), metasurfaces, and smart radio environments

Ambient backscatter and symbiotic radio communications (passive cooperation)

Aerial and non-terrestrial cooperative networks: UAV, HAPS, and satellite-assisted systems

Energy harvesting, SWIPT, and green cooperative networking

Advanced multiple access schemes with cooperation (NOMA, RSMA, grant-free massive access)

Physical-layer security and covert communications in cooperative networks

AI/ML-driven resource allocation and channel estimation

Integrated sensing-radar-communication-computing and edge intelligence

Performance enhancement of LPWAN/IoT technologies (LoRa, NB-IoT, massive machine-type communications)

Experimental platforms, testbeds, and practical deployments

Millimeter-Wave (mmWave) and THz relaying

V2X and Industrial IoT (IIoT)

Semantic and goal-oriented relaying, intelligent relaying

Advanced numerical methods for fluids and solids are mathematical and algorithmic tools used to solve problems related to fluid mechanics and solid mechanics. These methods are used to model and simulate the behavior of fluids and solids in various such as airflow around an aircraft, wave motion in a solid medium, or the behavior of fluids in chemical reaction systems.

There are many advanced numerical methods for fluids and solids, including finite difference methods, spectral methods, Monte Carlo methods, linear system solvers, and relaxation methods.

Finite difference methods are based on the discretization of space and time to solve the equations of physics. They are widely used to solve problems in fluid mechanics and solid mechanics.

Spectral methods are based on the representation of data as Fourier series or Legendre series. They are used to solve problems in fluid mechanics and solid mechanics in specific domains, such as airflow around an aircraft.

Monte Carlo methods are based on random sampling to solve problems in fluid mechanics and solid mechanics. They are used to solve complex problems such as the behavior of fluids in chemical reaction systems.

Linear system solvers are based on algorithms to solve systems of linear equations. They are used to solve problems in fluid mechanics and solid mechanics.

Relaxation methods are based on algorithms to solve systems of nonlinear equations. They are used to solve problems in fluid mechanics and solid mechanics.

In conclusion, advanced numerical methods for fluids and solids are important tools for solving complex problems in fluid mechanics and solid mechanics. They are widely used in various industries, such as aerospace, energy, chemistry, and medicine.

Modern engineering design increasingly demands advanced numerical methods to achieve a holistic balance between high mechanical performance, environmental sustainability, and structural safety under extreme loading conditions. This Special Issue aims to provide a comprehensive platform for the latest advances in numerical methods, computational modeling, and high-fidelity simulation techniques, supported by experimental validation across the entire life cycle of engineering structures.

We invite contributions that investigate the static and fatigue behavior of innovative materials—including metals, composites, and additively manufactured components—through predictive numerical modeling and advanced simulation approaches, while integrating Life Cycle Assessment (LCA) to quantify and mitigate environmental impacts. Particular emphasis is placed on structural resilience and performance assessment, especially through computational collision and impact simulations based on advanced nonlinear finite element methods.

By bridging the gap between small-scale material characterization and large-scale computational structural analysis, this Special Issue aims to advance the development of robust, efficient, and scalable numerical methods for sustainable and resilient structural design and performance assessment across marine, automotive, and civil engineering applications.

Themes:

Advanced numerical methods for static, fatigue, and fracture mechanics

Computational modeling and high-fidelity simulation of engineering structures

Experimental validation using full-field techniques (DIC, IRT, etc.)

Collision and crashworthiness analysis using nonlinear finite element methods

Life Cycle Assessment (LCA) and sustainability in computational design frameworks

Structural integrity analysis of lightweight sandwich and honeycomb configurations

Numerical and experimental investigation of structural joints under cyclic loading

In the era of intelligent industrialization, engineering computing and communication systems are undergoing a fundamental paradigm shift, driven by the integration of advanced numerical techniques and AI—core themes aligned with RIMNI's focus on computational/numerical models, soft computing, and AI innovations. Traditional methods, long the backbone of engineering design and simulation (key journal research areas), face inherent bottlenecks in high-dimensional, nonlinear, real-time tasks due to high computational complexity, poor unstructured data adaptability, and inefficiency in handling inverse/ill-posed problems.​

The rapid advancement of AI, machine learning, and soft computing provides transformative solutions, echoing RIMNI's emphasis on AI/ML and software innovation. Fusing AI's strengths in pattern recognition, adaptive learning, and data-driven modeling with numerical techniques' rigor enables more efficient, robust solutions for complex engineering tasks, advancing software/computer design and unlocking new applications, such as industrial IoT edge computing, AI-optimized communication protocols, digital twin-based maintenance.​

The special issue welcomes submissions that fall within, but are not limited to, the following scopes:

Development and improvement of AI-enhanced numerical algorithms for engineering computing

AI-driven numerical optimization techniques for communication systems

Data-driven numerical modeling for digital twins in engineering

Advanced numerical methods for AI model training and deployment in edge/cloud engineering computing platforms

Stochastic numerical techniques combined with AI for uncertainty quantification in engineering and communication systems

Case studies and experimental validations of AI-numerical integrated solutions in real engineering/communication projects

Comparative analysis of traditional vs. AI-driven numerical techniques, evaluating their performance, efficiency, and scalability

This Special Issue focuses on state-of-the-art research in the field of fracture mechanics and fatigue of materials and structures. The increasing demand for safe, reliable, and long-lasting engineering components has made understanding the fatigue and fracture behavior of materials a critical topic in mechanical design. This issue welcomes contributions that cover both theoretical and applied aspects, including experimental studies, analytical models, numerical simulations (such as FEM and XFEM), and life prediction methodologies. Special attention is given to innovations in damage detection, crack growth modeling, multiscale and multiphysics approaches, and the behavior of advanced materials such as composites, shape memory alloys, and additive-manufactured components. The aim is to foster interdisciplinary collaboration and promote new insights that improve structural integrity and durability.

In the real world, information is not always black-and-white and precise without a doubt. A great deal of human knowledge, perception and decision-making is built on "fuzziness". For instance, concepts such as "the temperature is very high", "the speed is very fast", and "this person is very young" have gradual and unclear boundaries. Traditional binary logic seems inadequate when dealing with this kind of information. Fuzzy information processing was born precisely to address this challenge. Its core theoretical basis is the theory of fuzzy sets. Unlike in classical set theory, where an element either completely belongs to or completely does not belong to a set, fuzzy sets describe the degree to which an element belongs to a certain set through a membership function, and this value varies continuously between 0 and 1. This enables us to quantify and manipulate these fuzzy concepts in mathematical language. The significance of fuzzy information processing lies in the effective modeling of uncertainties, serving as a bridge for human-computer interaction, enhancing the control and decision-making capabilities of complex systems, and promoting the development of intelligent computing.

This special issue of RIMNI aims to showcase the latest research progress, innovative methods, and cutting-edge applications in the field of fuzzy information processing. We hope to bring together the wisdom of researchers around the world to explore how to utilize fuzzy theory to solve increasingly complex decision-making, control, and data analysis problems in the real world. The special issue will focus on the integration of fuzzy theory with other advanced computing paradigms, as well as its unique value in addressing the challenges of big data, artificial intelligence, and complex systems.

This special issue welcomes high-quality original research or in-depth reviews covering theories, methods, algorithms, and applications. We encourage contributors to explore the boundaries of fuzzy information processing and apply it to emerging scientific and technological fields. The specific themes include, but are not limited to, the following topics:

Industrial and applied mathematics is increasingly shaping modern engineering through advanced numerical methods, high‑fidelity modeling and simulation, and computational tools for design and decision‑making. In parallel, artificial intelligence is accelerating numerical computing via data‑driven solvers, physics‑informed learning, learned surrogates, and optimization‑enhanced algorithms.

This Special Issue aims to capture state‑of‑the‑art contributions that bridge rigorous numerical analysis with impactful engineering applications across modeling, control, inverse problems, and AI‑enabled computation.

Topics of Interest (Non‑Exhaustive):

Mathematical Modeling & Simulation

• Computational and numerical models of engineering and industrial problems.

• Multiphysics simulation, reduced‑order modeling, uncertainty quantification, and model validation.

• Advanced computational mechanics and material modeling.

Differential Equations, Dynamical Systems, and Fractional Calculus

• Numerical methods for ODEs/PDEs, including stiff and multiscale systems.

• Fractional and variable‑order models and numerical realizations (Caputo, Riemann–Liouville, Caputo‑Fabrizio, Atangana–Baleanu, tempered operators, etc.).

• Stability, convergence, and error analysis for classical and fractional numerical schemes.

Control Theory & Automation

• Numerical optimization methods for robust/nonlinear control design.

• Observers, estimation, and fault detection with computational validation.

• Control and monitoring of energy systems and industrial processes.

Artificial Intelligence for Numerical Methods

• Physics‑informed learning (PINNs) and hybrid numerical–ML solvers.

• Operator learning and surrogate models for fast simulation and design.

• AI‑accelerated inverse problems, parameter identification, and data assimilation.

Inverse Problems, Statistics, and Stochastic Methods

• Deterministic and stochastic inverse problems and regularization.

• Stochastic calculus and probabilistic numerical methods for engineering.

• Data‑driven uncertainty modeling and risk‑aware decision support.

Introduction: Numerical methods are foundational to solving complex problems across diverse fields of engineering and applied sciences. From structural analysis and fluid mechanics to electrical systems and biomedical engineering, numerical methods provide the computational tools necessary for simulation, optimization, and design. As engineering challenges grow in complexity, the need for innovative numerical techniques and computational strategies becomes increasingly important. This Special Issue aims to bring together cutting-edge research that advances the theoretical development and practical application of numerical methods across various disciplines, fostering interdisciplinary collaboration and knowledge sharing.

Aim and Scope: The aim of this Special Issue is to publish high-quality research papers that address the development, improvement, and application of numerical methods in different branches of engineering and science. Contributions that explore new algorithms, computational models, and the use of advanced software for solving real-world problems are encouraged. The issue will serve as a platform to disseminate innovations that can be applied in multiple fields.

Suggested Themes:

• Development of novel numerical algorithms
• Multidisciplinary applications of numerical methods
• Numerical methods in machine learning
• Advances in computational fluid dynamics (CFD)
• Numerical methods in mechanical, materials and structural engineering
• Optimization techniques in engineering
• High-performance computing in numerical simulations
• Numerical methods in bioengineering and environmental science
• High-performance computing in numerical simulations
• Numerical methods, fuzzy systems and aggregation operators in decision-making for industrial management, business, and economics

Soil–structure interaction (SSI) plays a fundamental role in the seismic response of buildings and infrastructure systems. Although its importance has long been recognized in earthquake engineering, SSI effects remain only partially incorporated into routine assessment and design procedures, particularly when structures are subjected to complex site conditions and nonlinear seismic demands.

This Special Issue aims to advance the understanding and practical application of soil–structure interaction in seismic engineering, with particular emphasis on the role of numerical modeling in capturing the coupled response of structural systems, foundations, and supporting soils. Recent advances in computational mechanics and numerical simulation have significantly improved the ability to analyze these interactions; however, important challenges remain in the consistent integration of soil, foundation, and structural models, particularly under nonlinear and dynamic loading conditions.

The issue will provide a dedicated forum for original contributions addressing analytical, computational, and applied aspects of SSI. Topics of interest include nonlinear dynamic analysis, advanced numerical simulation of coupled soil–foundation–structure systems, modeling strategies for SSI in complex site conditions, and studies examining the influence of SSI on seismic demand, structural performance, and resilience.

By bringing together recent developments in numerical methods, theory, and engineering applications, this Special Issue seeks to promote more realistic and reliable approaches for evaluating the seismic performance of structures and infrastructure systems under earthquake loading.

The study of modern engineering and physical sciences increasingly demands a deep understanding of applied mathematics, especially special functions. These functions play a key role in fields such as acoustics, thermodynamics, electromagnetics, and optics, helping to express both approximate and exact analytical solutions to complex problems. This, in turn, provides clearer insights into the fundamental properties and mechanisms involved.

This Special Issue aims to explore the use of classical and higher-order special functions in addressing advanced challenges in mathematical physics. These challenges may be defined by specific symmetries, such as rectangular, cylindrical, or spherical, or by unconventional models. We also encourage the study of new special functions, with a focus on their governing differential equations, recurrence relations, and the development of efficient computational algorithms, such as those utilizing uniform asymptotic expansions for small and large parameters.

We invite you to contribute review articles and original research papers that highlight recent progress in the theory and applications of special functions.

Introduction and Background

Artificial Intelligence (AI) and Machine Learning (ML) have revolutionized problem-solving across disciplines by offering advanced tools for automation, prediction, optimization, and decision support. In engineering and software development, AI-driven approaches are reshaping how we design, simulate, and validate complex systems. Simultaneously, the adoption of AI in fields like education, healthcare, finance, and cybersecurity underscores its broad social impact and growing necessity for responsible deployment.

As AI systems become increasingly embedded in critical infrastructures and workflows, challenges around interpretability, reliability, adaptability, and human trust become central to their successful application. The integration of AI into numerical methods, computational models, and software systems calls for new research that bridges theoretical development with practical needs - precisely the mission of RIMNI.

Aim and Scope of the Special Issue

This Special Issue aims to bring together cutting-edge research on the development, analysis, and application of AI and ML techniques across both traditional engineering domains and emerging interdisciplinary contexts. We particularly encourage submissions that highlight numerical methods, computational modeling, and software innovations enriched by AI.

In line with RIMNI's mission, the issue seeks to:

Explore how AI and ML are advancing engineering, and simulation.

Showcase AI applications in software engineering, especially those involving automation, defect detection, and predictive modeling etc.

Present cross-domain applications of AI (e.g., in education, health, security) where computational rigor and system reliability are critical

Address evaluation, ethics, and human-centered design of AI tools, particularly in high-stakes or regulated environments

Suggested Themes

We invite original research articles, reviews, and case studies on topics including (but not limited to):

AI-enhanced numerical methods for simulation, modeling, and optimization.

Integration of ML into engineering, software and mathematics.

Data-driven modeling and soft computing for system analysis and control.

AI for software analytics, automated testing, and intelligent development.

NLP and ML applications in software engineering and requirements processing.

AI for healthcare diagnostics, and educational personalization,

Explainability, robustness, and fairness in AI-driven systems.

Human-AI interaction and cognitive design in engineering and decision-making tools.

Numerical rigor with AI adaptability.

Evaluation frameworks and performance benchmarks for AI in engineering and social domains.

……

RIMNI-The journal's scope includes Computational and Numerical Models of Engineering Problems, Development and Application of Numerical Methods, Advances in Software, Computer Design Innovations, Soft Computing, Machine Learning, Artificial Intelligence, etc. 

The surging integration of new energy power systems, driven by global decarbonization, introduces complex operational dynamics—high variability, multi-source data interdependencies, and escalating equipment complexity - posing critical challenges to traditional diagnostic paradigms. Artificial Intelligence (AI), particularly deep learning, image recognition, and hybrid algorithms, has emerged as a cornerstone for intelligent equipment health management, offering unprecedented capabilities in extracting latent patterns from heterogeneous data (sensors, images, vibration signals) and enabling proactive decision-making. This Special Issue solicits original contributions leveraging AI to address key technical gaps in new energy equipment health management, focusing on the following directions: (1) Real-time identification of incipient anomalies (e.g., insulation degradation in transformers, microcracks in PV modules) under variable loads and environmental conditions; (2) High-precision localization and classification of faults (e.g., gear box faults in wind turbines, CT saturation in secondary devices) via multi-modal AI models; (3) Data-driven degradation modeling for remaining useful life (RUL) estimation, integrating physics-informed learning and transfer learning; (4) Proactive risk assessment using AI-driven early warning systems to prevent cascading failures; (5) Quantitative assessment of equipment health indices (e.g., solar panel efficiency, circuit breaker contact wear) with explainable AI; (6) Scalable AI frameworks for interoperable health management across diverse equipment (e.g., coupling solar inverters with grid switches). We prioritize studies that bridge AI algorithm innovation with domain-specific engineering needs, emphasizing real-world validation and scalability. Contributions should advance both theoretical rigor (e.g., model generalizability, uncertainty quantification) and practical utility. By fostering interdisciplinary dialogue, this issue aims to accelerate the development of AI-empowered, resilient new energy power systems, paving the way for a sustainable energy future.

The integration of deep learning algorithms into predictive maintenance systems represents a significant advancement in the application of numerical methods for engineering design and decision-making. As industries increasingly adopt data-driven solutions to manage complex equipment and production processes, predictive maintenance has become a vital strategy for minimizing unexpected downtimes, reducing maintenance costs, and extending asset lifespans.

This research area is critically important in the context of modern engineering, where large-scale sensor data, real-time monitoring, and intelligent analysis converge to form the foundation of Industry 4.0. Deep learning models—especially those capable of handling time series data and anomaly detection—enable engineers to forecast failures and optimize repair schedules with high accuracy. These models leverage numerical techniques rooted in statistical learning, neural network training, and signal processing to extract actionable insights from complex, multi-dimensional datasets.

Given the growing demand for computationally efficient and scalable solutions, the development and validation of specialized algorithms for industrial predictive maintenance are of high relevance. This special issue seeks to highlight novel methodologies and practical implementations that bridge the gap between artificial intelligence, numerical modeling, and engineering maintenance systems—offering both theoretical advancements and real-world applications.

The primary aim of this Special Issue is to explore and disseminate recent developments in algorithm design for deep learning models applied to industrial predictive maintenance systems. As industries transition toward intelligent and data-driven operations, the need for robust computational approaches to forecast equipment failures has become increasingly critical. This Special Issue focuses on research that bridges deep learning methodologies with practical engineering applications, particularly in the optimization of system reliability, efficiency, and cost-effectiveness.

The scope encompasses innovative algorithmic strategies that utilize numerical and computational techniques to analyze sensor data, model degradation patterns, and predict faults within complex industrial environments. Topics of interest include the theoretical development of deep learning models, advanced signal processing for time series data, and the integration of industrial internet of things (IIoT) technologies to enable real-time predictive maintenance. The Special Issue also encourages submissions that provide comparative analysis of algorithms, discuss practical deployment challenges, or demonstrate real-world implementations in manufacturing and engineering systems.

By uniting contributions from academia and industry, this Special Issue aims to provide a comprehensive perspective on how deep learning and numerical methods can jointly enhance predictive maintenance, thus contributing to the advancement of smart, sustainable, and efficient industrial systems.

Suggested themes:

Predictive maintenance for induction motors using deep learning and machine learning techniques.

Industrial Internet of Things predictive maintenance facilitated by deep learning.

Industrial predictive maintenance using machine learning.

Predictive maintenance using machine learning for industry-wide sustainable smart manufacturing.

A systematic overview of the literature on machine learning techniques used in predictive maintenance.

Methods based on data that are used to estimate industrial equipment repair.

An analysis of cutting-edge machine learning algorithms for predictive maintenance in comparison.

Industrial production line predictive maintenance system.

Predictive maintenance using machine learning in the manufacturing sector.

Applications of data-driven predictive maintenance for temporal convolutional networks in industrial systems.

A study of unsupervised machine learning techniques for predictive maintenance's early fault identification.

Survey of future maintenance defect detection methods.

Analytical solutions play an important role and provide a deeper understanding of the physical solutions of differential equations. Although exact analytical solutions in the closed form functions are very rare, iterative analytical solutions in the form of series and/or transform techniques have proved to be effective in constructing semi-analytical solutions. Since they are complex in nature, these techniques are usually combined with various numerical techniques also. The aim of the special issue is to bring together scientist using common semi- analytical techniques together, to collect high-quality work and provide a dissemination of recent results on the topic.
Perturbation techniques may be considered the oldest and common series type solutions. The limitations of the technique to small parameters lead to many iterative analytical techniques recently. Some of the techniques to avoid such restrictions are the Perturbation Iteration Method, Iteration Perturbation Technique, Homotopy Perturbation Method, Homotopy Analysis Method, Variational Iteration Method, Differential Transform Method, Adomian Decomposition Method, Optimal Homotopy Asymptotic Method, Taylor Matrix Method etc. Variants of the perturbation techniques which do not require small parameter assumptions are also welcome. Solutions of physical problems in any of the iterative analytical methods are within the scope of this special issue. 
Another important unified approach to solve differential equations is the Lie Group theory and its restricted form similarity transformations. Usually, the equations are first transformed into a solvable form via the symmetries of the equations. Since the resulting equations are also complex in nature, resort to numerical techniques may be inevitable. Employment of such techniques in search of solutions to the physical problems is welcome. 
Solutions of differential equations that do not stem from physical applications are discouraged. Also purely numerical solution techniques without applying some form of analytical techniques are not within the scope of this special issue. As mentioned above, a combination of analytical and numerical techniques in search of solutions of physical problems are within the scope of this special issue.  

The increasing global demand for renewable energy sources like solar and wind power, coupled with the widespread adoption of power electronic devices, has led to power quality issues. Integrating renewable sources into the grid can alleviate the burden on power converters. This special issue of RIMNI - International Journal of Numerical Methods for Calculation and Design in Engineering aims to showcase innovative research on the optimal design, numerical modelling, and analysis of renewable source-integrated distribution systems that utilize Artificial Intelligence (AI) control techniques to enhance power quality, effective power management, performance, and cost-effectiveness.

We invite review papers and original research contributions that focus on innovative algorithms, advanced controllers, AI-based optimization, and numerical modelling and design of:

• Photovoltaic (PV) systems
• Wind power systems (WPS)
• Multilevel converters
• Relevant topics include, but are not limited to:
• Numerical modelling and design of multilevel converters for power quality improvement
• Optimal power management strategies
• AI-based deep learning techniques for control applications
• Advanced simulation techniques for integrating hybrid renewable energy systems
• Optimization of hybrid control systems that combine conventional and AI methodologies
• Integration of AI algorithms in real-time control systems
• Renewable energy systems and smart grids
• AI-based tuning of fractional-order controllers

The burgeoning low-altitude economy is unlocking new frontiers for economic and technological innovation. UAVs, as a critical infrastructure, are at the heart of this revolution, enabling applications from smart logistics to urban air mobility. The reliability of these services is fundamentally dependent on robust, efficient, and intelligent communication networks. This creates an urgent need for advanced algorithms to solve complex challenges in real-time trajectory optimization, dynamic resource allocation, and large-scale swarm coordination under uncertain environments.

This Special Issue aims to compile the latest breakthroughs in applying Artificial Intelligence (AI) to address these critical challenges in UAV-assisted communications. It will highlight how AI methodologies—including Evolutionary Computation, Deep Reinforcement Learning, Federated Learning, and other machine learning paradigms—provide innovative, scalable, and self-adaptive solutions. The focus is on leveraging AI's powerful learning and optimization capabilities to build the cognitive and decision-making core for next-generation autonomous UAV networks, thereby accelerating the sustainable growth of the low-altitude economy.

1. AI-driven 3D path planning and collision avoidance in dense airspace.
2. Deep reinforcement learning for dynamic spectrum management and interference mitigation.
3. Federated and distributed learning for privacy-preserving and collaborative swarm intelligence.
4. AI-based solutions for robust network operation under uncertainties and security threats.
5. Multi-agent AI systems for heterogeneous UAV swarm coordination and control.

Deadline Date: 20 August 2026