Advanced Prognostic Models for Complex Systems: From Theory to Industrial and Scientific Applications

Dear Colleagues,

Aims and Scope:

Predicting the future behavior of complex systems is a fundamental challenge across science and engineering. The ability to accurately forecast system states, predict failures, and estimate remaining useful life is critical for enhancing reliability, safety, and efficiency in areas ranging from smart manufacturing and infrastructure management to climate science and biomedicine. The emergence of sophisticated Artificial Intelligence (AI) and Machine Learning (ML) techniques has dramatically advanced the field of prognostics, enabling the modeling of highly nonlinear, temporal dynamics from vast datasets.

This Special Issue aims to explore the cutting edge of prognostic model development and application. We seek to showcase innovative methodologies that address the core challenges in forecasting: handling high-dimensional and noisy data, capturing long-term temporal dependencies, providing interpretable predictions, and operating in real-time environments. A key focus will be on efficient and powerful AI paradigms suited for temporal data, with a highlighted interest in Reservoir Computing (RC), including Echo State Networks (ESNs) and physical reservoirs, celebrated for their computational efficiency and prowess in learning dynamical systems. However, contributions exploring other advanced methods (e.g., deep sequence models, graph-based forecasts, hybrid approaches) are equally encouraged.

The scope extends from theoretical advances in dynamical system modeling to deployable solutions for real-world problems. This Special Issue will highlight interdisciplinary research that bridges the gap between algorithmic innovation and practical application, ultimately contributing to the next generation of prognostic tools for Industry 4.0, scientific discovery, and beyond.

Topics of Interest:

This Special Issue covers a broad range of topics, including but not limited to, the following:

Novel Methodologies for Forecasting and Prognostics:

• Reservoir Computing-based approaches: Echo State Networks, deep reservoirs, and quantum and physical RC implementations for time-series prediction.
• Spatiotemporal forecasting with Graph Neural Networks (GNNs) and transformers.
• Explainable AI (XAI) and interpretable Machine Learning for trustworthy prognostics.
• Hybrid models integrating physics-based and data-driven methods for prediction.
• Uncertainty quantification and confidence estimation in prognostic models.
• Transfer learning and few-shot learning for prognostics under data scarcity.
• AI-driven modeling of critical transitions and extreme event prediction.

Industrial Applications and Industry 4.0:

• Predictive maintenance remaining useful for life estimation in manufacturing, energy, and aerospace systems.
• Prognostic health management (PHM) for cyber–physical systems and digital twins.
• Fault detection, diagnosis, and prognosis in large-scale industrial IoT networks.
• Forecasting for smart grid stability, energy load, and renewable energy output.
• Supply chain risk prediction and logistics optimization.
• Prognostic models for robotic systems and autonomous operations.

Scientific Applications and Discovery:

• Prognostics in climate science and environmental modeling (e.g., weather forecasting, extreme weather events).
• Biomedical prognostics: Disease progression forecasting, personalized treatment outcome prediction.
• Analysis and forecasting of physiological and neural signals (e.g., EEG, MEG, ECG, fMRI).
• Financial market prediction and economic forecasting under uncertainty.
• Prognostic models for material science and complex material degradation.

Submission Guidelines:

We invite the submission of original research articles, comprehensive reviews, and perspective papers that contribute to the advancement of prognostic model development and application. Submissions should present novel methodologies, compelling applications, or insightful interdisciplinary studies. All manuscripts will undergo a rigorous peer-review process to ensure the highest quality and relevance to this Special Issue.

Expected Impact:

This Special Issue will provide a platform for researchers and practitioners to share the latest advancements in prognostic modeling for complex systems. By showcasing a diverse set of approaches—from the highly efficient Reservoir Computing to other cutting-edge AI techniques—this Special Issue will serve as a valuable resource for advancing the field. It will foster dialog between theoreticians and application experts, bridge disciplines, and inspire new research directions for creating reliable, scalable, and interpretable forecasting tools. This collection will be an essential reference for academics, industry professionals, and policymakers aiming to solve critical prediction challenges.

We look forward to receiving your contributions and advancing the dialog on the transformative potential of AI in complex systems.

Prof. Dr. Alexander N. Pisarchik
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• forecasting and prognostics
• Industry 4.0
• scientific applications