Special Issue - Scientific Machine Learning for Manufacturing Processes and Material Systems - Guest Editorial

Aug 5, 2026

Upload by Riley

Guest Editorial introduces the special issue on scientific machine learning for manufacturing processes and material systems, explaining why data-driven surrogates are advancing but also why newer methods are needed. It highlights limitations such as noise, limited budgets, data sparsity, and insufficient interpretability and robustness. The editorial positions scientific ML as a new paradigm to improve computational efficiency with domain awareness, interpretability, and model reliability. It outlines invited topics including physics-informed ML, diagnostics and control, uncertainty quantification, adaptive learning, explainable AI and causal inference, high-throughput frameworks, and knowledge-driven reasoning, then previews nine included papers and their contributions to additive manufacturing and materials modeling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages5

Reading Time13 min

AccessFree to download

Guest Editorial

Special Issue focus and motivation

Invited topics of interest

Overview of nine featured papers

Guest Editorial Special Issue: Scientific Machine Learning for Manufacturing Processes and Material Systems Editorial Board consists of (alphabetically by last name) Dr. Anindya Bhaduri, GE Research, USA, [Anindya.Bhaduri@ge.com](Anindya.Bhaduri@ge.com) Prof. Francisco Chinesta, ENSAM Institute of Technology, France, [Francisco.CHINESTA@ensam.eu](Francisco.CHINESTA@ensam.eu)[ ](Francisco.CHINESTA@ensam.eu)Prof. Elias Cueto, University of Zaragoza, Spain, [ecueto@unizar.es](ecueto@unizar.es) Prof. Dehao Liu, Binghamton University, USA, [dehaoliu@binghamton.edu](dehaoliu@binghamton.edu) Dr. John G. Michopoulos, Naval Research Laboratory, USA, [john.g.michopoulos.civ@us.navy.mil](john.g.michopoulos.civ@us.navy.mil)[ ](john.g.michopoulos.civ@us.navy.mil)Dr. Sandipp Krishnan Ravi, GE Research, USA, [SandippKrishnan.Ravi@ge.com](SandippKrishnan.Ravi@ge.com) Prof. Jian-Xun Wang, University of Notre Dame, USA, [JWANG33@nd.edu](JWANG33@nd.edu) Computational modeling, simulation and optimization of manufacturing processes and materials systems have been a persistent endeavor of the engineering research community at large. Significant progress has been achieved in this field due to the exponential increase in computing power, and the incorporation of data-driven modeling methods. Process and systems modeling often involves expensive and time-intensive simulations and experiments. Incorporation of machine learning (ML) models as efficient surrogate models has been proven to enhance the human understanding on the behavior of the system at hand, and reduce the computational optimization cost of the concerned processes and systems. However, there is a rising need to go beyond the conventional data-driven techniques to address challenges, such as, presence of noise in data, limited budget, data sparsity, lack of interpretability of ML models, etc. Tackling these issues will enable more comprehensive modeling of manufacturing processes and discovery of novel material systems. This special issue focuses in the new paradigm called scientific ML, and aims to explore and potentially resolve issues related to improving computational efficiency, incorporating domainawareness, improving interpretability and robustness into the models and modeling techniques. In particular, this special issue has invited both full research and review papers focusing on research advances in the areas of scientific machine learning for manufacturing processes and material systems. The announced topics of interest included but were not limited to the following topics: (1) Physics-informed ML for process/materials design and optimization. (2) Physics-informed ML for diagnostics, prognostics and process control. (3) Uncertainty quantification in modeling (including physics-informed ML, etc.) . (4) Leveraging high-throughput framework for modeling and optimization. (5) Efficient modeling through adaptive and active learning algorithms. (6) Explainable AI and causal inference augmented predictive modeling. (7) Exploring state-of-the-art ML algorithms in modeling and optimization. (8) Understanding of systems through knowledge representation and reasoning. (9) Leveraging data-fusion and multi-fidelity techniques in modeling. As result of this call, this issue features nine papers delving into various topics, including: probabilistic printability maps for laser powder bed fusion via functional calibration and uncertainty propagation; unsupervised anomaly detection via nonlinear manifold learning; a physics-informed general convolutional network for the computational modeling of materials with damage; multi-fidelity physics-informed generative adversarial network for solving partial differential equations; stochastic defect localization for cooperative additive manufacturing using gaussian mixture maps; stress representations for tensor basis neural networks: alternative formulations to finger-rivlin-ericksen; machine-learning metacompu

FAQs

Why does the editorial argue for going beyond conventional data-driven ML in manufacturing and materials?

It notes persistent challenges such as noise in data, limited budget and data sparsity, and lack of interpretability and robustness in many ML models used as surrogates.

What is the main goal of the special issue on scientific ML?

To explore and potentially resolve problems related to improving computational efficiency while adding domain awareness, interpretability, and robustness into modeling techniques for manufacturing processes and material systems.

Which kinds of research topics were invited for this special issue?

The call covers areas such as physics-informed ML for design/optimization and for diagnostics and control, uncertainty quantification, high-throughput modeling and optimization, adaptive or active learning, explainable AI and causal inference, and knowledge representation and reasoning.

Aug 5, 2026

Upload by Riley