Southwest Research Institute (SwRI) and St. Mary’s University have embarked on a groundbreaking collaboration aimed at revolutionizing the future of hydrogen storage technology. This joint venture seeks to develop a comprehensive, physics-based forecasting tool capable of predicting the degradation and long-term durability of titanium-iron (TiFe)-based metal hydride vessels. Leveraging a chemical and thermo-mechanical modeling framework, the project represents a significant leap forward in tackling one of the most persistent challenges in hydrogen storage materials science. This initiative is made possible through a $125,839 grant from the St. Mary’s-SwRI Technology and Applied Research (S²TAR) Program, designed to foster impactful research collaborations.

Metal hydrides are pivotal materials in the hydrogen energy landscape, serving as one of the few safe and compact solid-state options for hydrogen storage. These materials function by chemically binding hydrogen to metal lattices through chemisorption, effectively locking hydrogen atoms within the structure. Unlike high-pressure gaseous tanks or cryogenic liquid hydrogen storage, metal hydrides offer improved safety profiles and reduce energy-intensive requirements. However, despite these advantages, their widespread application is hindered by their limited durability and performance degradation resulting from repeated hydrogen absorption and desorption cycles.

At the heart of this ambitious research endeavor is the intricate problem of metal hydride vessel degradation. Over numerous charge and discharge cycles, physical changes ensue within the alloy powders comprising the metal hydride bed. These changes include fracturing of particles, densification of the powder bed, and mechanical stresses that collectively impair hydrogen storage capacity and vessel performance. Traditional evaluation methods rely heavily on prolonged, costly experimental testing to assess long-term vessel integrity—a bottleneck that impedes innovation and commercialization.

The project team, headed by Dr. Richard S. Fu of SwRI and Dr. Mohamed Shaat of St. Mary’s University, seeks to transcend these limitations by integrating advanced physics-based simulations with targeted experimental validation. This dual approach aims to create a robust modeling framework capable of forecasting the lifecycle and operational durability of TiFe metal hydride vessels. The predictive tool will account for the coupled chemical, thermal, and mechanical phenomena driving hydrogen cycling performance over hundreds or even thousands of cycles.

Dr. Shaat is spearheading the development of an intricate, multiphysics computational framework at St. Mary’s University. This model is designed to encapsulate the complex interplay between hydrogen diffusion, chemisorption reactions, phase transformations within the metal hydride, heat generation and transfer, and the evolution of mechanical stress within the vessel. By accurately simulating these interconnected processes, the framework seeks to facilitate precise performance predictions, while also identifying design parameters and operational regimes that optimize both efficiency and vessel longevity.

Central to the team’s vision is the translation of fundamental physical and chemical principles of hydrogen interaction into computationally efficient predictive models. Dr. Shaat emphasizes the importance of capturing the coupling mechanisms—particularly how hydrogen transport influences thermal and mechanical responses and vice versa—in order to provide reliable simulations that replace and reduce the dependence on lengthy physical testing. This innovative approach promises to significantly reduce costs, accelerate development cycles, and improve hydrogen storage system designs.

On the experimental front, SwRI’s team, under Dr. Fu’s guidance, is undertaking controlled, long-term cycling experiments to collect essential validation data. By subjecting metal hydride vessels to realistic charge-discharge scenarios, they aim to quantitatively monitor performance degradation mechanisms as they unfold. These experiments will provide the empirical backbone necessary to calibrate and refine the modeling framework, ensuring that simulation outputs faithfully represent real-world behavior under operational conditions.

The synergy between modeling efforts and experiments forms the cornerstone of the project’s iterative design loop. As Dr. Fu explains, modeling insights will direct the focus of experimental tests to critical phenomena, while the resulting data will feedback to correct and enhance the models. This dynamic interplay is expected to unravel previously obscure degradation mechanisms by illuminating the coupled chemical, thermal, and mechanical interactions at work within the metal hydride vessels. Ultimately, this feedback-driven methodology will yield a predictive tool capable of guiding material improvements and engineering decisions.

Hydrogen’s emergence as a clean, versatile energy carrier is a key cornerstone of global efforts to decarbonize energy and transportation sectors. However, to fulfill its potential, advances in storage technology are imperative. Unlike batteries or fossil fuels, hydrogen storage demands novel materials and engineering solutions due to its unique physical and chemical characteristics. By focusing on metal hydride vessels, this project addresses a promising yet underdeveloped storage pathway that could unlock safer, more efficient hydrogen deployment across diverse applications.

The S²TAR funding mechanism plays an instrumental role in enabling this interdisciplinary collaboration by providing seed resources that draw on the expertise strengths of both SwRI and St. Mary’s University. This partnership is not only poised to produce high-impact scientific outcomes but also lays the foundation for sustained cooperation. Through this collaboration, the team is well-positioned to attract larger external funding sources from federal agencies and industry players focused on advancing hydrogen infrastructure and clean energy technology.

As work progresses, the team anticipates that their predictive modeling tool will be an invaluable resource for the hydrogen storage community. It will offer designers and researchers an evidence-based platform to evaluate new materials, optimize vessel designs, and predict operational lifetimes with higher confidence. By systematically addressing the core durability challenges of metal hydride storage, this project represents a wide-reaching advancement that could significantly accelerate solid-state hydrogen storage adoption worldwide.

In conclusion, this joint initiative by Southwest Research Institute and St. Mary’s University epitomizes the cutting edge of hydrogen storage research. Through combining rigor in experimental validation and sophistication in physics-based modeling, the project champions a future where hydrogen is stored more safely and efficiently. The knowledge generated here promises to not only rewrite the fundamentals of storage vessel degradation understanding but also to catalyze practical applications in the global hydrogen economy.

Subject of Research: Physics-based modeling and experimental validation of TiFe-based metal hydride hydrogen storage vessel degradation and durability.

Article Title: Advancing Solid-State Hydrogen Storage: Predictive Modeling and Experimental Synergy for Metal Hydride Vessel Durability

News Publication Date: June 24, 2026

Web References: https://www.swri.org/markets/energy-environment/power-generation-utilities/advanced-power-systems/hydrogen-energy-research?&utm_medium=referral&utm_source=eurekalert!&utm_campaign=s2tar-metal-hydrides-pr

Image Credits: Southwest Research Institute

Keywords

Hydrogen storage, metal hydrides, TiFe alloys, chemisorption, physics-based modeling, thermo-mechanical framework, hydrogen diffusion, phase transformation, performance degradation, solid-state hydrogen storage, experimental validation, multiphysics simulations

In a groundbreaking advancement poised to revolutionize semiconductor analysis, a team of researchers from the Institute of Science Tokyo has pioneered a tandem neural network (TNN) architecture that dramatically accelerates the inference of vital material parameters from transistor measurements. This novel machine learning framework addresses one of the most vexing challenges in semiconductor physics—the multivalued inverse problem—achieving unprecedented speed and accuracy that eclipses traditional computational methods.

Semiconductor devices underpin nearly every aspect of modern electronics, from smartphones to sophisticated computing systems. The performance and reliability of these devices hinge on intricate material properties such as defect densities, trap states, and charge carrier mobilities. While engineers can rapidly measure transistor behavior through current-voltage characteristics, deciphering the precise material attributes driving this behavior remains an elusive inverse problem. Conventional approaches rely heavily on iterative simulations and optimization techniques, often consuming hours or even days to converge on plausible solutions.

At the heart of the difficulty lies the phenomenon of multivaluedness: distinct combinations of semiconductor material parameters can yield virtually indistinguishable transistor responses. This ambiguity complicates the task of tracing device performance back to its physical origins. The research team recognized that conventional simulation frameworks are ill-equipped to navigate this degeneracy efficiently. Their insight was to harness the power of tandem neural networks, an innovative deep learning configuration capable of simultaenously enforcing physical consistency and mathematical plausibility in parameter estimation.

The tandem neural network developed by the team couples two interconnected models operating in series. The initial inverse model proposes candidate sets of material parameters based on observed transistor behavior. This output then feeds into a forward model pre-trained to reconstruct transistor characteristics from material parameters. By integrating the forward model’s reconstructions into the training loss function of the inverse network, the system effectively teaches itself to generate solutions that not only fit the measurement data but also align with the physical laws governing transistor operation.

Training this sophisticated architecture required an extensive dataset of over 1,000 simulated transistor measurements, specifically focusing on amorphous indium-gallium-zinc oxide (a-IGZO) transistors—a material of significant interest for flexible and transparent electronics. The dataset spanned a parameter space roughly 1,000 times broader than previous studies, encompassing six key variables: defect density, electron trap states, and carrier mobility among them. Astonishingly, the TNN inferred all six parameters from a single transistor current-voltage curve in less than one millisecond, achieving near-perfect accuracy across the range.

Beyond simulations, real-world validation was paramount. The researchers fabricated a series of a-IGZO transistors under five distinct processing conditions in their laboratories. When subjected to the TNN analysis, the model reproduced the measured device characteristics with exceptional fidelity, requiring no parameter tuning or iterative refinement. This immediate, high-precision performance marks a quantum leap compared to traditional simulation-dependent approaches that demand repetitive calculations, often spanning hours or days.

Assistant Professor Keisuke Ide, one of the principal investigators, highlighted the transformative implications of this speedup: “Our tandem neural network achieves a computational acceleration exceeding six orders of magnitude relative to conventional device simulation methods. This means what once took days can now be done almost instantaneously, radically changing the landscape of semiconductor diagnostics and research.”

The implications of this advancement extend well beyond academic curiosity. In industrial manufacturing, instantaneous and ultra-accurate assessment of transistor material properties can serve as an integral part of quality control, allowing defects and performance variants to be detected and addressed on the production line in real-time. This rapid feedback loop could markedly reduce waste and improve yield in semiconductor fabrication facilities.

Moreover, the TNN framework paves the way for autonomous laboratories where artificial intelligence designs, executes, and interprets experiments with minimal human oversight. By swiftly and reliably unraveling complex material-property relationships, AI-driven research tools can accelerate innovation cycles, optimizing device designs and material formulations in ways previously unattainable due to computational bottlenecks.

Interestingly, the tandem neural network architecture is not conceptually limited to semiconductors alone. The researchers underscore its potential applicability across a broad spectrum of inverse problems characterized by multivaluedness, spanning materials science, chemistry, optics, and possibly even biological systems where multiple underlying parameter sets may produce indistinguishable observational data.

The Institute of Science Tokyo, newly established in 2024 through the merger of Tokyo Medical and Dental University and Tokyo Institute of Technology, serves as a nexus for such cutting-edge interdisciplinary research. This project exemplifies the institute’s mission to advance scientific understanding and technology in ways that create tangible value for society.

As the demands for faster, smaller, and more efficient semiconductor components intensify, novel computational tools that can disentangle the complex interplay of material parameters swiftly and accurately become indispensable. The tandem neural network approach represents a critical milestone on this journey, ushering in a new era where machine learning not only supplements but fundamentally transforms physical sciences research.

This rise of AI-powered physics inference is poised to fuel accelerated material discovery, optimized manufacturing, and ultimately, enhanced electronic devices that power tomorrow’s technological landscape. With this tandem neural network, researchers have cracked open the door to solving multivalued inverse problems at blistering speeds, a feat that was once considered beyond reach.

Subject of Research: Semiconductor material characterization using machine learning

Article Title: Tandem Neural Network Rapidly Solves Multivalued Inverse Problems: Application to Oxide-Semiconductor Characterization

News Publication Date: 27-May-2026

Web References: https://doi.org/10.1002/aisy.70437

Image Credits: Institute of Science Tokyo

Keywords

Artificial intelligence, machine learning, semiconductor analysis, inverse problems, multivaluedness, twin neural networks, material characterization, oxide semiconductors, transistor diagnostics, amorphous indium-gallium-zinc oxide, computational speedup, autonomous laboratories