The alloy in question, Mg-8wt.%Li, sits in a sweet spot of composition. Above roughly 8 percent lithium by weight, the material becomes dual-phase, containing both the hexagonal close-packed alpha phase typical of magnesium and the body-centered cubic beta phase that lithium stabilizes. That b.c.c. beta phase is the secret ingredient: it deforms far more readily than the hexagonal phase, endowing the alloy with ductility that no other magnesium alloy system can match. The Mg–Li family holds the record for elongation among all magnesium alloys, although its absolute strength remains modest, which is precisely why understanding and controlling its deformation mechanisms matters so much for lightweight structural applications.

To push the alloy into its most deformable state, the team turned to high-pressure torsion, a severe plastic deformation technique in which a disk of material is squeezed under a nominal pressure of 4 gigapascals while being twisted through five full turns. The process shears the microstructure into an ultrafine grain structure. Electron microscopy and transmission Kikuchi diffraction revealed that the extruded material, which started with grains of about 2.2 micrometers, was refined to an average spatial grain size of roughly 0.4 micrometers, with individual subgrains resolved in the range of 0.15 to 0.40 micrometers. The two phases became elongated and aligned with the torsion direction, a signature of the intense shear the disk experienced.

Miniature tensile specimens, cut from the disk mid-radius by electric discharge machining with a gauge cross-section of just 0.8 by 0.8 millimeters, were then pulled at room temperature across strain rates spanning from 10^-5 to 10^-3 per second. The results were striking. The peak stress varied dramatically with strain rate, a hallmark of high strain rate sensitivity, and the alloy exhibited large elongations at the slowest rates of 10^-4 and 10^-5 per second. This unusual increase in ductility at low strain rates, previously reported for similar alloys, is exactly the behavior that makes dual-phase Mg–Li alloys candidates for room-temperature superplasticity, a property normally reserved for ceramics and exotic superalloys at soaring temperatures.

Creep tests added another layer of intrigue. Under constant loads between 10 and 100 megapascals at room temperature, and at 373 kelvin under 10 and 25 megapascals, the creep rates steadily decreased as strain accumulated. Such decelerating creep is normally seen in coarse-grained metals at high temperature, where dislocation substructures build up during the initial stage of deformation, but that explanation should not apply to an ultrafine-grained material whose grains are already smaller than any stable subgrain size. The authors point to a recent study on ultrafine-grained aluminum that attributed similar behavior to strengthening by dynamic recovery, and they adopted the strain rate at 2 percent strain as representative of the as-processed state for further analysis.

The most consequential number to emerge from the creep experiments was the activation energy. Using the temperature dependence of the creep rate between room temperature and 373 kelvin, the team estimated activation energies of 64 kilojoules per mole at 25 megapascals and 77 kilojoules per mole at 10 megapascals. Both values fall well below the 135 kilojoules per mole for self-diffusion and the 92 kilojoules per mole for grain boundary diffusion in pure magnesium. The authors attribute this reduction to the large fraction of the b.c.c. beta phase, which has a lower melting temperature and correspondingly lower diffusion barriers. Reported grain boundary diffusion energies for related alloys, 65 kilojoules per mole for Mg-9%Li and 61 kilojoules per mole for Mg-8%Li-1%Zn, bracket the measurements, and the team settled on 75 kilojoules per mole for their modeling. The low activation energy is a clear signal that thermally activated mechanisms are at work even at room temperature.

To interpret these observations, the researchers deployed a two-pronged computational strategy. First, they applied a recently updated model for grain boundary sliding, the mechanism in which grains slide past one another along their boundaries, which is the canonical explanation for superplastic flow. The model treats the total flow stress as the sum of a threshold stress, capturing other strengthening contributions such as solid solutions, and a grain boundary sliding contribution that depends on shear modulus, temperature, grain size, Burgers vector and the grain boundary diffusion coefficient. A rectified linear function is used as a mathematical constraint to prevent the model from predicting negative stresses when thermal activation is strong. Second, they trained machine learning algorithms on 67 carefully curated data points from the literature, restricted to dual-phase Mg–Li alloys containing no alloying elements other than lithium, with lithium contents between 8 and 12 weight percent, to keep composition effects from contaminating the analysis.

The machine learning lineup included two black-box models, support vector regression and random forest, and two white-box symbolic regression models, one unconstrained and one constrained by dimensional consistency. The black-box models, evaluated with Shapley Additive Explanations, agreed that temperature is the dominant control on flow stress, that strain rate plays an intermediate role, and that grain size matters only marginally. On the training data the algorithms performed well, with mean absolute percentage errors ranging from 11.5 percent for the random forest to 35.3 percent for support vector regression. But when the models were asked to predict the new experimental data generated in this study, the black-box approaches collapsed, producing errors exceeding 250 percent, while the grain boundary sliding model and the dimension-constrained symbolic regression held their ground at roughly 35 percent error.

The deeper story emerged when the team plotted predicted flow stress against grain size, strain rate and temperature and compared the trends with experiment. The experiments revealed a fascinating crossover: for grains larger than about half a micrometer, refining the grains strengthens the alloy in classic Hall–Petch fashion, but below that threshold, further refinement actually softens it, the inverse Hall–Petch regime. Only the grain boundary sliding model captured this transition cleanly. The black-box models failed to reproduce the steep strain rate dependence of the flow stress, with support vector regression even predicting a physically implausible negative strain rate sensitivity at high rates. The dimension-constrained symbolic regression, guided by physically meaningful features such as the Zener–Holomon parameter and dimensionless groups derived from the grain boundary sliding equations, performed far better than its unconstrained counterpart, demonstrating that embedding physical knowledge into machine learning pays real dividends.

The take-home message resonates well beyond magnesium. Machine learning models are only as trustworthy as the data behind them, and with a sparse training set of 67 points, the black-box algorithms interpolated plausibly but extrapolated badly, especially outside the temperature and strain rate ranges they had seen. The century-old physics-based model, by contrast, reproduced every experimental trend once its activation energy was adapted to the dual-phase alloy. For engineers dreaming of lightweight magnesium–lithium components that can be superplastically formed at room temperature, the study offers both a validated design tool and a cautionary tale: in materials science, the white box and the physics still matter, and the smartest models are those that know the laws they are trying to learn.

Subject of Research: Deformation mechanisms and grain boundary sliding in ultrafine-grained dual-phase Mg–Li alloys processed by high-pressure torsion

Article Title: Analysis of deformation mechanism of dual-phase Mg–Li alloy, processed by high-pressure torsion, using experiments and machine learning

Article References: Carvalho, A. P., Edalati, K., & Figueiredo, R. B. (2026). Analysis of deformation mechanism of dual-phase Mg–Li alloy, processed by high-pressure torsion, using experiments and machine learning. Journal of Materials Science. https://doi.org/10.1007/s10853-026-13355-x

Image Credits: AI Generated

DOI: 10.1007/s10853-026-13355-x

Keywords: magnesium-lithium alloy, high-pressure torsion, grain boundary sliding, severe plastic deformation, machine learning, superplasticity, creep, activation energy, Hall-Petch, symbolic regression, ultrafine grains, flow stress

The study, published in the Journal of Materials Science by Hamed Shahmir and Sina Kooshamanesh of Tarbiat Modares University, Mohammad Sajad Mehranpour of the University of Tehran, and veteran superplasticity researcher Terence G. Langdon, focuses on a class of materials called high-entropy alloys. Unlike conventional metals, which are built around one dominant element with small additions of others, high-entropy alloys mix four, five, or even more principal elements in roughly equal proportions. The result is a chaotic atomic landscape that can produce extraordinary combinations of strength, ductility, and thermal stability, properties that have made these materials one of the hottest topics in metallurgy since their emergence in the early 2000s.

Superplasticity is not a given for any metal. It requires a very fine, stable grain structure, typically with grains smaller than about ten micrometers, and it generally appears only within a specific window of temperature and strain rate. Under those conditions, the dominant deformation mechanism shifts to grain boundary sliding, in which individual crystalline grains slide past one another like bricks in a lubricated wall rather than stretching internally. When this mechanism operates cleanly, elongations exceeding several hundred percent, and in exceptional cases several thousand percent, become possible. The problem is that the conditions are delicate: grains must remain small at high temperature, which demands resistance to grain growth, and the alloy’s microstructure must not degrade catastrophically during deformation.

High-entropy alloys are theoretically ideal candidates for this behavior. Their sluggish atomic diffusion, a consequence of the complex multi-element lattice, helps stabilize fine grains at elevated temperatures, and many of them form dual-phase or multiphase structures that further pin grain boundaries in place. Over the past decade, laboratories around the world have demonstrated superplastic flow in alloys such as the famous equiatomic CoCrFeMnNi, various AlCoCrCuFeNi derivatives, and a growing family of medium-entropy and eutectic compositions, some processed by severe plastic deformation techniques like high-pressure torsion to create the necessary ultrafine grains. But each demonstration has come at the cost of extensive trial-and-error experimentation.

That cost is precisely what the new research set out to eliminate. The authors compiled the available experimental data on superplasticity in nanostructured and ultrafine-grained high-entropy alloys, spanning a wide range of chemical compositions, processing routes, grain sizes, testing temperatures, and strain rates. This curated dataset became the training ground for machine learning models tasked with learning the hidden relationships between a material’s composition and processing history and its superplastic response. Machine learning, in essence, searches for patterns in data that human intuition and classical constitutive equations may miss, and it can do so across a multidimensional space of alloying elements that no experimental campaign could ever explore exhaustively.

The approach reflects a broader transformation sweeping through materials science. In recent years, machine learning has been applied to predict the hardness and grain refinement of severely deformed metals, to screen out high-entropy alloys prone to forming brittle sigma phase, to identify thermomechanical processing parameters that deliver desired combinations of strength and ductility, and to estimate properties such as stacking fault energy in refractory multi-principal element alloys. High-throughput computational screening, coupled with thermodynamic databases and empirical parameters, now allows researchers to explore thousands of candidate compositions on a laptop before a single ingot is melted. The new study extends this toolkit to one of the most mechanically demanding and commercially valuable properties of all: the ability to deform superplastically.

Why does this matter industrially? Superplastic forming is already used commercially in aerospace, particularly for titanium alloys in aircraft structures, where complex double-skin panels and engine components are blow-formed at high temperature. But the process is slow, energy-intensive, and limited to a handful of well-characterized alloys whose superplastic windows were established through decades of empirical work. If machine learning can rapidly identify which high-entropy alloys will exhibit superplasticity, and under what conditions of temperature, strain rate, and grain size, the timeline for qualifying new formable materials could shrink from decades to years. Lighter, stronger, and more corrosion-resistant alloys could enter superplastic forming lines, enabling aircraft and spacecraft structures that are currently impractical to manufacture.

The scientific significance goes beyond engineering convenience. By training models on data from many different alloy families, the researchers can interrogate which compositional and microstructural features matter most for superplastic flow. Grain size emerges as a central variable, as expected from the classical mechanics of grain boundary sliding, where strain rate scales strongly with the inverse of grain size raised to a power of roughly two. But the model can also weigh subtler factors, such as the stabilizing effect of sluggish diffusion on grain growth, the role of second-phase particles in pinning boundaries, and the influence of phase fraction in multiphase alloys. In doing so, machine learning acts not just as a predictor but as a hypothesis generator, pointing experimentalists toward the mechanisms most worth investigating.

There are, of course, important caveats. Machine learning models are only as good as the data they learn from, and superplasticity data for high-entropy alloys remain relatively sparse compared with conventional alloys. The field of small-data machine learning in materials science has developed techniques to handle this scarcity, including careful feature selection, regularization, and physics-informed constraints, but extrapolation beyond the training data remains risky. A model trained on face-centered cubic alloys may not reliably predict the behavior of refractory body-centered cubic systems, and superplasticity depends on processing details, such as the severity of prior deformation and annealing conditions, that must be captured accurately in any dataset. The authors note that their underlying data will be made available on request, a practice that supports reproducibility and future model refinement.

Nevertheless, the trajectory is clear. Twenty years after the CoCrFeMnNi alloy was first reported, high-entropy alloys have matured from laboratory curiosities into serious candidates for structural applications, and superplasticity has emerged as one of their most promising attributes. Combining that experimental maturity with the predictive power of machine learning creates a genuine shortcut: instead of melting, deforming, and testing alloy after alloy, researchers can computationally shortlist the compositions most likely to flow like taffy at high temperature, then devote laboratory resources only to the best candidates. If that workflow becomes standard, the next generation of superformable metals may be designed on a computer before they ever exist in a crucible, and the seventy-five-year-old science of superplasticity may be entering its fastest-moving era yet.

Subject of Research: Machine learning prediction of superplasticity in high-entropy alloys

Article Title: Using machine learning to predict superplasticity in high-entropy alloys

Article References: Shahmir, H., Kooshamanesh, S., Mehranpour, M. S., & Langdon, T. G. (2026). Using machine learning to predict superplasticity in high-entropy alloys. Journal of Materials Science. https://doi.org/10.1007/s10853-026-13754-0

Image Credits: AI Generated

DOI: 10.1007/s10853-026-13754-0

Keywords: high-entropy alloys, superplasticity, machine learning, grain boundary sliding, ultrafine-grained materials, severe plastic deformation, materials science, computational materials science, grain refinement, aerospace forming, CoCrFeMnNi, thermal stability