The material was the equiatomic, face-centered-cubic alloy commonly called the Cantor alloy, a five-element solid solution containing chromium, manganese, iron, cobalt and nickel. The study cites a stacking fault energy of approximately 30 ± 5 millijoules per square metre at room temperature, a comparatively low value associated with the material’s capacity for twinning and, under sufficiently severe deformation, transformation to a hexagonal close-packed structure. High-pressure torsion combines high pressure with large shear strain, allowing the researchers to vary deformation temperature while tracking changes in phase stability, microstructure, crystallographic texture and microhardness.

For the experiments, the team arc-melted and drop-cast the alloy under high-purity argon. The ingots were homogenized for 48 hours at 1,473 kelvin, after which disks with a radius of 4 millimetres and an initial thickness of about 0.8 millimetres were cut from them. The disks were deformed under a quasi-hydrostatic nominal pressure of 7.8 gigapascals at 77, 293, 473, 573 or 673 kelvin.

Following five rotations, the estimated maximum shear strain was about 160. Synchrotron X-ray diffraction and Rietveld refinement were used to identify phases and estimate their volume fractions, while diffraction peak broadening was used to estimate average crystallite sizes. The mean error in the refined phase fractions was approximately 0.4 percent.

At 77 kelvin, high-pressure torsion partially transformed the original face-centered-cubic alloy into a hexagonal close-packed phase, described as ε-martensite. Quantification indicated that the transformed phase accounted for 67 percent of the material at a shear strain near 100. The transformation was therefore a major part of the low-temperature microstructure rather than a minor secondary effect.

Diffraction measurements also showed that the mean grain size of the surviving face-centered-cubic phase increased from approximately 35 nanometres after deformation at 77 kelvin to about 50 nanometres at 473 kelvin. The hexagonal phase formed at 77 kelvin had a mean size of roughly 45 nanometres, showing that both phases were refined to comparable nanoscale dimensions. At the highest deformation temperature, 673 kelvin, the alloy decomposed into body-centered-cubic and tetragonal σ phases.

Their combined fraction was approximately 1.9 percent at a shear strain near 50 but rose to about 11 percent near a strain of 100, demonstrating that decomposition was strongly dependent on accumulated strain. Severe deformation creates vacancies, dislocations and grain boundaries that enhance atomic diffusion and provide nucleation sites, allowing precipitation to proceed more rapidly than in coarse-grained, undeformed material. Despite this precipitation, the mean grain size at 673 kelvin reached about 130 nanometres by diffraction and 120 nanometres in electron backscatter diffraction.

The latter analysis showed a globular structure consistent with continuous dynamic recrystallization and a bimodal grain-size distribution. Additional measurements helped distinguish the proposed explanation from other microstructural changes. Above room temperature, the dislocation density in the face-centered-cubic phase decreased with increasing deformation temperature, consistent with enhanced dynamic recovery and greater atomic mobility.

The dislocation density was also lower after deformation at 77 kelvin, possibly because of self-annealing and because the hexagonal phase became unstable during unloading or reheating and reversed toward the face-centered-cubic structure. These recovery effects would ordinarily be associated with reduced hardness, so they did not account for the observed increase. The crystallographic texture remained weak and changed little across most processing temperatures; accordingly, the researchers judged its influence through variations in the Taylor factor to be negligible.

Texture randomization was consistent with a contribution from boundary sliding, although it was not direct proof of that process. Room-temperature microhardness increased along the radial shear-strain gradient within each disk and generally saturated above a shear strain of about 60. The annealed, undeformed alloy had a Vickers microhardness of 123, while the values measured after torsion were higher.

When saturation hardness was plotted against deformation temperature, it followed an almost linear upward trend, apart from additional hardening caused by precipitation at 673 kelvin. After an approximate subtraction of that precipitation contribution, the 673-kelvin point also fell close to the trend. The alloy processed at room temperature was harder than the material processed at 77 kelvin, reversing the expectation that the more transformed and more highly refined low-temperature specimen would be harder.

Measurements at 77 and 673 kelvin had relatively large scatter, associated with inhomogeneous deformation at low temperature and continuing precipitation at high temperature. The central interpretation is an inverse Hall–Petch regime. Conventional Hall–Petch strengthening predicts that smaller grains impede dislocation motion more effectively and therefore make a polycrystalline material harder.

In this study, however, microhardness increased with grain size across the face-centered-cubic phase, from roughly 35 to 130 nanometres. The authors connect this reversal to sliding along grain and phase boundaries in an exceptionally fine, highly defective structure. Boundaries generated by severe deformation are far from equilibrium and can support relatively rapid boundary-mediated deformation.

Shear transformation zones, comprising clusters of closely packed atoms that rearrange cooperatively to accommodate local shear, were discussed as a plausible mechanism for nanoplasticity. The interpretation contrasts with ultrafine-grained materials governed by conventional Hall–Petch strengthening, where hardness decreases as grain size increases and recovery becomes more influential. The experiment has an important limitation arising from the time between deformation and measurement.

Warm specimens remained at or near their deformation temperature for roughly 30 to 60 seconds while being unloaded and removed from the anvils, making some static annealing unavoidable. Earlier work cited in the study found that a 30-second heat treatment at 723 kelvin after room-temperature high-pressure torsion could increase hardness by about 30 Vickers units, although phase decomposition may also have contributed to that increase. Because the present microhardness measurements were made only after deformation and cooling to room temperature, they cannot cleanly separate deformation-state hardening from subsequent annealing effects.

Deformation at 77 kelvin was also heterogeneous, as indicated by torque behavior reported in related work and by the wide scatter in indentation measurements. Such localization can produce regions with different strain, microstructure and hardness, adding uncertainty to comparisons among processing temperatures. Overall, the study shows that reducing a high-entropy alloy to nanometre scale does not automatically produce stronger material in the conventional sense.

In CrMnFeCoNi processed by high-pressure torsion, larger grains within the relevant nanostructured range were associated with greater room-temperature hardness rather than lower hardness. The combined phase, grain-size, dislocation-density and texture measurements point to grain- and phase-boundary sliding as the principal explanation, while short-term annealing may also have contributed. These findings apply to the tested Cantor alloy and processing conditions rather than establishing a universal rule for high-entropy alloys.

The authors propose future work using in situ torque measurements during torsion to determine flow stress directly and better distinguish deformation mechanisms from annealing effects.

Subject of Research: Temperature-dependent nanostructuring and anomalous microhardness in high-pressure-torsion-deformed CrMnFeCoNi high-entropy alloy

Article Title: Anomalous hardening of CrMnFeCoNi high-entropy alloy deformed by high-pressure torsion

Article References: Chulist, R., Hohenwarter, A., Pippan, R., Schell, N., & Skrotzki, W. (2026). Anomalous hardening of CrMnFeCoNi high-entropy alloy deformed by high-pressure torsion. Journal of Materials Science. https://doi.org/10.1007/s10853-026-13649-0

Image Credits: AI Generated

DOI: 10.1007/s10853-026-13649-0

Keywords: CrMnFeCoNi, high-entropy alloy, high-pressure torsion, inverse Hall–Petch effect, nanostructured metals, grain-boundary sliding, severe plastic deformation, phase transformation, microhardness, alloy hardening, Anomalous, hardening

The research, carried out by Thi-Nhai Vu of Nha Trang University and Van-Trung Pham and colleagues at the University of Danang – University of Science and Technology in Vietnam, relies on molecular dynamics simulations, a technique that tracks the motion of every individual atom in a material by solving the classical equations of motion under an interatomic potential. Rather than testing bulk samples in a mechanical testing frame, the team simulated nanoindentation, the process of pushing a hard, sharply pointed tip into a material and measuring its resistance. Nanoindentation is the standard method for probing hardness and elastic modulus at very small length scales, and by reproducing it atom by atom, the researchers could watch dislocations nucleate, grain boundaries slide, and stacking faults spread in real time, something no laboratory microscope can capture with such completeness.

The first major finding concerns the celebrated Hall-Petch relationship, one of the oldest rules in metallurgy. For more than half a century, engineers have known that shrinking the grains of a polycrystalline metal makes it harder, because grain boundaries act as obstacles that block the glide of dislocations, the line defects responsible for plastic flow. The simulations confirmed this classic strengthening trend in CoCuFeNiPd alloys with larger grains, where plastic deformation was dominated by dislocation activity nucleated near the indenter tip and propagating through the crystal interior. But when the grain size was reduced into the ultrafine nanocrystalline regime, the trend reversed dramatically. Hardness and the reduced Young’s modulus began to fall rather than rise as grains became smaller, a phenomenon known as inverse Hall-Petch behavior.

The reason for this reversal, revealed directly by the atomic-scale trajectories, is a change in the dominant deformation mechanism. In the inverse Hall-Petch regime, grains have become so small that dislocations can no longer pile up effectively against boundaries; instead, the material deforms by grains sliding past one another along their shared boundaries and by whole grains rotating under the indenter’s pressure. Grain boundary sliding and grain rotation allow the material to accommodate strain without the intense dislocation activity that characterizes conventional plasticity. This mechanistic crossover has been observed in other nanocrystalline metals and ceramics, but the present study pins down how it plays out in a chemically complex, five-element high-entropy system, where the rugged energy landscape created by chemical disorder adds further obstacles to dislocation motion.

The second variable the team explored was the palladium concentration, denoted by the subscript x in CoCuFeNiPdx. Palladium is the largest and heaviest of the five elements in this alloy family, and adding it increases what metallurgists call lattice distortion: the local warping of the crystal lattice caused by atoms of different sizes trying to share the same lattice sites. The simulations showed that increasing Pd content enhances both hardness and indentation resistance. The mechanism is twofold. First, stronger lattice distortion raises the frictional resistance that dislocations experience as they move through the lattice, effectively making the entire crystal a rougher terrain for defect motion. Second, higher palladium levels promote short-range ordering, a subtle chemical phenomenon in which atoms of particular species preferentially occupy neighboring sites, creating local patterns within the nominally random solid solution. These ordered domains act as additional barriers that significantly impede dislocation glide, a strengthening route that has attracted intense interest since recent experimental and computational work demonstrated that short-range order can simultaneously boost the strength and ductility of high-entropy alloys.

However, the study also uncovered a cautionary limit. When the palladium content becomes excessive, the alloy begins to undergo local phase separation, with palladium-rich regions segregating from the rest of the matrix. This chemical inhomogeneity suppresses the material’s ability to accommodate strain, undermining the very ductility and damage tolerance that make high-entropy alloys attractive in the first place. The message for alloy designers is that palladium is a powerful strengthening agent only up to an optimum concentration; beyond that point, the benefits of lattice distortion and short-range ordering are outweighed by the embrittling effects of compositional segregation. This kind of composition-property trade-off is exactly the information needed to guide the rational design of Pd-containing HEAs for real applications.

Temperature emerged as the third decisive factor. As the simulation temperature increased, the alloys exhibited pronounced thermal softening, with both hardness and elastic modulus declining. Elevated temperature promotes structural disorder, thermally shaking atoms out of their ideal lattice positions and weakening the short-range order that had helped block dislocations. At the same time, the increased atomic disorder interferes with the propagation of dislocations in a different way, scattering and absorbing them before they can carry plastic deformation efficiently across grains. The net result is a material that yields more easily and deforms more diffusely at high temperature, an important consideration for any application in which nanoscale contact occurs under thermal load, such as microelectromechanical systems, high-temperature coatings, or cutting tools.

Perhaps the most valuable contribution of the work is its unified atomic-scale picture of how these mechanisms couple. The researchers demonstrate that nanoindentation-induced deformation in CoCuFeNiPdx alloys is never governed by a single process but by the simultaneous evolution of grain boundary activity, dislocation nucleation, stacking fault formation, and amorphous transformation, the latter being the local loss of crystallinity under the extreme contact pressures beneath the indenter tip. Stacking faults, which are planar packing defects in the face-centered cubic lattice, appear as intermediate carriers of plasticity between perfect dislocation slip and full amorphization. Which of these channels dominates depends on grain size, composition, and temperature, and the simulations show how shifts in one variable can redirect the entire deformation pathway. This mechanistic map gives experimentalists concrete signatures to look for, for example in transmission electron microscopy of indented regions, and gives modelers benchmarks against which to validate larger-scale simulations.

The study also situates itself within a rapidly growing literature on high-entropy alloys, a field launched in 2004 when independent groups led by Jien-Wei Yeh and Brian Cantor first reported the surprising stability and properties of multi-principal-element alloys. In the two decades since, HEAs have been explored for structural, cryogenic, irradiation-resistant, and high-temperature applications, and concepts such as the four core effects of high-entropy materials, including severe lattice distortion and sluggish diffusion, have been progressively clarified. Recent work has highlighted chemical short-range order as a tuning knob of exceptional power, and the present results extend that theme to the specific case of palladium-bearing CoCuFeNiPd, an alloy system that earlier simulations had already flagged as one where short-range ordering and grain boundary segregation can inhibit the onset of inverse Hall-Petch softening.

For engineers thinking about applications, the relevance is direct. Nanoscale contact governs the performance and reliability of micro- and nanoelectromechanical devices, thin-film coatings, wear-resistant surfaces, and precision machining processes. A material that maintains high hardness and elastic resilience while tolerating strain at elevated temperature is the ideal candidate for such roles, and the new results indicate how to move toward that target: choose grain sizes on the Hall-Petch side of the crossover, tune palladium content high enough to maximize distortion and ordering but low enough to avoid phase separation, and account for thermal softening in any environment where heat is present. The Vietnamese team’s atomistic tour of CoCuFeNiPd thus delivers both fundamental insight into how chemically complex crystals deform under contact and practical guidance for the next generation of high-entropy alloys designed for nanoscale service. As simulation tools and interatomic potentials continue to improve, studies of this kind are expected to play an ever larger role in screening alloy compositions before a single ingot is melted, accelerating the path from atomic-scale understanding to real-world materials.

Subject of Research: Atomic-scale simulation of grain size, palladium composition, and temperature effects on the nanoindentation behavior of CoCuFeNiPdx high-entropy alloys

Article Title: Atomic-scale investigation of grain-size, Pd composition, and temperature effects on the nanoindentation behavior of CoCuFeNiPdx high-entropy alloys

Article References: Vu, T.-N., Pham, V.-T., Tran, N.-H., Luu, D.-B., Tao, Q.-B., & Nguyen, T.-T. (2026). Atomic-scale investigation of grain-size, Pd composition, and temperature effects on the nanoindentation behavior of CoCuFeNiPdx high-entropy alloys. Journal of Materials Science. https://doi.org/10.1007/s10853-026-13891-6

Image Credits: AI Generated

DOI: 10.1007/s10853-026-13891-6

Keywords: high-entropy alloys, nanoindentation, molecular dynamics, Hall-Petch, grain boundary sliding, palladium, short-range ordering, lattice distortion, dislocations, thermal softening, hardness, CoCuFeNiPd

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