There is a growing interest in High Entropy Alloys (HEAs) due to their outstanding mechanical properties. Most simulation studies have focused on face-centered cubic (fcc) HEAs; however, bcc HEAs can offer a larger elastic modulus and plastic yielding, thus, becoming possible candidates for the next generation of refractory materials. In this work, we focus on molecular dynamics (MD) simulations of bcc HfNbTaZr nanocrystalline samples, with a grain size (d) between 5 and 17 nm, deformed under tension at 300 K. The elastic modulus increases with the grain size and reaches a plateau near 10 nm. We find the typical inverse Hall–Petch (HP) behavior with yield strength, ultimate tensile stress (UTS), and flow stress increasing with d. Up to 12 nm, there are contributions from dislocations and twins; however, grain boundary (GB) activity dominates deformation. For the 5 nm grains, the GB disorder extends and leads to extensive amorphization and grain size reduction. For $d>10$ nm, there is a HP-type behavior with dislocations and twinning controlling deformation. For this regime, there is hardening at large strains. Compared to bcc single metal samples, the HP maximum of this HEA appears at a lower grain size, and this could be related to the chemical complexity facilitating dislocation nucleation. We use machine learning to help understand deformation regimes. We also compare our results to a single crystal (SC) HfNbTaZr HEA deformed along [001] and find that the single crystal is weaker than the nanocrystalline samples. The single crystal deforms initially by twinning and then rapidly by dislocation multiplication, leading to strong hardening. It has been proposed that edge dislocations play a major role in bcc HEA plasticity, and we also analyze the relative contributions of edge versus screw dislocations during deformation for both single crystal and nanocrystalline samples.

Morphological characterization and fluid dynamics simulations were carried out to classify the rupture status of 71 (36 unruptured, 35 ruptured) patient specific cerebral aneurysms using a machine learning approach together with statistical techniques. Eleven morphological and six hemodynamic parameters were evaluated individually and collectively for significance as rupture status predictors. The performance of each parameter was inspected using hypothesis testing, accuracy, confusion matrix, and the area under the receiver operating characteristic curve. Overall, the size ratio exhibited the best performance, followed by the diastolic wall shear stress, and systolic wall shear stress. The prediction capability of all 17 parameters together was evaluated using eight different machine learning algorithms. The logistic regression achieved the highest accuracy (0.75), whereas the random forest had the highest area under curve value among all the classifiers (0.82), surpassing the performance exhibited by the size ratio. Hence, we propose the random forest model as a tool that can help improve the rupture status prediction of cerebral aneurysms.