In-situ TEM investigation of void swelling in nickel under irradiation with analysis aided by computer vision

Understanding the stability of irradiation-induced voids in materials is important for engineering material's swelling behavior under irradiation. In-situ TEM offers a spatial and temporal resolution that is suitable for investigating the evolution of voids under irradiation. However, the in-situ videos have often been too large to be analyzed manually, leaving the valuable data underutilized. We developed a deep learning-based semantic segmentation model to consistently study the growth and shrinkage of voids in nickel under 1 MeV krypton ion irradiation at various temperatures from 525 degrees C to 650 degrees C. With a foil thickness near 100 nm and ion flux of 6.3 x 10(11) ions center dot cm(-2)center dot s(-1), the pre-existing voids, which were created beforehand by irradiation at 600 degrees C to 0.5 dpa, shrank at low temperatures and grew at high temperatures under irradiation, where the transition occurred at 575 degrees C (similar to 0.5 TM). The observed stability transition provided new insight for the shrinkage mechanism of voids under irradiation. In addition, an annealing experiment on nickel, previously irradiated at 600 degrees C to 3 dpa, was performed sequentially at 650 degrees C to 720 degrees C to reveal the shrinkage rate of void as a function of temperature and void size. The advantage of combining computer vision and in-situ TEM to obtain comprehensive void evolution was demonstrated.