All-Solid-State Battery (ASSB), which is nonflammable, safe, and high capacity, is expected to be commercialized for electric vehicle applications in the near future. However, the correlation between the electrode structure and the stress on the solid-solid contact surface is unknown, and no design theory has been established. However, the design theory has not been established because the correlation between the stresses on the electrode structure and the solid-solid contact surface is unknown. In this study, a stress distribution estimation method for complex electrode structures using machine learning was investigated.The stress estimation was performed using the discrete element method (DEM)¹⁾ . The average particle size of LCO was given as 9-12 ㎛, standard deviation as 0-2, and Young's modulus was given as 264 GPa²⁾. The LGPS particles were fixed at 1 ㎛ in diameter, with Young's modulus of 26.7 GPa, Poisson's ratio of 0.32, and density of 1.988 g/cm³. The distribution of the stresses on each particle was calculated from the DEM calculation results and confirmed to be approximately Gaussian.A convolutional neural network (CNN)³⁾ was used as the model for machine learning, and various structural parameters, including the stress on each particle calculated by DEM, were identified to create a dataset. Five hundred images were used for training, 320 of which were used for training, 80 for validation, and 100 for testing. The coefficient of determination (R²) of the standard deviation of the stress on each particle was AM_0.861, SE_0.936, and SE_0.936, confirming that the stress distribution can be predicted by the machine learning model. The contact area of the electrochemical reaction interface, AM-SE, was calculated from the stress on the contact surface calculated by DEM and Hertzian contact theory⁴⁾. The total interfacial area was also predicted well with a coefficient of determination of 0.921.Thus, it was possible to predict the stress distribution and effective contact area in the electrode layer of the all-solid-state battery. Next, we will verify the validity of the electrode structure and stress distribution by simultaneously measuring the in-situ stress distribution and Li concentration distribution during charging and discharging using X-ray spectroscopy and atomic force microscopy. In addition, a machine learning model of crack formation during charging and discharging will be developed. By linking machine learning and measurement, we will connect to the structural design of electrode layers to improve charge-discharge and cycle characteristics, and aim to establish fundamental technology that will contribute to the early commercialization of all-solid-state batteries.