The paper Heterogeneous peridynamic neural operators: Discover biotissue constitutive law and microstructure from digital image correlation measurements introduces the Heterogeneous Peridynamic Neural Operator (HeteroPNO) approach for data-driven constitutive modeling of heterogeneous anisotropic materials based on digital image correlation (DIC) data. The two-phase learning approach utilizes an nonlocal constitutive law and spatially varying fiber orientation fields through a two-phase neural network training process, ensuring accurate and interpretable predictions of tissue behavior under various loading conditions.