Data-driven methods have been a subject of interest in several fields within science and engineering. The development of Neural Operators [1] has increased the attention of surrogate modeling in Computational Science and Engineering applications as a potential replacement for the expensive numerical simulations based on the approximation and discretization of partial differential equations (PDEs). Neural Operators aim to learn the solution operator from PDEs instead of fitting it into a specific case. It has been shown that Fourier Neural Operators (FNOs) perform well in many porous media applications, particularly carbon sequestration and storage [2]. Nonetheless, FNOs have a substantial memory and computational overhead given the structure required for efficient spectral convolutions in the Fourier layers, making FNOs generally infeasible for large 4D Porous Media applications. In this study, we perform numerical assessments of FNO variants that are tailored to reduce the number of parameters of the model and increase efficiency in both runtime and spatial complexities. We assess the accuracy and performance of the Factorized FNO (F-FNO), Tensorized FNO (TFNO), and U-shaped Neural Operator (UNO) variants in the Tenth SPE Comparative Solution Project [3], which consists of a 3D spatial domain transient three-phase flow in porous media application. To generate the data for FNO ingestion, we use OPM Flow [4], an open-source solver of black-oil equations. Of particular importance in the present work is the development of a modern, high-performance pipeline tailored for large, three-dimensional black-oil problems using advanced machine learning software engineering techniques. [1] Li, Z., Kovachki, N., Azizzadenesheli, K., Liu, B., Bhattacharya, K., Stuart, A. and Anandkumar, A. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895, 2020. [2] Wen G., Hay C., Benson S. M. CCSNet: a deep learning modeling suite for CO2 storage, Advances in Water Resources, 155:104009, 2021. [3] Christie, M. A., and Blunt, M. J. Tenth SPE Comparative Solution Project: A Comparison of Upscaling Techniques. SPE Reservoir Evaluation & Engineering 4(04): 308–317, 2001. [4] Rasmussen A.T., Sandve T. H., Bao K., Lauser A., Hove J., Skaflestad B., Klöfkorn R., Rustad A. B., Sævareid O., Lie K.-A., Thune A. The Open Porous Media Flow reservoir simulator, Computers & Mathematics with Applications, 81: 159-185, 2021.