The work presented in this paper reports a versatile and customizable watershed-based pore network extraction tool. It was used to build pore networks from microscale computed tomography images of highly porous carbon-fiber materials. The extracted networks were used to characterize the structural properties (pore and throat diameter, and porosity distributions) and to predict the dry, in-plane, effective diffusivities of two commercial gas diffusion layers under various levels of compression. The relationship between compression and effective diffusivity was used to accurately predict experimental values available in the literature to within 10% of the reported values for compressive strains less than 0.55. Through this work, we validate the accuracy of watershed-derived pore networks for predicting in-plane effective diffusivities, further establishing the reliability of watershed-derived pore network modeling for fuel cell applications. (c) The Author(s) 2019. Published by ECS. This is an open access article distributed under the terms of the Creative Commons Attribution Non-Commercial No Derivatives 4.0 License (CC BY-NC-ND, http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial reuse, distribution, and reproduction in any medium, provided the original work is not changed in any way and is properly cited. For permission for commercial reuse, please email: [email protected].