The shift towards sustainable energy solutions is driving the adoption of fuel cells, particularly Proton Exchange Membrane Fuel Cells (PEMFCs), in transportation and power generation. These PEMFCs are favored for their high-power density, quick startup, low operational temperatures, and compact design. Academic research has explored different modeling approaches for fuel cells, with a focus on accurate parameter estimation to enhance system design and performance. Various optimization-based methodologies, including evolutionary algorithms and nature-inspired optimizers, have been developed to estimate optimal parameters for PEMFCs. These methods aim to minimize the differences between experimental and calculated voltages, improving the overall efficiency of fuel cell systems. Researchers have utilized a range of optimization techniques such as multiverse optimizer, sparrow search algorithm, Harris hawk optimizer, and monarch butterfly optimizer to determine the optimal parameters for PEMFCs. The objective is to reduce the sum squared error (SSE) between experimental and predicted voltages, enhancing the accuracy of the models. Additionally, approaches like the Bayesian-regularized neural network and sunflower optimizer have been employed to estimate unknown parameters in PEMFCs. The continuous advancements in parameter estimation methodologies for PEMFCs indicate a positive trend towards optimizing fuel cell technology for practical applications, contributing to the sustainable energy transition.