in the form of a metal hydride has come forth as a safe and low-pressure storage solution with competitive volumetric energy density. In this technology, hydrogen is stored in a hydride-forming metal, in this study specifically AB5-type metal hydride, through exothermic absorption, which can then be discharged through endothermic desorption. This results in a complex batch system where hydrogen discharge is caused by high-temperature fluid heating the reactor and by extension the metal hydride bed. This in turn increases the hydrogen pressure of the gas surrounding the metal hydride bed which then is released through a regulator to achieve the desired pressure of the discharge hydrogen. This discharge dynamic system as a result is notoriously hard to model and predict. This paper reports the modelling of a metal hydride reactor during its discharge state using neural network regression. This was done by generating a validated finite element model of the reactor which was then used to generate dynamic operational data based on the desired pressure outlet and heating fluid temperature as independent variables. This data was then used to train an artificial neural network using the desired gas pressure, heating fluid temperature, and time as inputs and concentration as the variables the neural network would predict. Regarding model performance, the best-performing artificial neural network model achieved a regression coefficient of 0.9999 and a mean squared error of less than 10^-5 during training. Likewise, the best-performing neural network model validation using the experimentally observed data achieved a regression coefficient of 0.99 and a mean squared error of less than 10^-4. This proves that neural networks can model the complexity of metal hydride reactors during discharge, specifically the HySA-systems Metal Hydride reactor prototype.