The oxidative dehydrogenation (ODH) of butene has been recently developed as a viable alternative for the synthesis of 1, 3-butadiene due to its advantages over other conventional methods. Since the process is highly exothermic, it is crucial to control the temperature to enhance the reactor performance. Hence, in this study, a multi-tubular reactor model for the butadiene synthesis via ODH of butene was developed using computational fluid dynamics (CFD). For this, the 3D multi-tubular model which combines complex reaction kinetics with a shell-side coolant fluid over a series of individual reactor tubes was generated using OpenFOAM®. Then, the developed model was validated and analyzed with the experimental results. Additionally, parametric studies were conducted to evaluate the effect of thermodynamic conditions (isothermal, non-isothermal and adiabatic), feed temperature and gas velocity on reactor performance. Moreover, the investigation of 12 different molten salts was carried out to provide the right decision basis for selecting suitable salts for both cooling and thermal storage applications. Parametric studies involving the different salts indicated that low melting point salts resulted in high heat removal efficiencies but reduced the overall conversion, yield, and selectivity of the reactor due to the lower reaction temperatures. Thermophysical properties such as specific heat capacities were found to have no significant impact on the cooling efficiency of the reactor. An economic evaluation of the salts based on their heating costs indicated that salts of LiNaKCsCaNO₃ and NaKCaNO₃ are most suitable, especially for thermal storage systems where only latent heat of fusion is required. However, in cases where further heating of the salt is needed, higher melting point salts (such as solar salt) proved to be much more economical. Investigation of the effect of different tube diameters on the cooling performance of the reactor indicated that reactors having a diameter to length ratio between 32 to 58 provide sufficient cooling and high conversion. Lastly, a software platform is presented to aid in the training and development of neural networks by using genetic algorithms for optimizing the hyperparameters, such as the number of neurons, learning rate, and activation function. The software platform can also plot 3D contours, heat maps (correlation plots), and other line graphs. For the validation and generalization of the software, it was benchmarked against five cases presented by different authors across various chemical engineering fields. The prediction results obtained using the software package were higher than those presented in the published literature, demonstrating the optimal performance of the software package.