“…Due to its excellent abilities such as handling data with high dimensionality, the approximation for arbitrary nonlinear functions, and computational efficiency, the artificial neural network (ANN) system has successfully provided a good representation in biological, chemical, and physical phenomena. [24][25][26] Recently, the advanced system that aims to balance the compromise between the accuracy of models and cost-effectiveness of collecting limited numbers of experimental conditions, of which combines both advantages of ANNs and the response surface methodology (RSM), has been reported. [27][28][29] Although many works have been done using the RSM as a tool for the optimization of hydrogen dark fermentation, 30,31 the employment of the hybrid ANNs-RSM system and its application in the investigation of the effect of critical operational conditions, ie, BC, metal cofactor Ni 0 , pH, and dosage of microbes upon hydrogen production, to the best of our knowledge, have never been reported before.…”