The Microbial desalination cell (MDC) is an environmentally friendly water purification technology that uses organic contaminants in wastewater as an energy source to power the desalination process. The Microbial Desalination and Chemicals Production Cell (MDCC) is a modified version of the Microbial Desalination Cell (MDC) that desalinates salt water, generates electricity, and produces acid and base simultaneously. However, electrolysis system technology optimization depends heavily on laboratory experiments. Mathematical modeling has been proposed as a viable replacement to laboratory experimentation due to their high costs and long timeframes. Modeling MDCs using artificial intelegence is a potential way for addressing these obstacles. On this research, the influence of different electrolyte to salt ratios in the innovative two-chamber design of MDC was analyzed, along with modeling desalination performance using Support Vector Regression (SVR) and Multilayer Perceptron (MLP) for the first time and validating experimental results. In addition, acid and base recovery was examined utilizing a seven chambers microbia; desalnation cell and chemical production cell (7C-MDCC) with three external resistances (1, 10, and 1000 ). Due to the dominating concentration gradient, the findings indicated that the desalination rate of two chambers microbial desalnation cell (TC-MDC) might fall in the rapid desalination zone over a long range of desalination cycles (> 93%) at a high E/S ratio. In addition, the suggested SVR and MLP models could estimate the desalination performance utilizing the voltage, pH of effluent, electrolyte volume, and salt concentration of effluent as input variables. The SVR was able to predict desalination performance with the highest degree of accuracy among the two investigated models. Additionally, results showed that the pH of HCl and NaOH while using 1 were reached almost 2.033 and 12.1 respectively. Considering the volume of the acid and cathode production chambers (2L each), results showed that the HCl and NaOH productions at the end of the cycle were 27.06 mg and 31.24 mg, respectively while using 1. Further results of 10  resistance II showed that the production concentration was 2.92 mg of HCl and 1.45 mg of NaOH. Additionally, results analysis of 1K set out that in the acid-base production concentration was 0.25 mg HCl and 10.77 mg of NaOH. More than 55% desalination rate was reached during the operation of all three resistances. This research showed the potential of applying renewable and sustainable energy sources to understand the desalination behavior of the newly developed TC-MDC at different electrolyte-to-salt ratios and to produce acids and bases using 7C-MDCC. Further, the prospect of adopting AI to predict desalination performance. More study on optimization of various design parameter for efficient acid base recovery needs to be done also, more study should be done on reduction of internal resistance by optimizing the parameters. In addition, application of AI in MDC process is still in juvenile phase, so more focus on AI integration is needed.