The depletion of fossil fuel sources and increase in energy demands have increased the need for a sustainable alternative energy source. The ability to produce hydrogen from microalgae is generating a lot of attention in both academia and industry. Due to complex production procedures, the commercial production of microalgal biohydrogen is not yet practical. Developing the most optimum microalgal hydrogen production process is also very laborious and expensive as proven from the experimental measurement. Therefore, this research project intended to analyse the random time series dataset collected during microalgal hydrogen productions while using various low thermally pre-treated palm kernel expeller (PKE) waste via machine learning (ML) approach. The analysis of collected dataset allowed the derivation of an enhanced kinetic model based on the Gompertz model amidst the dark fermentative hydrogen production that integrated thermal pre-treatment duration as a function within the model. The optimum microalgal hydrogen production attained with the enhanced kinetic model was 387.1 mL/g microalgae after 6 days with 1 h thermally pre-treated PKE waste at 90 °C. The enhanced model also had better accuracy (R2 = 0.9556) and net energy ratio (NER) value (0.71) than previous studies. Finally, the NER could be further improved to 0.91 when the microalgal culture was reused, heralding the potential application of ML in optimizing the microalgal hydrogen production process.
Municipal wastewater is ubiquitously laden with myriad pollutants discharged primarily from a combination of domestic and industrial activities. These heterogeneous pollutants are threating the natural environments when the traditional activated sludge system fails sporadically to reduce the pollutants' toxicities. Besides, the activated sludge system is very energy intensive, bringing conundrums for decarbonization. This research endeavoured to employ Chlorella vulgaris sp. In converting pollutants from municipal wastewater into hydrogen via alternate light and dark fermentative process. The microalgae in attached form onto 1 cm3 of polyurethane foam cubes were adopted in optimizing light intensity and photoperiod during the light exposure duration. The highest hydrogen production was recorded at 52 mL amidst the synergistic light intensity and photoperiod of 200 μmolm-2s-1 and 12:12 h (light:dark h), respectively. At this lighting condition, the removals of chemical oxygen demand (COD) and ammoniacal nitrogen were both achieved at about 80%. The sustainability of microalgal fermentative performances was verified in recyclability study using similar immobilization support material. There were negligible diminishments of hydrogen production as well as both COD and ammoniacal nitrogen removals after five cycles, heralding inconsequential microalgal cells' washout from the polyurethane support when replacing the municipal wastewater medium at each cycle. The collected dataset was finally modelled into enhanced Monod equation aided by Python software tool of machine learning. The derived model was capable to predict the performances of microalgae to execute the fermentative process in producing hydrogen while subsisting municipal wastewater at arbitrary photoperiod. The enhanced model had a best fitting of R2 of 0.9857 as validated using an independent dataset. Concisely, the outcomes had contributed towards the advancement of municipal wastewater treatment via microalgal fermentative process in producing green hydrogen as a clean energy source to decarbonize the wastewater treatment facilities.