Biohydrogen production from microalgae is a potential alternative energy source that is now intensively being researched. The complex natures of the biological processes involved have afflicted the accuracy of traditional modelling and optimization, besides being costly. Accordingly, machine learning algorithms have been employed to overcome setbacks, as these approaches have the capability to predict nonlinear interactions and handle multivariate data from microalgal biohydrogen studies. Thus, the review focuses on revealing the recent applications of machine learning techniques in microalgal biohydrogen production. The working principles of random forests, artificial neural networks, support vector machines, and regression algorithms are covered. The applications of these techniques are analyzed and compared for their effectiveness, advantages and disadvantages in the relationship studies, classification of results, and prediction of microalgal hydrogen production. These techniques have shown great performance despite limited data sets that are complex and nonlinear. However, the current techniques are still susceptible to overfitting, which could potentially reduce prediction performance. These could be potentially resolved or mitigated by comparing the methods, should the input data be limited.

The valorization of chicken manure via pyrolysis can give biowaste a second life to generate value and contribute to the circular economy. In the present study, the thermal degradation and pyrolysis characteristics of chicken manure pyrolysis were investigated via thermogravimetric analyses (TGA) coupled with optimization methods. Thermogravimetric data were obtained for the samples at five heating rates of 5, 10, 20, 30 and 50 °C/min over a range of temperature under inert conditions. The manure devolatilization process was initiated at between 328 and 367 °C to overcome the global activation energy barrier. The determined activation energy of the manure via Flynn–Wall–Ozawa (FWO), Kissinger–Akahira–Sunose (KAS), Friedman and Kissinger methods was in the range of 167.5–213.9 kJ/mol. By using the particle swarm optimization (PSO) method, the pyrolytic kinetic parameters of the individual component present in the manure were calculated, in which the activation energy for cellulose (227.8 kJ/mol) was found to be higher than that of hemicellulose (119 kJ/mol) and lignin (134.3 kJ/mol). Based on intrinsic transition-state theory, the pre-exponential factor and activation energy of the manure can be correlated through a linear equation ln A_α = 0.2006 E_α − 1.2847. The devolatilization characteristics of the chicken manure were elucidated via the optimization process, paving the way for the design of thermochemical conversion reactors and processes.