A Review Unveiling Various Machine Learning Algorithms Adopted for Biohydrogen Productions from Microalgae

Abstract

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.

Challenges and Future Perspectives on Production, Storage Technologies, and Transportation of Hydrogen: A Review

“…[10,11] To address today's energy market needs for sustainability in industry and transportation, "Green Hydrogen" produced from renewables plays a pivotal role in decarbonization. [12][13][14] In addition to these developments in industry, there are also various lab-based efforts worldwide including, plasmolysis of water/water vapors, reforming of alcohols, biohydrogen (based on microalgae), or chemical cycles [15][16][17][18][19][20] There is no doubt that hydrogen is one of the key tools in energy transition, and it has a very significant effect on CO 2 emission reductions (6%) according to NZE Scenario. IEA reported in the Global Hydrogen Review that ≈90 Mt H 2 was produced worldwide in 2020, where 80% of this amount was produced from fossil resources.…”

“…In addition to these developments in industry, there are also various lab‐based efforts worldwide including, plasmolysis of water/water vapors, reforming of alcohols, biohydrogen (based on microalgae), or chemical cycles [ 15–20 ]…”

Fungal systems for lignocellulose deconstruction: From enzymatic mechanisms to hydrolysis optimization

“…Once adequately trained, these AI systems can propose novel, high‐performing cocktails for untested biomass materials based solely on rapid compositional characterization. Machine learning algorithms, such as ANN, random forests, and support vector machines, can construct nonlinear multivariate models correlating the structural composition of various biomasses to the performance of different enzyme combinations (Ahmad Sobri et al., 2023; Yang et al., 2022). By training these models on datasets that encompass characterized biomass samples and their corresponding hydrolysis efficacies for specific enzyme cocktails, the algorithms can learn complex mapping functions that relate input variables, such as cellulose, hemicellulose, and lignin content, to the desired output of enzymatic hydrolysis yield (Haldar et al., 2023).…”

Enhancing Biohydrogen Production: The Role of Iron-Based Nanoparticles in Continuous Lactate-Driven Dark Fermentation of Powdered Cheese Whey

“…In this context, biohydrogen (bioH 2 ) is emerging as a promising and environmentally friendly renewable fuel alternative [1]. Defined as H 2 biologically produced from microbial metabolism using renewable organic substrates [2], bioH 2 can potentially be obtained via dark fermentation (DF) due to its high H 2 productivity, versatility, and high kinetic growth rates [3]. DF is currently regarded as one of the most promising biotechnological platforms for the development of organic-waste-based biorefineries, with the potential to convert a wide range of organic substrates, mainly from renewable sources (e.g., food waste, lignocellulosic and algal biomass, municipal organic waste, and industrial/agricultural wastewater [4]) into bioH 2 and high-value organic acids.…”