Biogas production plays a key role in the development of renewable energy systems; however, forecasting biomethane yield remains challenging due to the nonlinear nature of anaerobic digestion. The objective of this study was to develop a predictive model based on Radial Basis Function Neural Networks (RBF-NN) to approximate biomethane production using operational data from the Przybroda biogas plant in Poland. Two separate models were constructed: (1) the relationship between process temperature and daily methane production, and (2) the relationship between methane fraction and total biogas flow. Both models were trained using Gaussian activation functions, individually adjusted neuron parameters, and a zero-level correction algorithm. The developed RBF-NN models demonstrated high approximation accuracy. For the temperature-based model, root mean square error (RMSE) decreased from 531 m3 CH4·day−1 to 52 m3 CH4·day−1, while for the methane-fraction model, RMSE decreased from 244 m3 CH4·day−1 to 27 m3 CH4·day−1. The determination coefficients reached R2 = 0.99 for both models. These results confirm that RBF-NN provides an effective and flexible tool for modeling complex nonlinear dependencies in anaerobic digestion, even when only limited datasets are available, and can support real-time monitoring and optimization in biogas plant operations.
With growing global demand for renewable energy and the need for efficient use of organic waste, agricultural waste (including animal excrement and plant residues) is considered a key and promising feedstock for biogas production via anaerobic digestion. Despite the environmental and energy benefits of this approach, significant variability in the chemical composition and quality of the feedstock poses a serious obstacle to ensuring consistently high methane yields. This review systematizes and evaluates modern approaches aimed at overcoming this variability. Particular attention is paid to the integration of machine learning methods, particularly artificial neural networks. These methods demonstrate high accuracy in modeling and predicting methanogenesis efficiency based on analysis of input biomass characteristics. Furthermore, the review critically evaluates the role of intelligent control and automation systems using hybrid algorithms for adaptive adjustment of process parameters (carbon-to-nitrogen ratio, temperature, pH) in real time. The implementation of these intelligent technologies is key to process optimization, increased reliability, and the economic competitiveness of the biogas industry.