1 June 2025 in Environmental Research Communications
Biogas production through anaerobic digestion (AD) of industrial organic waste and wastewater offers a sustainable method for energy recovery. However, since process efficiency heavily relies on operational factors, continuous monitoring of the AD process and the implementation of necessary operational strategies are crucial. In recent years, the use of machine learning techniques (ML) has become widespread for analysing the effects of operational factors on anaerobic digestion efficiency. Among these, Support Vector Regression (SVR) with a Radial Basis Function (RBF) kernel has been used to predict biogas yield based on diverse operating parameters. This study aimed to investigate the predictability of changes in biogas production using the SVR algorithm with an RBF kernel in a full-scale anaerobic digester treating wastewater from a fruit processing plant. In the model, biogas production was estimated based on variations in selected operational parameters, achieving a regression coefficient (R2) of 0.8983 ± 0.03 with mean square error (MSE) of 0.0047 ± 0.0017. The model’s performance was evaluated using 10-fold cross-validation techniques and relevant statistical indicators to ensure robustness and generalisability. Hyperparameter tuning was conducted to enhance prediction accuracy while reducing model error. The findings demonstrated that ML-based modelling can serve as a reliable and effective tool to improve biogas production efficiency in wastewater treatment applications. Furthermore, the study highlights the potential of such models to support real-time process control and decision making in anaerobic digestion systems operating under variable industrial conditions.
3 November 2026 in Physica Scripta
Magnetic field modeling is essential for a wide range of applications, from electromagnetic device design to the analysis of geomagnetic and material-based systems. This study proposes two distinct neural network frameworks based on physics-informed radial basis function neural networks (PI-RBFNNs) to solve Maxwell’s equations on four different domains. The proposed unified and domain-specific network architectures use region-aware radial basis function kernels and are initialized by collocation governing equations in boundary and jump conditions. The models capture magnetic field behavior in both homogeneous and heterogeneous regions, with the level of agreement depending on the problem complexity and network architecture. All models are implemented using the TensorFlow framework, which enables efficient automatic differentiation and scalable optimization. Unlike conventional mesh-based numerical methods, the proposed PI-RBFNN framework provides a mesh-free formulation for magnetostatic field modeling. To evaluate the effectiveness of the models, results obtained from both configurations are compared with benchmark data from the literature and solutions generated by the finite difference method (FDM). The results show good agreement for simpler configurations, while discrepancies increase for more heterogeneous problems. For intermediate cases, the domain-specific architecture reduces the relative error with respect to FDM compared with the unified architecture. These findings demonstrate the potential of PI-RBFNN architectures for mesh-free modeling of magnetostatic field problems involving heterogeneous material regions and interface conditions, while further validation against independently converged reference solutions is required for broader assessment of their accuracy.