EnviroPiNet: A Physics-Guided AI Model for Predicting Biofilter Performance
This work addresses the problem of modeling complex environmental systems with sparse, high-dimensional data for researchers and engineers in environmental biotechnology, representing a novel application rather than an incremental improvement.
The study tackled the challenge of predicting biofilter performance in environmental biotechnologies by applying Buckingham Pi theory for dimensionality reduction and developing the EnviroPiNet model, which achieved an R^2 of 0.9236 on testing data, outperforming traditional methods like PCA and autoencoders.
Environmental biotechnologies, such as drinking water biofilters, rely on complex interactions between microbial communities and their surrounding physical-chemical environments. Predicting the performance of these systems is challenging due to high-dimensional, sparse datasets that lack diversity and fail to fully capture system behaviour. Accurate predictive models require innovative, science-guided approaches. In this study, we present the first application of Buckingham Pi theory to modelling biofilter performance. This dimensionality reduction technique identifies meaningful, dimensionless variables that enhance predictive accuracy and improve model interpretability. Using these variables, we developed the Environmental Buckingham Pi Neural Network (EnviroPiNet), a physics-guided model benchmarked against traditional data-driven methods, including Principal Component Analysis (PCA) and autoencoder neural networks. Our findings demonstrate that the EnviroPiNet model achieves an R^2 value of 0.9236 on the testing dataset, significantly outperforming PCA and autoencoder methods. The Buckingham Pi variables also provide insights into the physical and chemical relationships governing biofilter behaviour, with implications for system design and optimization. This study highlights the potential of combining physical principles with AI approaches to model complex environmental systems characterized by sparse, high-dimensional datasets.