Multi-output lstm improves industrial biogas process monitoring and stability prediction
Multi-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation
Machine LearningArtificial Intelligence
Summary
Anaerobic digestion is a method to produce biogas but requires careful monitoring to avoid failures. The authors show that usual methods miss important warnings because the data is limited and focused on normal operation. They created a new approach that generates realistic data for unstable conditions and uses a special multi-output neural network to predict multiple important indicators at once. This helps detect problems early and could improve industrial biogas plants' reliability.
What this means in practice
- •For industrial bioprocess operators: Enable early detection of instability in anaerobic digestion plants by predicting multiple process indicators simultaneously.
- •For environmental engineers: Use augmented data and multi-output models to improve monitoring of organic waste digestion processes with sparse field data.
Authors
Rohit Murali, Benaissa Dekhici, Tao Chen, Dongda Zhang, Michael Short
Abstract
Anaerobic digestion (AD) requires close monitoring of key process variables, including pH, the ratio of volatile organic acids to alkaline buffer capacity and biogas production, to maintain biological stability and prevent process failure. While mechanistic frameworks such as the Anaerobic Digestion Model No. 1 are highly parameterised, computationally expensive, and difficult to calibrate for real-time applications, data-driven Long Short-Term Memory (LSTM) networks offer a potentially more adaptable alternative. However, current data-driven approaches in AD are predominantly limited to single-output architectures that focus solely on production yields, as opposed to simultaneous prediction of vital stability indicators. Furthermore, industrial AD datasets are typically sparse and skewed toward steady-state operations. Baseline evaluations demonstrated this scarcity prevents standard algorithms (Random Forest, XGBoost) and unaugmented LSTMs from recognising the transition to unstable operations, resulting in poor estimation of stability indicators. To overcome these challenges, this study proposes a novel generative data augmentation framework using an LSTM-beta-Variational Autoencoder coupled with a multi-output LSTM (MO-LSTM) soft sensor. By synthesising physically valid sequences of these transitions to unstable operations from one year of full-scale plant data, the method safely populates sparse regions of the feature space. Trained on this augmented dataset, the MO-LSTM achieved robust simultaneous estimation across all targets. This approach mitigates data sparsity, providing a basis for hybrid mechanistic-data-driven modelling and early-warning soft sensors in industrial bioprocesses.