WASE: Using data and AI to make biological waste-to-energy systems more resilient and efficient

This case study explores how WASE, a waste-to-energy technology company, is applying data infrastructure and machine learning techniques to improve the operation of biogas production systems. By combining scientific expertise with better data and AI practices, WASE helps hardware operators detect problems earlier and optimise the performance and resilience of their systems – with the ultimate aim of moving towards greater levels of human-augmented automation. Participation in The Alan Turing Institute’s Turing Way Practitioners Hub has supported this work by strengthening WASE’s approach to aspects including data handling, operational reproducibility, and responsible innovation in this complex, real-world industrial context. This case study is published under The Turing Way Practitioners Hub 2025-26 Cohort - case study series. The Practitioners Hub is The Turing Way project that works with experts from partnering organisations to promote data science best practices. Key takeaways High-resolution data infrastructure is as critical as physical hardware for system resilience; by centralising disparate streams into a "single source of truth," WASE transforms legacy anaerobic digestion into a digitally-optimised biological engine. Machine learning models can use historical data combined with real-time information gathered by biological soft sensors to provide beneficial system insights – replacing slow laboratory measurements and enabling earlier intervention. By implementing human-in-the-loop design, WASE provides a transparent roadmap towards human-augmented automation, empowering operators to manage biological volatility with greater precision and confidence. Incremental deployment and transparency help reduce risk and build trust with operators in a traditional sector – particularly as systems move towards increased automation. Participation in The Turing Way Practitioners Hub has supported the institutionalisation of responsible innovation and rigorous data handling, ensuring all AI developments are built upon a foundation of industrial-grade reliability.