Integration of Anaerobic Digestion with Heat Pump - Machine learning-based technical and environmental assessment

Aug 5, 2026

Upload by Jiven

Anaerobic digestion (AD)-based biogas production reduces the environmental footprint of organic wastes while supporting a circular economy. The study proposes an integrated system that supplies AD thermal energy using an air source heat pump (ASHP), compared against a baseline heated by natural gas. Multiple machine learning models predict biogas output, with Gaussian Process Regression delivering the best accuracy (R2 = 0.84, RMSE = 0.0755 L gVS−1 day−1). The GPR-informed thermodynamic model indicates an optimal thermophilic temperature around 55 °C.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Highlights

Integration and prediction objectives

Operational parameter effects

Life cycle assessment outcome

Article

Introduction

Impact of feedstock and process parameters

Bioresource Technology 369 (2023) 128485 Contents lists available at ScienceDirect Bioresource Technology journal [homepage:](homepage: www.elsevier.com/locate/biortech)[ www.elsevier.com/locate/biortech](homepage: www.elsevier.com/locate/biortech) | Integration of anaerobic digestion with heat Pump: Machine learning-based technical and environmental assessment
Zahra Hajabdollahi Ouderjia, 1, Rohit Gupta a, b, c, 1, Andrew Mckeown a, Zhibin Yu a, Cindy Smith a, William Sloan a, Siming You a, *
a James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK
b Nanoengineered Systems Laboratory, UCL Mechanical Engineering, University College London, London WC1E 7JE, UK c Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London W1W 7TS, UK | | | --- | --- | | H I G H L I G H T S
• Integration of air source heat pump with anaerobic digestion.
• Applying machine learning models to predict biogas and methane yield.
• Exploring the effects of heat pump operational parameters on biogas yield.
• Life cycle assessment application to investigate the environmental impacts.
• Proposed solution mitigates global warming potential significantly.
A R T I C L E I N F O
Keywords: Net-zero Bioenergy
Data-driven models
Life cycle assessment
Waste management | G R A P H I C A L A B S T R A C T
A B S T R A C T
Anaerobic digestion (AD)-based biogas production mitigates the environmental footprint of organic wastes (e.g., food waste and sewage sludge) and facilitates a circular economy. The work proposed an integrated system where the thermal energy demand of an AD is supplied using an air source heat pump (ASHP). The proposed system is compared to a baseline system, where the thermal energy is supplied by a natural gas-based heating system. Several machine learning models are developed for predicting biogas production, among which the Gaussian Process Regression (GPR) showed a superior performance (R2 = 0.84 and RMSE = 0.0755 L gVS − 1 day − 1). The GPR model further informed a thermodynamic model of the ASHP, which revealed the maximum biogas yield to be approximately 0.585 L.gVS− [1](1.day)[.day](1.day)− 1 at an optimal temperature of 55 ◦ C (thermophilic). Subsequently, life cycle assessment showed that ASHP-based AD heating systems achieved 28.1 %(thermophilic) and 36.8 %(mesophilic) carbon abatement than the baseline system. | 1. Introduction Over the past decades, anaerobic digestion (AD) has proven to be an effective way of reducing the volume of organic waste significantly, while recovering value-added products such as biogas and digestate. The performance of an AD process is strongly influenced by the choice of * Corresponding author. E-mail address: [siming.you@glasgow.ac.uk](siming.you@glasgow.ac.uk) (S. You). 1 The authors contribute equally. [https://doi.org/10.1016/j.biortech.2022.128485](https://doi.org/10.1016/j.biortech.2022.128485) Received 30 October 2022; Received in revised form 9 December 2022; Accepted 11 December 2022 Available online 12 December 2022 0960-8524/© 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license ([http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/)). Z. Hajabdollahi Ouderji et al. Bioresource Technology 369 (2023) 128485 Fig. 1. Integration of the thermal systems with AD-CHP in for the baseline and alternative scenarios. The baseline scenario corresponds to a natural gas-based AD heating system, while the alternative scenario uses an ASHP-based heating system. Abbreviations – El: Electricity, D: Diesel, Ch: Chemicals, Em: Emissions. The grey shaded regions indicate processes that are included within the system boundary. input waste which varies from vegetable and animal waste, agricultural waste to industrial and municipal solid waste, etc. Using multiple waste streams as a feedstock (co-di

FAQs

What integrated system is proposed in the study?

The study integrates an air source heat pump to supply thermal energy demand for an anaerobic digestion process producing biogas.

Which machine learning model performed best for predicting biogas yield?

Gaussian Process Regression (GPR) showed superior performance with R2 = 0.84 and RMSE = 0.0755 L gVS−1 day−1.

How did the ASHP-based heating system compare environmentally with the natural gas baseline?

Life cycle assessment indicates ASHP-based AD heating systems achieved carbon abatement of 28.1% under thermophilic conditions and 36.8% under mesophilic conditions versus the baseline.

Aug 5, 2026

Upload by Jiven