Deep Transfer Learning for Predicting Microbial Attachment in Microbial Fuel Cells to Enhance Bioenergy Recovery
Chalak Qazani, Mohammad Reza, Ghasemi, Mostafa, Seavers, Michael, Ali Khan, Murtaza, and Asadi, Houshyar (2026) Deep Transfer Learning for Predicting Microbial Attachment in Microbial Fuel Cells to Enhance Bioenergy Recovery. Journal of Sustainable Forestry. (In Press)
|
PDF (Published Version)
- Published Version
Available under License Creative Commons Attribution. Download (6MB) | Preview |
Abstract
Microbial Fuel Cells (MFCs) offer a promising pathway for converting organic matter from biomass-rich wastewater into electricity while contributing to sustainable energy recovery. However, predicting and optimizing microbial attachment to electrodes–critical for power generation–remains a challenge. This study introduces a deep learning approach using transfer learning to predict microbial attachment patterns on electrode surfaces from scanning electron microscope (SEM) images. The methodology employs advanced convolutional neural networks (ResNet18 and VGG19_bn) that are fine-tuned on experimentally collected SEM images of MFC electrode surfaces. Among the tested models, ResNet18 achieved the highest accuracy (51.16%) in classifying microbial attachment levels, demonstrating the potential of AI-assisted bioenergy optimization. Findings confirm a positive correlation between microbial surface coverage and MFC performance, with higher attachment improving power density and COD removal efficiency. This research provides a framework for integrating artificial intelligence into bioenergy systems, supporting real-time monitoring and control of MFCs for efficient renewable energy generation.
| Item ID: | 91748 |
|---|---|
| Item Type: | Article (Research - C1) |
| ISSN: | 1540-756X |
| Keywords: | biomass energy, deep learning for bioenergy, microbial attachment prediction, Microbial fuel cell, sustainable forestry, transfer learning |
| Copyright Information: | © 2026 The Author(s). Published with license by Taylor & Francis Group, LLC. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent. |
| Date Deposited: | 14 Aug 2026 00:56 |
| FoR Codes: | 46 INFORMATION AND COMPUTING SCIENCES > 4601 Applied computing > 460199 Applied computing not elsewhere classified @ 100% |
| SEO Codes: | 22 INFORMATION AND COMMUNICATION SERVICES > 2202 Environmentally sustainable information and communication services > 220299 Environmentally sustainable information and communication services not elsewhere classified @ 100% |
| More Statistics |
Actions (Repository Staff Only)
 |
Item Control Page |