Related Experiment Video
Updated: Jul 25, 2025
Characterizing Mediated Extracellular Electron Transfer in Lactic Acid Bacteria with a Three-Electrode, Two-Chamber Bioelectrochemical System
Published on: August 23, 2024
Application of artificial intelligence-based methods in bioelectrochemical systems: Recent progress and future
Chunyan Li1, Dongchao Guo2, Yan Dang1
1Beijing Key Lab for Source Control Technology of Water Pollution, College of Environmental Science and Engineering, Beijing Forestry University, Beijing, 100083, China; Engineering Research Center for Water Pollution Source Control & Eco-remediation, College of Environmental Science and Engineering, Beijing Forestry University, Beijing, 100083, China.
Artificial intelligence (AI) methods enhance bioelectrochemical systems (BESs) by analyzing complex data for improved energy production and wastewater treatment. This review compares AI algorithms like neural networks and fuzzy logic for optimizing BES performance.
Area of Science:
- Environmental Science
- Biotechnology
- Computer Science
Background:
- Bioelectrochemical Systems (BESs) utilize microbial metabolism for energy generation, wastewater treatment, and bioremediation.
- The complex mechanisms of BESs necessitate advanced analytical approaches for performance optimization.
- Artificial intelligence (AI) offers powerful tools for pattern recognition and data analysis in complex biological systems.
Purpose of the Study:
- To review and compare commonly used AI algorithms in BES applications.
- To analyze the application of AI in predicting microbial communities, substrates, and reactor performance.
- To discuss limitations and future directions for AI-based optimization of BESs.
Main Methods:
- Review and comparative analysis of AI algorithms including Artificial Neural Network (ANN), Genetic Programming (GP), Fuzzy Logic (FL), Support Vector Regression (SVR), and Adaptive Neural Fuzzy Inference System (ANFIS).
- Examination of AI applications in predicting key BES parameters.
- Discussion of AI algorithm features, such as ANN's network structure, GP's training utility, FL's reasoning, SVR's accuracy, and ANFIS's hybrid nature.
Main Results:
- AI algorithms demonstrate significant potential in enhancing BES efficiency through data-driven insights.
- Specific AI methods offer distinct advantages: ANN (simplicity), GP (training), FL (human-like logic), SVR (accuracy/robustness), ANFIS (hybrid benefits).
- AI applications successfully predict microbial dynamics, substrate conversion, and reactor performance, improving system management.
Conclusions:
- AI-based methods are crucial for optimizing BES performance and unlocking their full potential in energy and environmental applications.
- Further research into AI limitations and development is recommended for advancing BES technology.
- This review provides a comprehensive overview for researchers and practitioners in the field of AI-driven BESs.
