Artificial intelligence and machine learning approaches in composting process: A review

Area of Science:

• Environmental Science
• Computer Science
• Biotechnology

Background:

• Composting process stability and performance prediction strategies are gaining research interest.
• Machine learning (ML) is increasingly applied for optimizing composting, predicting data, detecting anomalies, and managing complex variables.

Approach:

• This review examines the application, perspectives, and challenges of ML algorithms in composting.
• Key ML algorithms discussed include Artificial Neural Networks (ANNs), Random Forest (RF), Adaptive-network-based fuzzy inference systems (ANFIS), Support Vector Machines (SVMs), and Deep Neural Networks (DNNs).

Key Points:

• The review highlights limitations in current error and performance metrics used in composting studies.
• Artificial Intelligence (AI) algorithms, such as Genetic Algorithm (GA), Differential Evaluation Algorithm (DEA), and Particle Swarm Optimization (PSO), are predominantly used for tuning ML algorithm parameters, not core model parameters.

Conclusions:

• ML offers significant potential for enhancing composting process management and prediction.
• Further research should explore broader applications of AI algorithms for comprehensive composting process optimization.