Machine learning-based prediction of compost maturity and identification of key parameters during manure composting.

Evaluating compost maturity, e.g. via manual seed germination index (GI) measurement, is both time-consuming and costly during composting. This study employed six machine learning methods, including random forest (RF), extra tree (ET), eXtreme gradient boosting, gradient boosting decision tree, back propagation neural network, and multilayer perceptron, to develop models for predicting GI during manure composting. RF and ET exhibited robust predictive performance for GI, achieving high coefficient of determination (R) of 0.937 and 0.904, respectively, along with root mean squared error of 7.261 and 8.930. SHapley additive exPlanations identified the duration time of composting, total nitrogen, and electrical conductivity as the key features influencing GI. Validation with actual GI data further confirmed the effectiveness of RF and ET models in predicting GI. This study could facilitate optimizing manure composting strategies, enable efficient parameter regulation, reduce labor costs, assist in anomaly detection, and promote intelligent management in real-world composting practices.