Improving prediction of N2O emissions during composting using model-agnostic meta-learning

Abstract

Nitrous oxide (N₂O) represents a significant environmental challenge as a harmful, long-lived greenhouse gas that contributes to the depletion of stratospheric ozone and exacerbates global anthropogenic greenhouse warming. Composting is considered a promising and economically feasible strategy for the treatment of organic waste. However, recent research indicates that composting is a source of N₂O, contributing to atmospheric pollution and greenhouse effect. Consequently, there is a need for the development of effective, cost-efficient methodologies to quantify N₂O emissions accurately. In this study, we employed the model-agnostic meta-learning (MAML) method to improve the performance of N₂O emissions prediction during manure composting. The highest R² and lowest root mean squared error (RMSE) values achieved were 0.939 and 18.42 mg d^-1, respectively. Five machine learning methods including the backpropagation neural network, extreme learning machine, integrated machine learning method based on ELM and random forest, gradient boosting decision tree, and extreme gradient boosting were adopted for comparison to further demonstrate the effectiveness of the MAML prediction model. Feature analysis showed that moisture content of structure material and ammonium concentration during composting process were the two most significant features affecting N₂O emissions. This study serves as proof of the application of MAML during N₂O emissions prediction, further giving new insights into the effects of manure material properties and composting process data on N₂O emissions. This approach helps determining the strategies for mitigating N₂O emissions.

Keywords: Machine learning models; Manure composting; Model-agnostic meta-learning; Nitrous oxide; Prediction.