Long Fei, Xu Meicai, Liao Wei, Liu Hong
Department of Biological and Ecological Engineering, Oregon State University, Corvallis, OR 97331, USA.
Anaerobic Digestion Research and Education Center, Department of Biosystems & Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USA.
Bioresour Technol. 2025 Nov;435:132940. doi: 10.1016/j.biortech.2025.132940. Epub 2025 Jul 5.
The improper disposal of food waste and livestock manure poses significant environmental risks, including nutrient pollution, water contamination, and greenhouse gas emissions. Anaerobic digestion (AD) provides a sustainable pathway for converting organic waste into biogas while reducing environmental impacts. However, optimizing AD performance at a commercial scale remains challenging due to feedstock variability, operational complexity, and time-dependent dynamics. In this study, we analyzed six years of data from a commercial-scale AD system processing 18 types of food and manure waste to develop machine learning (ML) models for predictive analysis and process optimization. Three key outputs, total gas production, methane percentage, and HS content, were predicted using Random Forest (RF), Artificial Neural Networks (ANN), and XGBoost. RF consistently yielded the highest performance with accuracy of 0.91 (gas production), 0.93 (methane), and 0.91 (HS). Feature importance analysis revealed that time-series factors (e.g., rolling averages of previous days), pH, temperature, and hydraulic retention time (HRT) significantly influenced model accuracy. Notably, feedstocks such as dairy manure and pineapple waste exhibited strong correlations with both gas yield and HS fluctuations. Optimization using Particle Swarm Optimization and Simulated Annealing demonstrated the potential to improve biogas production by up to 12 % and reduce HS levels by as much as 65 % through adjusted operating conditions. These findings highlight the value of ML in not only forecasting AD performance with high accuracy but also in identifying operational strategies to enhance system efficiency and stability. This work provides actionable insights for the data-driven management of commercial-scale AD systems.
食物垃圾和畜禽粪便的不当处理带来了重大的环境风险，包括营养物污染、水污染和温室气体排放。厌氧消化（AD）为将有机废物转化为沼气同时减少环境影响提供了一条可持续途径。然而，由于原料的变异性、操作的复杂性和随时间变化的动态特性，在商业规模上优化厌氧消化性能仍然具有挑战性。在本研究中，我们分析了一个商业规模厌氧消化系统六年的数据，该系统处理18种食物和粪便废物，以开发用于预测分析和过程优化的机器学习（ML）模型。使用随机森林（RF）、人工神经网络（ANN）和XGBoost预测了三个关键输出，即总气体产量、甲烷百分比和HS含量。RF始终表现出最高的性能，气体产量的准确率为0.91，甲烷为0.93，HS为0.91。特征重要性分析表明，时间序列因素（如前几天的滚动平均值）、pH值、温度和水力停留时间（HRT）对模型准确率有显著影响。值得注意的是，奶牛粪便和菠萝废物等原料与气体产量和HS波动都表现出很强的相关性。使用粒子群优化和模拟退火进行优化表明，通过调整操作条件，有可能将沼气产量提高多达12%，并将HS水平降低多达65%。这些发现突出了机器学习在不仅高精度预测厌氧消化性能，而且在识别提高系统效率和稳定性的操作策略方面的价值。这项工作为商业规模厌氧消化系统的数据驱动管理提供了可操作的见解。
