Journal of Integrative Agriculture ›› 2026, Vol. 25 ›› Issue (6): 2595-2606.DOI: 10.1016/j.jia.2025.09.002

• • 上一篇    下一篇

基于机器学习的有机固体废物堆肥过程中氮素损失预测

  

  • 收稿日期:2025-04-03 修回日期:2025-09-04 接受日期:2025-08-08 出版日期:2026-06-20 发布日期:2026-05-07

Machine learning-driven prediction of nitrogen loss in organic solid waste composting

Haoran Mi1, Dawei Gao2, Deling Yuan1, Xiao Liu3, Lili Gao4, Shengping Li5#, Yuanwang Liu1#   

  1. 1 Hebei Key Laboratory of Heavy Metal Deep-Remediation in Water and Resource Reuse, School of Environmental and Chemical Engineering/State Key Laboratory of Metastable Materials Science and Technology, Yanshan University, Qinhuangdao 066004, China

    2 School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China

    3 Earth & Environment Strasbourg (EES), University of Strasbourg, Strasbourg 67084, France

    4 State Key Laboratory of Efficient Utilization of Agricultural Water Resource, Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing 100081, China

    5 State Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China

  • Received:2025-04-03 Revised:2025-09-04 Accepted:2025-08-08 Online:2026-06-20 Published:2026-05-07
  • About author:Haoran Mi, Mobile: +86-13643122038, E-mail: mhr1120800322@163.com; #Correspondence Shengping Li, Mobile: +86-18511339881, E-mail: lishengping@caas.cn; Yuanwang Liu, Mobile: +86-15624955445, E-mail: liuyuanwang@ysu.edu.cn
  • Supported by:
    This study was financially supported by the National Key R&D Program of China (2021YFD1900700), the National Natural Science Foundation of China (52400188), and the Youth Innovation Program of the Chinese Academy of Agricultural Sciences (Y2025QC09).

PDF

摘要：

堆肥是可持续废弃物管理的关键环节，能够显著实现资源回收并带来环境效益。然而，氮素损失始终是堆肥过程中的主要难题，亟需建立氮损失预测模型。本研究基于307组涵盖堆肥策略、理化性质及堆肥时间阶段的实验数据，采用五种机器学习算法对有机固废堆肥过程中的氮损失进行预测。结果表明，AdaBoost 算法在剔除冗余特征（规模和碳氮比）后表现最优，决定系数达到 0.847。进一步通过Shapley分析发现，堆肥时间阶段、膨松剂、原料类型及铵态氮含量是影响氮损失的关键因素。其中，堆肥初期是氮损失最敏感的时期；以锯末、稻壳和玉米秸秆为膨松剂可提升氮保留率；采用静态通风并辅以化学添加剂亦能有效降低氮损失。上述发现为优化堆肥条件、最大限度减少氮损失提供了科学依据，并为实际操作中的最佳实践给予了明确指导。

Abstract:

Composting represents a crucial component of sustainable waste management, providing significant resource recovery and environmental advantages.  However, nitrogen loss during composting remains a significant challenge, necessitating the development of a predictive model for nitrogen loss during the composting process.  This investigation implemented five machine learning models, utilizing 307 data points encompassing composting strategies, physicochemical properties, and composting time stages, to predict nitrogen loss during organic solid waste composting.  The findings demonstrated that the adaptive boosting (AdaBoost) algorithm achieved optimal performance with a coefficient of determination of 0.847 after eliminating redundant features (scale and C/N).  Moreover, Shapley additive explanation analysis identified several key factors significantly influencing nitrogen losses during composting, including composting time stages, bulking agents, raw materials, and ammonium nitrogen levels.  Notably, the initial phase of composting emerged as the most critical period for nitrogen loss.  The utilization of sawdust, rice husk, and corn stalk as bulking agents enhanced nitrogen retention in compost.  Furthermore, implementing static aeration for ventilation and applying chemical additives effectively reduced nitrogen losses during the composting process.  These results provide a scientific foundation for identifying optimal composting conditions to minimize nitrogen loss, thereby offering practical guidance for effective composting operations.

Key words: machine learning , composting , adaptive boosting , nitrogen loss , feature selection