堆肥
成熟度(心理)
计算机科学
机器学习
工程类
农业工程
人工智能
生化工程
废物管理
心理学
发展心理学
作者
Yilin Kong,Jing Zhang,Xuanshuo Zhang,Xia Gao,Jie Yin,Guoying Wang,Jiaming Li,Guoxue Li,Cui Zhong-liang,Jing Yuan
标识
DOI:10.1016/j.cej.2024.151386
摘要
Composting is a resource treatment method that uses aerobic microorganisms to convert organic solid waste into stable humus and applied as organic fertilizer. The maturity evaluation of compost is of great significance for its safe application in farmland. Presently, lots of methods have been used to evaluate the compost maturity, including physical indicators, chemical indicators and biological indicators, as well as spectroscopic indicators, computer vision and machine learning. However, these indicators all have limitations. This review systematically delineates and analyzes the role, connotation, applicability, and constraints of various compost maturity evaluation indices. Physical indicators offer ease of operation and qualitative assessment, while quantitative evaluation necessitates machine learning and computer vision approaches. Chemical indicators allow for quantitative maturity assessment, yet evaluation outcomes are substantially influenced by compost raw material properties, necessitating a comprehensive evaluation system incorporating multiple chemical indices and raw material categorization. Although the seed germination index is currently an authoritative indicator for evaluating compost maturity, the absence of standardized seeds and normalized methods impedes the comparison of research results. The spectroscopic indexes are the high demands on detection instruments and data analysis capabilities. Machine learning presents a promising avenue for objective evaluation in the future. However, the development of machine learning models and algorithms necessitates more standardized data training sets to enhance accuracy. In light of the pressing need for maturity evaluation, establishing a more standardized and universal maturity evaluation system or developing rapid, accurate, and cost-effective detection indicators is imperative. This study analyzed compost maturity evaluation methods in order to give technical assistance for accurate and quantitative compost maturity evaluation as well as safe manure return to the field.
科研通智能强力驱动
Strongly Powered by AbleSci AI