Non-destructive spectroscopy assisted by machine learning for coal industrial analysis: Strategies, progress, and future prospects

• Published in: TrAC, Trends in analytical chemistry (Regular ed.) Vol. 192; p. 118322
• Main Authors: Liu, Yu, Xu, Yu-Peng, Chen, Pu, Li, Jing-Yan, Liu, Dan, Chu, Xiao-Li
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2025
• Subjects: Coal; Laser-induced breakdown spectroscopy; Machine learning; Spectral analysis; Spectral analysis; Coal; Machine learning; Laser-induced breakdown spectroscopy
• ISSN: 0165-9936
• DOI: 10.1016/j.trac.2025.118322

Coal plays an irreplaceable role in the global energy system. With growing energy demand and environmental concerns, rapid and accurate coal quality analysis is essential. This review summarizes recent advances in applying machine learning-assisted spectroscopic techniques—including mid-infrared (MIR)spectroscopy, near-infrared (NIR)spectroscopy, terahertz (THz)spectroscopy, X-ray fluorescence (XRF)spectroscopy, laser-induced breakdown spectroscopy (LIBS), and spectral fusion—for coal identification, quality evaluation, and real-time monitoring. Special emphasis is placed on LIBS instrumentation, modeling strategies, and industrial applications. Key challenges such as matrix effects and signal instability are discussed, along with solutions involving hardware improvements, optimized conditions, and data processing. The review also highlights future trends and the commercialization potential of these technologies, especially spectral fusion, aiming to support efficient and clean coal utilization. •Recent advancements in non-destructive spectroscopic techniques (MIR, NIR, THz, XRF, LIBS) for coal analysis are reviewed.•Machine learning enhances the accuracy and repeatability of spectroscopic models for coal analysis.•Strategies for enhancing spectroscopic performance are discussed.•Spectral fusion and real-time online coal analysis are highlighted.•Challenges and prospects of non-destructive spectroscopic techniques in the coal industry are addressed.