Applications of chemical fingerprints and machine learning in plant ecology: Recent progress and future perspectives

With the rapid development of chromatography, spectroscopy and other detection techniques, chemical fingerprinting has become a powerful tool for ecology research. The data generated by these techniques contain a large amount of key information related to the molecular structure, and the optimization and study of these data using chemometrics and machine learning algorithms will have higher precision and accuracy. This paper reviews the analytical techniques used to generate chemical fingerprints in recent years and scrutinises the diversity of applications of chemical fingerprints in the field of plant ecology. Applications in combination with machine learning are emphasized. Prospects for chemical fingerprinting combined with machine learning in plant ecology include the development of fingerprinting databases for accurate species identification, and the integration of advanced techniques to incorporate fingerprinting techniques into ecological modelling to predict plant responses to environmental changes. These innovative avenues hold the promise of improving our understanding of plants and their complex interactions in various ecosystems and integrating them to advance ecological research.