Quantification of salt stress in wheat leaves by Raman spectroscopy and machine learning

Creative Commons License

Kecoglu I., Sirkeci M., Unlu M. B., ŞEN A., Parlatan U., GÜZELÇİMEN F.

Scientific Reports, cilt.12, sa.1, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 12 Sayı: 1
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1038/s41598-022-10767-y
  • Dergi Adı: Scientific Reports
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, BIOSIS, CAB Abstracts, Chemical Abstracts Core, EMBASE, MEDLINE, Veterinary Science Database, Directory of Open Access Journals
  • İstanbul Üniversitesi Adresli: Evet

Özet

© 2022, The Author(s).The salinity level of the growing medium has diverse effects on the development of plants, including both physical and biochemical changes. To determine the salt stress level of a plant endures, one can measure these structural and chemical changes. Raman spectroscopy and biochemical analysis are some of the most common techniques in the literature. Here, we present a combination of machine learning and Raman spectroscopy with which we can both find out the biochemical change that occurs while the medium salt concentration changes and predict the level of salt stress a wheat sample experiences accurately using our trained regression models. In addition, by applying different machine learning algorithms, we compare the level of success for different algorithms and determine the best method to use in this application. Production units can take actions based on the quantitative information they get from the trained machine learning models related to salt stress, which can potentially increase efficiency and avoid the loss of crops.