|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ПсковГУ |
||
Machine learning methods for designing a carbon dot based photoluminescent multimodal nanosensorстатья
Статья опубликована в высокорейтинговом журнале
Статья опубликована в журнале из списка Web of Science и/или Scopus- Авторы: Chugreeva Galina, Laptinskiy Kirill, Guskov Artem, Kupriyanov Gavriil, Isaev Igor, Dolenko Sergey, Dolenko Tatiana
- Журнал: Scientific reports
- Том: 16
- Год издания: 2026
- Издательство: Nature Publishing Group
- Местоположение издательства: United Kingdom
- Номер статьи: 11808
- DOI: 10.1038/s41598-026-38266-4
- Аннотация: This study addresses the problem of simultaneous determination of metal cations and nitrate anions concentrations inmulticomponent aqueous solutions. To solve this task, a photoluminescent nanosensor based on carbon dots synthesized bythe hydrothermal method from citric acid and ethylenediamine is developed. A key novel feature of the developed nanosensoris its multimodality, i.e. the ability to simultaneously determine (by the same photoluminescent spectrum) the concentrations ofall ions under consideration. Various representations of the photoluminescent spectrum of carbon dots added to the studiedsolution are used as the source of information. To determine the target concentrations from the photoluminescent spectraunder consideration, machine learning methods are used: neural networks of the multilayer perceptron type, convolutionalneural networks, Kolmogorov-Arnold neural networks, gradient boosting, and linear regression. The use of the transferlearning technique for neural networks in the transition from solving a 6-parameter problem to solving a 7-parameter problemis considered. It was shown that the best results are achieved using convolutional neural networks. (The mean absoluteerrors of simultaneous determination of Cu2+, Ni2+, Co2+, Pb2+, Al3+, Cr3+ , cations and NO−3 anion concentrations were0.68, 1.05, 0.43, 1.38, 1.08, 0.32 and 2.43 mM, respectively.) Such precision meets the requirements for determining theconcentration of ions in wastewater and process water. Transfer learning allows reducing the computational cost of the solution.Kolmogorov-Arnold networks can provide a visual interpretation of the resulting model.
- Добавил в систему: Куприянов Гавриил Александрович
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|