Combining materials design and deep learning: AI-enhanced luminescence thermometry with a novel Eu                    <sup>3+</sup>                    /Tb                    <sup>3+</sup>                    polymeric coordination compound

Polikovskiy, T.A.; Gontcharenko, V.E.; Korshunov, V.M.; Metlin, M.T.; Metlina, D.A.; Samsonov, S.V.; Belousov, Y.A.; Brites Carlos, D.S.; Carlos, L.D.; Taydakov, I.V.

Авторы: Polikovskiy Trofim A., Gontcharenko Victoria E., Korshunov Vladislav M., Metlin Mikhail T., Metlina Darya A., Samsonov Sergey V., Belousov Yury A., Brites Carlos D.S., Carlos Luís D., Taydakov Ilya V.
Журнал: Materials Chemistry Frontiers
Том: 9
Номер: 23
Год издания: 2025
Издательство: Royal Society of Chemistry
Местоположение издательства: United Kingdom
Первая страница: 3443
Последняя страница: 3459
DOI: 10.1039/d5qm00598a
Аннотация: Conventional thermal sensors often face limitations due to their reliance on direct contact and restrictedmeasurement ranges, leading to the emergence of novel techniques like luminescence thermometry.However, sensitivity of luminescent thermometers is limited by the only used Boltzmann-based Mott–Seitz model, which is imperfect. To overcome this, we complemented Mott–Seitz model applyingmachine learning algorithms, achieving supreme accuracy improvement. Thus, here we report a combined approach to luminescence thermometry, utilizing novel mixed-metal polymer Eu3+/Tb3+ triscomplex and a deep learning algorithm. The complex, synthesized using 4,4,4-trifluoro-1-(5,5-dimethyl1H-pyrazol-4-yl)butane-1,3-dione, exhibits maximum relative thermal sensitivity of 5.5% K1 and atemperature uncertainty ranging from 0.1 to 1.8 K across a wide temperature range (190 to 300 K). Weenhanced accuracy seven-fold from RMSE 2.54 K for the conventional intensity ratio method to RMSE0.36 K for combined method using convolutional neural network. These results highlight the potential ofcombined approach to achieve record-high precision thermometers even for common compounds
Добавил в систему: Белоусов Юрий Александрович

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ПсковГУ
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

ИСТИНА ПсковГУ

Combining materials design and deep learning: AI-enhanced luminescence thermometry with a novel Eu <sup>3+</sup> /Tb <sup>3+</sup> polymeric coordination compoundстатья Исследовательская статья

Прикрепленные файлы