Unveiling the Potential of AI for Nanomaterial Morphology Prediction

Ivan Dubrovsky, Andrei Dmitrenko, Aleksei Dmitrenko, Nikita Serov, Vladimir Vinogradov
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11957-11978, 2024.

Abstract

Creation of nanomaterials with specific morphology remains a complex experimental process, even though there is a growing demand for these materials in various industry sectors. This study explores the potential of AI to predict the morphology of nanoparticles within the data availability constraints. For that, we first generated a new multi-modal dataset that is double the size of analogous studies. Then, we systematically evaluated performance of classical machine learning and large language models in prediction of nanomaterial shapes and sizes. Finally, we prototyped a text-to-image system, discussed the obtained empirical results, as well as the limitations and promises of existing approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-dubrovsky24a, title = {Unveiling the Potential of {AI} for Nanomaterial Morphology Prediction}, author = {Dubrovsky, Ivan and Dmitrenko, Andrei and Dmitrenko, Aleksei and Serov, Nikita and Vinogradov, Vladimir}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {11957--11978}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/dubrovsky24a/dubrovsky24a.pdf}, url = {https://proceedings.mlr.press/v235/dubrovsky24a.html}, abstract = {Creation of nanomaterials with specific morphology remains a complex experimental process, even though there is a growing demand for these materials in various industry sectors. This study explores the potential of AI to predict the morphology of nanoparticles within the data availability constraints. For that, we first generated a new multi-modal dataset that is double the size of analogous studies. Then, we systematically evaluated performance of classical machine learning and large language models in prediction of nanomaterial shapes and sizes. Finally, we prototyped a text-to-image system, discussed the obtained empirical results, as well as the limitations and promises of existing approaches.} }
Endnote
%0 Conference Paper %T Unveiling the Potential of AI for Nanomaterial Morphology Prediction %A Ivan Dubrovsky %A Andrei Dmitrenko %A Aleksei Dmitrenko %A Nikita Serov %A Vladimir Vinogradov %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-dubrovsky24a %I PMLR %P 11957--11978 %U https://proceedings.mlr.press/v235/dubrovsky24a.html %V 235 %X Creation of nanomaterials with specific morphology remains a complex experimental process, even though there is a growing demand for these materials in various industry sectors. This study explores the potential of AI to predict the morphology of nanoparticles within the data availability constraints. For that, we first generated a new multi-modal dataset that is double the size of analogous studies. Then, we systematically evaluated performance of classical machine learning and large language models in prediction of nanomaterial shapes and sizes. Finally, we prototyped a text-to-image system, discussed the obtained empirical results, as well as the limitations and promises of existing approaches.
APA
Dubrovsky, I., Dmitrenko, A., Dmitrenko, A., Serov, N. & Vinogradov, V.. (2024). Unveiling the Potential of AI for Nanomaterial Morphology Prediction. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:11957-11978 Available from https://proceedings.mlr.press/v235/dubrovsky24a.html.

Related Material