Deep Learning-Driven Integration of Multimodal Data for Material Property Predictions

• Type: Article in International Scientific Journal
• Date: 2025

Authors

Costa, V (Author) Other; Oliveira, José Manuel (Author) FEP; Ramos, P (Author) Other

Journal

Title: COMPUTATION

Vol. 13 No. 12

Initial page: 282 (30)

ISSN: 2079-3197

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-018-4R8

DOI: 10.3390/computation13120282

Abstract (EN): <jats:p>This study investigates the integration of deep learning for single-modality and multimodal data within materials science. Traditional methods for materials discovery are often resource-intensive and slow, prompting the exploration of machine learning to streamline the prediction of material properties. While single-modality models have been effective, they often miss the complexities inherent in material data. The paper explores multimodal data integration¿combining text, images, and tabular data¿and demonstrates its potential to improve predictive accuracy. Utilizing the Alexandria dataset, the research introduces a custom methodology involving multimodal data creation, model tuning with AutoGluon framework, and evaluation through targeted fusion techniques. Results reveal that multimodal approaches enhance predictive accuracy and efficiency, particularly when text and image data are integrated. However, challenges remain in predicting complex features like band gaps. Future directions include incorporating new data types and refining specialized models to improve materials discovery and innovation.</jats:p>

Language: English

Type (Professor's evaluation): Scientific