Machine learning‐based model for predicting the material properties of nanostructured aerogels

• Published in: SPE polymers 2023-01, Vol.4 (1), p.24-37
• Main Authors: Tafreshi, Omid Aghababaei, Saadatnia, Zia, Ghaffari‐Mosanenzadeh, Shahriar, Okhovatian, Sogand, Park, Chul B., Naguib, Hani E.
• Format: Article
• Language: English
• Subjects: Aerogels; Artificial neural networks; Datasets; data‐driven modeling; Heat conductivity; Machine learning; Material properties; Model accuracy; Modulus of elasticity; Nanostructure; nanostructured aerogels; neural network; Neural networks; Porous materials; Radiation; Solvents; Synthesis; Unsupervised learning
• ISSN: 2690-3857; 2690-3857
• DOI: 10.1002/pls2.10082

Data‐driven modeling in material science rose to prominence in the last decade, and various supervised and unsupervised machine learning techniques have been employed for material development and deriving insights for decision‐making purposes. In this context, machine learning can have prominent importance in the field of nanostructured aerogels for accelerated materials design and material properties prediction. Current attempts rely only on experimental approach, which have inherent shortcomings, including inefficiency due to the prolonged synthesis process, and necessity of analyzing microstructure and properties. In order to address the challenges associated with the traditional experimental approach, in this study, an artificial neural network (ANN) is employed to predict the material properties of nanostructured aerogels. Polyimide (PI) organic aerogels are selected for this purpose. Through understanding the contributing material and processing factors in PI aerogel synthesis, a dataset is prepared. Data preprocessing is performed, and through hyperparameter tuning, ANN is constructed and trained for a given dataset. Various material properties are predicted, including compressive modulus, density, and porosity. Results show that ANN is trained with high accuracy, which demonstrates the versatility and accuracy of model in materials properties prediction. This study can therefore pave the way for establishing a platform for data‐driven materials innovation. This study focused on the development of a machine learning predictive model as a new toolbox to mitigate costs, risks, and time associated with the traditional experimental approach in aerogel materials fabrication. To achieve this objective, an artificial neural network model was constructed with optimized topology. Various properties of aerogels including compressive modulus, density, and porosity were accurately predicted and a procedure for the use of model for novel aerogel materials development is recommended.