![MRS Bulletin Materials News Podcast artwork](https://is1-ssl.mzstatic.com/image/thumb/Podcasts113/v4/6d/7b/08/6d7b08c6-549c-9606-a4f7-76693377b522/mza_6858712600852089095.jpg/100x100bb.jpg)
Episode 2: Gao and Ni on a deep learning method to predict elastic modulus field
MRS Bulletin Materials News Podcast
English - March 24, 2021 11:00 - 26 minutes - 18.3 MB - ★★★★★ - 2 ratingsScience News Tech News materials research materials science 3d bioprinting artificial intelligence machine learning bioelectronics perovskites quantum materials robotics and synthetic biology Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
MRS Bulletin’s Impact editor Markus Buehler interviews Huajian Gao of Nanyang Technological University, Singapore and Bo Ni of Brown University on their development of a deep learning method to predict the elastic modulus field based on strain data that may be the result of an experiment. The method is highly efficient and offers real-time solutions to problems that usually require complex numerical methods that rely on variational methods to solve elasticity problems, like finite element analysis. This type of approach may change the way researchers interpret experimental data. See the article “A deep learning approach to the inverse problem of modulus identification in elasticity” (doi:10.1557/mrs.2020.231).