RESEARCH INTERESTS

My research expertise is in computational mechanics, materials modeling & design, and machine learning. In my master's study at NTU, I worked on problems in the area of solid mechanics, structural dynamics, and signal processing. In my Ph.D. study at MIT, I focused on understanding the mechanics of deformation and failure of materials at the atomic level. More specifically, I investigated the structure-property relationships of various types of nanomaterials and biomaterials using atomistic modeling tools including molecular dynamics (MD) and density functional theory (DFT).

 

In 2016, I was deeply inspired by the success of Google DeepMind's AlphaGo program and started to develop machine learning approaches for solving computational mechanics problems. I have published 5 peer-reviewed papers on materials discovery and design using machine learning. I envision that rapid advances in machine learning and artificial intelligence will help solve inverse design problems as well as reduce the computational cost of multiscale modeling and overcome its time-scale and length-scale barriers.

 

I greatly appreciate the financial support that I have received for my study and research. For my Ph.D. study at MIT, I received financial support via a fellowship from the Taiwanese Government and funding from CRP Henri Tudor in the framework of the BioNanotechnology project. For my postdoctoral training at MIT, I received research funding from the Office of Naval Research (ONR) and the Multidisciplinary University Research Initiative (MURI). For my postdoctoral training at UC Berkeley, I was fully funded by the Department of Mechanical Engineering at UC Berkeley.


Abstract: Elastography is an imaging technique to reconstruct elasticity distributions of heterogeneous objects. Since cancerous tissues are stiffer than healthy ones, for decades, elastography has been applied to medical imaging for noninvasive cancer diagnosis. Although the conventional strain-based elastography has been deployed on ultrasound diagnostic-imaging devices, the results are prone to inaccuracies. Model-based elastography, which reconstructs elasticity distributions by solving an inverse problem in elasticity, may provide more accurate results but is often unreliable in practice due to the ill-posed nature of the inverse problem. We introduce ElastNet, a de novo elastography method combining the theory of elasticity with a deep-learning approach. With prior knowledge from the laws of physics, ElastNet can escape the performance ceiling imposed by labeled data. ElastNet uses backpropagation to learn the hidden elasticity of objects, resulting in rapid and accurate predictions. We show that ElastNet is robust when dealing with noisy or missing measurements. Moreover, it can learn probable elasticity distributions for areas even without measurements and generate elasticity images of arbitrary resolution. When both strain and elasticity distributions are given, the hidden physics in elasticity—the conditions for equilibrium—can be learned by ElastNet.

Full paper: C-T Chen and GX Gu, Learning hidden elasticity with deep neural networks, Proceedings of the National Academy of Sciences, 2021, DOI: 10.1073/pnas.2102721118



Updated: Nov 9, 2020


Abstract: Atoms are the building blocks of matter that make up the world. To create new materials to meet some of civilization’s greatest needs, it is crucial to develop a technology to design materials on the atomic and molecular scales. However, there is currently no computational approach capable of designing materials atom-by-atom. In this study, we consider the possibility of direct manipulation of individual atoms to design materials at the nanoscale using a proposed method coined “Nano-Topology Optimization”. Here, we apply the proposed method to design nanostructured materials to maximize elastic properties. Results show that the performance of our optimized designs not only surpasses that of the gyroid and other triply periodic minimal surface structures, but also exceeds the theoretical maximum (Hashin–Shtrikman upper bound). The significance of the proposed method lies in a platform that allows computers to design novel materials atom-by-atom without the need of a predetermined design.

Full paper: C-T Chen, DC Chrzan, GX Gu, Nano-topology optimization for materials design with atom-by-atom control, Nature Communications, 2020, DOI: 0.1038/s41467-020-17570-1


Updated: Nov 9, 2020


Abstract: In recent years, machine learning (ML) techniques are seen to be promising tools to discover and design novel materials. However, the lack of robust inverse design approaches to identify promising candidate materials without exploring the entire design space causes a fundamental bottleneck. A general‐purpose inverse design approach is presented using generative inverse design networks. This ML‐based inverse design approach uses backpropagation to calculate the analytical gradients of an objective function with respect to design variables. This inverse design approach is capable of overcoming local minima traps by using backpropagation to provide rapid calculations of gradient information and running millions of optimizations with different initial values. Furthermore, an active learning strategy is adopted in the inverse design approach to improve the performance of candidate materials and reduce the amount of training data needed to do so. Compared to passive learning, the active learning strategy is capable of generating better designs and reducing the amount of training data by at least an order‐of‐magnitude in the case study on composite materials. The inverse design approach is compared with conventional gradient‐based topology optimization and gradient‐free genetic algorithms and the pros and cons of each method are discussed when applied to materials discovery and design problems.

Full paper: CT Chen and GX Gu, Generative deep neural networks for inverse materials design using backpropagation and active learning, Advanced Science, 2020, DOI: 10.1002/advs.201902607