Applications of Machine learning in Computational Nanotechnology

Machine learning (ML) has gained extensive attentions in recent years due to its powerful data analysis capabilities. It has been successfully applied to many fields and helped the researchers to achieve several major theoretical and applied breakthroughs. Some of the notable applications in the field of computational nanotechnology are machine learning potentials, property prediction and material discovery. This review summarizes of the state-of-the-art research progress in these three fields. Machine learning potentials bridge the efficiency vs. accuracy gap between density functional calculations (DFT) and classical molecular dynamics (MD). For property predictions, machine learning provides a robust method that eliminate the needs of repetitive calculations for different simulation setup. Material design and drug discovery assisted by machine learning greatly reduces the capital and time investment by orders of magnitude. In this perspective, several common machine learning potentials and machine learning models are firstly introduced. Using these state-of-the-art models, developments in property predictions and material discovery are overviewed, respectively. Finally, this paper was concluded with an outlook on future directions of data-driven research activities in computational nanotechnology.

Finite Element Analysis in Nanotechnology Research

The Finite Element Analysis in the field of Nanotechnology is continually contributing to the areas ranging from electronics, micro computing, material science, quantum science, engineering, biotechnology, medicine, aerospace, and environment and in computational nanotechnology. The finite element method (FEM) is widely used for solving problems of traditional fields of engineering and Nano research where experimental analysis is unaffordable. This numerical technique can provide accurate solution to complex engineering problems. Over decades this method has become the noted research area for the mathematicians. The popularity of FEM is due to the advent of computer FEA software such as NASTRAN, ANSYS, ABAQUS, Matlab, OPEN Foam, Simscale and the like. With the development of nanoscience, the researchers found difficulties in spending funds for nano related projects. The FEA has evolved as the affordable methodology and offers solutions to all complicated systems of research.

nanoHUB.org: A Gateway to Undergraduate Simulation-Based Research in Materials Science and Related Fields

ABSTRACTOur future engineers and scientists will likely be required to use advanced simulations to solve many of tomorrow's challenges in nanotechnology. To prepare students to meet this need, the Network for Computational Nanotechnology (NCN) provides simulation-focused research experiences for undergraduates at an early point in their educational path, to increase the likelihood that they will ultimately complete a doctoral program. The NCN summer research program currently serves over 20 undergraduate students per year who are recruited nationwide, and selected by NCN and the faculty for aptitude in their chosen field within STEM, as well as complementary skills such as coding and written communication. Under the guidance of graduate student and faculty mentors, undergraduates modify or build nanoHUB simulation tools for exploring interdisciplinary problems in materials science and engineering, and related fields. While the summer projects exist within an overarching research context, the specific tasks that NCN undergraduate students engage in range from modifying existing tools to building new tools for nanoHUB and using them to conduct original research. Simulation tool development takes place within nanoHUB, using nanoHUB’s workspace, computational clusters, and additional training and educational resources. One objective of the program is for the students to publish their simulation tools on nanoHUB. These tools can be accessed and executed freely from around the world using a standard web-browser, and students can remain engaged with their work beyond the summer and into their careers. In this work, we will describe the NCN model for undergraduate summer research. We believe that our model is one that can be adopted by other universities, and will discuss the potential for others to engage undergraduate students in simulation-based research using free nanoHUB resources.