Actions for Data Science in Scanning Probe Microscopy : Advanced Analytics and Machine Learning

Email RIS file
Bookmark
Report an Issue

Data Science in Scanning Probe Microscopy : Advanced Analytics and Machine Learning

Author
Dusch, William George
Published
[University Park, Pennsylvania] : Pennsylvania State University, 2019.
Physical Description
1 electronic document
Additional Creators
Hudson, Eric
Access Online

Availability

I Want It
I Want It

Finding items...

Graduate Program
Restrictions on Access
Open Access.
Summary
Scanning probe microscopy (SPM) has allowed researchers to measure materials structural andfunctional properties, such as atomic displacements and electronic properties at the nanoscale. Over thepast decade, great leaps in the ability to acquire large, high resolution datasets have opened up thepossibility of even deeper insights into materials. Unfortunately, these large datasets pose a problem fortraditional analysis techniques (and software), necessitating the development of new techniques inorder to better understand this new wealth of data.Fortunately, these developments are paralleled by the general rise of big data and the development ofmachine learning techniques that can help us discover and automate the process of extracting usefulinformation from this data. My thesis research has focused on bringing these techniques to all aspects ofSPM usage, from data collection through analysis. In this dissertation I present results from three ofthese efforts: the improvement of a vibration cancellation system developed in our group via theintroduction of machine learning, the classification of SPM images using machine vision, and thecreation of a new data analysis software package tailored for large, multidimensional datasets which ishighly customizable and eases performance of complex analyses.Each of these results stand on their own in terms of scientific impact for example, the machinelearning approach discussed here enables a roughly factor of two to three improvement over ouralready uniquely successful vibration cancellation system. However, together they represent somethingmore a push to bring machine learning techniques into the field of SPM research, where previouslyonly a handful of research groups have reported any attempts, and where all efforts to date havefocused on analysis, rather than collection, of data. These results also represent first steps in thedevelopment of a driverless SPM where the SPM could, on its own, identify, collect, and begin analysisof scientifically important data.
Other Subject(s)
Genre(s)
Dissertation Note
Ph.D. Pennsylvania State University 2019.
Reproduction Note
Microfilm (positive). 1 reel ; 35 mm. (University Microfilms 13917899)
Technical Details
The full text of the dissertation is available as an Adobe Acrobat .pdf file ; Adobe Acrobat Reader required to view the file.
View MARC record | catkey: 27087994