Huta Raj Banjade
Eligible to work in USA without any sponsorship : adqtsz@r.postjobfree.com
**** ********* *****, ********, **, 23225, USA : +1-215-***-****
• Great Learning: https://eportfolio.mygreatlearning.com/huta-banjade
● Stack-overflow: https://stackoverflow.com/users/6457270/hemanta
● LinkedIn: www.linkedin.com/in/huta-banjade-phd-b301bb181
● Google scholar: https://scholar.google.com/citations?user=cnDnyM4AAAAJ&hl=en&oi=sra Overview
• Computational Physicist with expertise in Machine Learning (ML), Python, and Density functional theory calculations for atomistic systems.
• I have three years of experience in Data Mining and Machine Learning techniques to analyze multiple sources of materials information with different dimensions obtained from Materials Project Database.
• I have two years of experience in experimental solid state physics. I worked on thin film deposition (using Chemical Vapor Deposition technique) and their analysis by using Atomic Force Microscopy, and Scanning Transmission Electron Microscopy.
Technical Skills
● Python: Four years of daily experience in analyzing crystal structure data and their properties for high-speed electronics applications.
● Machine Learning: Three years' experience in training supervised and unsupervised machine learning algorithms to identify and predict the compoundproperties such as bandgap and formation energies
● Toolbox: Numpy, Scipy, Pandas, Keras, TensorFlow, PyTorch, Scikit-learn, Gephi for network visualization
● Bash Scripting: Six years' daily experience in object-oriented tasks, such as file manipulation, data extraction, and job submission in the supercomputing clusters
● Experimental Techniques: Chemical Vapor Deposition Technique (CVD), Atomic Force Microscopy (AFM), Ion Miling, Scanning Transmission Electron Microscopy Education
● PhD in Computational Physics Temple University, PA, USA (Aug 2020)
● M.Sc., Physics Temple University, PA, USA (Aug 2016)
● B.Sc., Physics/Statistics Tribhuvan University, Nepal (Jun 2005) Training and Certification
● “Data Science and Machine Learning: Making Data-Driven Decisions”: Great Learning, MIT.
● “Introduction to Data Science in Python”: Coursera
● “Applied Social Network Analysis in Python”: Coursera
● “Neural Networks and Deep Learning”: Coursera
● “Applied Plotting, Charting and Data Representation in Python”: Coursera
● “Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization”: Coursera
Professional Experience and Independent Projects
● Postdoctoral Fellow Virginia Commonwealth University, VA, USA (Sep 2020 – present )
• Computational design of the super-atomic clusters and solid electrolytes for battery application
• I am currently using machine learning and data mining techniques to predict the geometries of the super-atomic clusters.
● Research Assistant, Temple University (Oct 2016 – Aug 2020 )
● Ph.D. thesis: “Machine learning and computation: exploring structure-property correlations in inorganic crystalline materials.”
● Implemented Data Mining and Machine Learning techniques to analyze multiple sources of material information with different dimensions to predict hard-to-determine physical properties of crystal structures. This work has been published in the peer-reviewed Journal (Science advance) and is featured in Phys.org. See the links below:
https://www.science.org/doi/10.1126/sciadv.abf1754 https://phys.org/news/2021-05-motif-centric-framework-inorganic-crystalline.html
● Constructed material network; a network for crystal structures based on structure motif. This network can recommend new compounds depending on users' application interests.
● Applied dimensional reduction techniques such as Principal component analysis (PCA) and t- stochastic neighborhood embedding method (t-SNE) to investigate the hidden pattern present in the data.