Resume

My GitHub repository click here

Summary

I’m always fascinated by how complex systems can be simplified to essential processes and enjoys solving real-world problems with math and programming. As a data scientist, I believe that best practices are built on the thorough understanding of underlying algorithms, and the ability to communicate effectively.

Projects

Whale Identifcation Using Deep Learning (blog, repo)
(in progress)

  • Developed neural network that identi es whales based on photos
  • Applied biometric recognition techniques for ocean conservation
  • Tools: Keras, Neural networks, Spark, AWS

A 3D Interactive Recommender for TED Talks (blog, repo)

  • Investigated relationships between TED talks using topic modeling
  • Created a TED talk recommender using a 3D interactive visualization
  • Tools: NLTK, Gensim, Word2Vec, scikit-learn, pymongo

Edible or Poisonous? A Mushroom Classifier (blog, repo)

  • Evaluated various classi ers for identifying edible mushrooms
  • Performed feature engineering accounting for human perception errors
  • Tools: scikit-learn, pandas, NumPy, D3.js, Flask, PostgreSQL

Predicting Sediment Concentration in the Mississippi River (blog, repo)

  • Developed a regression model to predict Mississippi River sediment load
  • Automated retrieving USGS hydrological data using web-scraping tools
  • Tools: pandas, scikit-learn, StatsModels, BeautifulSoup, Selenium

Experience

Data Science Fellow | Metis | January 2018 - April 2018

  • Completed 5 data science projects in an ACCET-accredited 12-week immersive data science program

Postdoctoral Fellow | The Water Institute of the Gulf | April 2016 - December 2017

  • Provided optimized diversion operation plans to government agencies based on statistical analysis using historical Mississippi River data
  • Built numerical models to simulate the performance of sediment diversions Completed 10+ technical consulting reports
  • Worked with teams of 5+ members on multiple projects end-to-end

Postdoctoral Researcher | The University of Texas at Austin | November 2012 - March 2016

  • Developed numerical and statistical methods to study river patterns
  • Mentored graduate students and lectured at graduate-level workshops
  • Produced 5 peer-reviewed publications and gave 2 invited conference talks
  • Organized sessions in 3 major conferences as chairs and conveners

Graduate Research Assistant | University of Minnesota | September 2007 - October 2012

  • Developed a computational model that captures the complexity in natural systems using simpli ed process representations
  • Implemented various mathematical models to simulate pattern formation
  • Produced 2 peer-reviewed publications and 1 keynote conference talk

Graduate Teaching Assistant | University of Minnesota | Sep 2009 to May 2010

  • Lectured and mentored in Fluid Mechanics and Computer Applications

Skills

Programming
Python, SQL, Matlab, Linux, MongoDB, AWS, GitHub
Machine Learning
scikit-learn, NumPy, pandas, Keras, Natural language processing, Spark
Science & Engineering
Delft3D, ArcGIS, numerical analysis, hydrology, geomorphology, CFD, coastal engineering
Languages
English, Chinese (Mandarin)
Other
Microsoft Office, Adobe Suite, underwater photography, aerial photography

Education

Ph.D. in Civil Engineering | 2013
Univerisity of Minnesota, Twin Cities, MN

B.S. in Applied Mathematics | 2007
Peking University, China