Skip to content

Summary of final project

The final project for the class is to use the tools we have developed regarding data analysis, data visualization and inferential thinking to gain insight from an Earth science data set. The data you choose to investigate is open and the question you choose to ask is open. The goal of your approach should be to analyze data in a way that gives insight into a phenomenon associated with Earth science.

Requirements for the project that should all be contained within a Jupyter notebook:

  • Pose a question and have an introductory markdown text cell that describes the problem, describes the ways you are going to approach the problem and describes the data you are going to use to do so. This text should include references.
  • Use at least three different types of data visualizations plots that are ones we used throughout the course.
  • Use at two different data analysis methods/approaches that you utilized in the course.
  • Conclude with a substantive markdown text cell that contains at least of page of text and describes the results of your analysis.
  • Have a final acknowledgements section and a works cited section.

As your submission, upload a zipped directory that contains:

  • a polished Jupyter notebook that contains your data analysis, visualizations and explanatory text.
  • the underlying data sets you used in your analysis
  • exported PDF of the Jupyter notebook
  • each person is required to upload one submission. If it is a collaborative project, please note that and inclue names of the group mebers, limted to a maximum of three members.

Choice of problems and data

The choice of problems and data that you apply are open --- you get to choose your own adventure. However, it is absolutely essential that you cite the source of the data and discuss/cite any resource, place, or person that you got ideas from. It is perfectly reasonable to get ideas and inspiration from other sources. When you do, you need to be fully transparent about where such ideas came from with acknowledgements and citations as appropriate.

Some places to go for Earth Science data:

You can also find data sets in individual papers or other databases. You can search Google Scholar for a topic you are interested in and download the associated data to deal with and analyze.

Specific data sets we have used so far:

  • global elevation data
  • a comprehensive seismic catalog
  • Mauna Loa CO2
  • igneous geochemistry data (additional data can be downloaded from EarthChem.org)