Week 6

-
We continued to research distance measurements and figure out how they work. We K-means to cluster the net ecosystem exchange values from 659 sights. Then I began to calculate the dynamic time warping distances from all of the sites so that I can use K-means to cluster the values to visualize the similarity of the net ecosystem values.

Comments

Post a Comment

Popular posts from this blog

Description of project

-
When scientists collect their data there tends to be an overlap in the acquired data. Due to this computer resources and space are wasted for this duplicated data. In this project we will focus on techniques to help scientists track and identify this duplicated data so that it can be dealt with. We will do this by developing MinHash algorithms. Doing this we hope will help scientists find duplicated data and not have to waste computer space and resources.
Read more

Week 2

-
I have read a lot of papers and feel I am getting the hang on what is going on from a theoretical stand point. I have started coding and am attempting to use faiss, nmslib and falconn algorithms to use Locality Sensitive Hashing, LSH on a small dataset. Eventually I want to be able to use these algorithms to analyze a larger dataset from FLUXNET.
Read more

Week Starting 06/17/19 (Week 3)

-
This week the research dataset was changed from the Sloan Digital Sky Survey to the FLUXNET dataset.  FLUXNET measures the exchanges of carbon dioxide, water vapor, and energy between terrestrial ecosystems and the atmosphere. I finished my research proposal, which can be found here: https://drive.google.com/open?id=1yXAvF-o3i_VXOL7Tl7_QvyDVWCXOopM69zbvg--vtpM. I have started to research the FLUXNET data and so far I have read four papers on the subject.
Read more