data science for conservation international's big ecosystem data dr. brand niemann director and...

14
Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community http://semanticommunity.info/ http://www.meetup.com/Virginia-Big-Data-Meetup/ http://www.meetup.com/Federal-Big-Data-Working-Group/ http://www.meetup.com/Northern-Virginia-Semantic-Web-Meetup/ http://semanticommunity.info/Data_Science/Federal_Big_Data_Working_Gro up_Meetup May 25, 2015 1

Upload: nathaniel-parrish

Post on 04-Jan-2016

216 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

1

Data Science for Conservation

International's Big Ecosystem Data

Dr. Brand NiemannDirector and Senior Data Scientist/Data Journalist

Semantic Communityhttp://semanticommunity.info/

http://www.meetup.com/Virginia-Big-Data-Meetup/ http://www.meetup.com/Federal-Big-Data-Working-Group/

http://www.meetup.com/Northern-Virginia-Semantic-Web-Meetup/ http://semanticommunity.info/Data_Science/Federal_Big_Data_Working_Group_Meetup

May 25, 2015

Page 2: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

2

Overview

• I am looking for the best datasets to visualize in Spotfire that come from Vertica and the TEAM Site.• For example I see at: http://www.teamnetwork.org/products/gis

• GIS Datasets I could download by agreeing to the Agreement (which I did) and others that say:• Supplementary GIS Data (for select sites)• TEAM Network Members only• Your account does not currently have Network Member privileges.• So should I request permission to work with those?

• Riwanda: http://www.teamnetwork.org:28080/gridsphere/gridsphere?cid=download• Got a few examples of spreadsheets

• Lidar: http://www.teamnetwork.org/data/lidar• Got a few examples of images and PDF Metadata

• Camera Trap: http://www.teamnetwork.org/camera-trap-downloads• Got an example of JPEGs

• I tried: http://www.teamnetwork.org/gridsphere/gridsphere?cid=search• And got a popup message that said the file was 132 MB and an email would be sent to download it. I got the 10 MB ZIP

download file just now and it looks useful.

• Did I miss anything here and are there any other data download sites like TEAM?

Page 3: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

3

TeamNetwork.Org: Web Page

http://www.teamnetwork.org/

Download Team Data

Page 4: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

4

Data Query and Download: Web Page

http://www.teamnetwork.org/data/query

• TEAM Protocol Data• Monitoring Ecosystem Services,

Agriculture, and Livelihoods in Rwanda

• Lidar Data• GIS Data• Historic Camera Trap Data

Got an example of Each: See Next Slide

Search

Page 5: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

5

Data Query and Download: Files

Page 14: Data Science for Conservation International's Big Ecosystem Data Dr. Brand Niemann Director and Senior Data Scientist/Data Journalist Semantic Community

14

Conclusions and Recommendations

• I Data Mined for the best datasets to visualize in Spotfire that come from Vertica and the TEAM Site.• The data sets, and their metadata, required extraction from ZIP files and

some reformatting for input to Spotfire.• I built a MindTouch Knowledge Base and a Spotfire Dashboard to analyze 12

data sets in CSV, Excel, and Shape file formats.• The results are shown in 7 Spotfire Tabs with dynamically linked adjacent

visualizations.• I need Conservation International Subject Matter Expertise to help interpret

the Spatial Data and suggestions for more data sets for Data Science.