life under your feet johns hopkins university computer science earth and planetary sciences
DESCRIPTION
Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences Physics and Astronomy http://www.lifeunderyourfeet.org. Today. Introduce Life Under Your Feet Show some data Our current goals and future directions. Long-Term Environmental Monitoring. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/1.jpg)
Life Under Your Feet
Johns Hopkins UniversityComputer Science
Earth and Planetary SciencesPhysics and Astronomy
http://www.lifeunderyourfeet.org
![Page 2: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/2.jpg)
Today
• Introduce Life Under Your Feet
• Show some data
• Our current goals and future directions
![Page 3: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/3.jpg)
Long-Term Environmental Monitoring
![Page 4: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/4.jpg)
![Page 5: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/5.jpg)
![Page 6: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/6.jpg)
Sensor Network Design Philosophies
• Use low cost components
• No access to line power– Deployed in remote locations
• Radio is the biggest consumer of power– Minimize radio communication
• Transfer data in bulk (amortize radio costs)– Data Latency vs. Lifetime tradeoff
![Page 7: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/7.jpg)
![Page 8: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/8.jpg)
All Data Online and available!http://dracula.cs.jhu.edu/luyf/en/tools/VZTool/
![Page 9: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/9.jpg)
Deployments
![Page 10: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/10.jpg)
Cub hill locations (50)
![Page 11: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/11.jpg)
Soil Temperature Dataset
![Page 12: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/12.jpg)
Data Features
– Correlated in time and space
– Evolving over time (seasons)
– Diurnal patterns
– Gappy (Due to hardware failures)
– Faulty (Noise, Jumps in values)
![Page 13: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/13.jpg)
Goals
Leverage spatiotemporal correlations:
• Model-based fault detection• Increase network lifetime
– Retrieving data from representative locations– Use model to interpolate at other locations– Tradeoff latency for reduced communication
![Page 14: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/14.jpg)
Examples of Faults
![Page 15: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/15.jpg)
Motivation for both goals
• Environmental Scientists want fault-free data and want to see visualizations– ~ 5% of data is faulty
• Networks need to last a year or more
• They start looking at the actual data much much later– Opportunity to postpone collecting all data
![Page 16: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/16.jpg)
Soil Temperature Dataset
![Page 17: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/17.jpg)
Sketch
• Estimate fixed common effect (daily median)
• Subtract location-specific deviation from this common effect
• Model residuals using PCA– Basis defined in the spatial domain– Initialized using good data– Vectors are randomized and fed one by one
• Tamas’ incremental robust PCA– Gaps corrected using L2 minimization– Outlier rejection
• Robust function downweights outlier vectors• Threshold reprojection error to remove outlier measurements
![Page 18: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/18.jpg)
Initialization
Good Period
![Page 19: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/19.jpg)
Tamas’ Iterative and Robust gap-filling (MATLAB)
![Page 20: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/20.jpg)
Smooth / Original
![Page 21: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/21.jpg)
Original and Ratio
![Page 22: Life Under Your Feet Johns Hopkins University Computer Science Earth and Planetary Sciences](https://reader033.vdocument.in/reader033/viewer/2022042901/56814bc6550346895db89dd9/html5/thumbnails/22.jpg)
Moving forward
• Better way to model these correlations?– Use some of your methods
• How do we use correlations to redesign our data collection subsystem
– 2 phase operation– Periodically download from everyone (infrequent)– In between, download from representative locations– Use correlations to interpolate and present to scientists– Postpone downloading all data in bulk much later– Extend network lifetime