SlideShare a Scribd company logo
PUBLIC SECTOR
SUMMIT
WASHINGTON, DC
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR
SUMMIT
Increasing the Use and Value of Earth
Science Data and Information
Annie Burgess, PhD
Lab Director
ESIP
301009
Amanda Tan, PhD
Cloud Technology Lead
University of Washington
Matthew Bartos
PhD Candidate
University of Michigan
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Agenda
Earth science data challenges
ESIP: an Earth science data community
AWS research cloud credits at work
Real-time quality control for IoT data
Improving snow covered area measurements
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Scientists have the
opportunity to analyze
Tb/Pb scale data.
Earth science data volumes are increasing
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Management and analysis at scale
Cloud computing solves
many big-data management
challenges and enables
research acceleration.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
The technology exists
Community Maximises Data Impact
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Earth Science Information Partners (ESIP)
By the numbers:
120+ Member Orgs
1000 Active Participants
30+ Working Groups
Supported by:
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
ESIP Lab as a catalyst
Support and build
cross-disciplinary teams to
experiment with technology
Projects receive visibility and
rapid feedback from the Earth
science data community
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
AWS cloud credits for research
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Cloud computing across disciplines
It isn’t new that modelers are excited about BIG computers
We need cloud-savvy data stewards and scientists across all disciplines
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
AWS cloud credits for research at work
Real-time Sensor Testbed for Improved Provenance and Data Quality
https://github.com/ESIPFed/SensorDat
M. Daniels1, A. Botnick1, C. Scully-Allison2, S. Strachan2, M. Bartos3, R. Brown4
1 National Center for Atmospheric Research
2 Department of Computer Science, University of Nevada, Reno
3 Department of Civil and Environmental Engineering, University of Michigan
4 McMurdo Dry Valleys LTER and Sevilleta Field Station, University of New Mexico
Inferring detailed snow-covered areas for studying changes in ecosystems
from high-resolution CubeSat imagery
https://github.com/acannistra/planet-snowcover
N. Cristea1, A. Tan2, A. Cannistra3, and K. Pradhan3
1 Civil and Environmental Engineering and eScience Institute, University of Washington
2 eScience Institute and IT Research Computing, University of Washington
3 Department of Biology, University of Washington
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR
SUMMIT
Real-time Sensor Testbed for
Improved Provenance and Data
Quality
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Quality control for streaming IoT data
Challenge: Applied geoscientist need data that is timely and reliable
Quality controlled measurements that arrive too late are of little use
Approach: A real-time QAQC framework powered by AWS
‘Recipe’ documents describe operations to apply to data
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Specify training and test datasets for machine learning
Raw River Depth
Measurements
Transform raw measurements into useful data
Quality control recipes
Corrected Depth Measurements
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Rapid & reliable dissemination of data to
stakeholdersA static web map (Amazon Simple Storage
Service (Amazon S3)) provides geospatial
context for users.
QAQC’d data are written to InfluxDB and
visualized using Grafana (hosted on Amazon
Elastic Compute Cloud (Amazon EC2)).
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR
SUMMIT
Inferring detailed snow-covered
areas for studying changes in
ecosystems from high-resolution
CubeSat imagery
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
The Science
Changes in snow coverage threaten
montane biodiversity
Our interest
How is snow disappearance affecting
plant communities in the mountains?
What is needed?
High resolution (m-scale) snow cover
area masks
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Data sources
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Approach
Can we use Machine Learning
techniques to derive snow masks?
?
Derive Snow
Mask
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Methodology
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Workflow Architecture
https://github.com/acannistra/planet-snowcover
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Robosat
https://github.com/mapbox/robosat
• data preparation: creating a
dataset for training feature
extraction models (Slippy map)
• training and modeling:
segmentation models for
feature extraction in images -
convolutional neural networks
trained on pairs of images and
masks (PyTorch, GPU)
• post-processing: turning
segmentation results into
cleaned and simple geometries
Robosat: Machine learning pipeline for end-to-end feature
extraction from aerial and satellite imagery
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Preliminary results snow vs. no snow
Planet RGB
LiDAR-derived
snow mask
CNN prediction from
4-band Planet tile
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Planet RGB
LiDAR-derived
snow mask
CNN prediction from
4-band Planet tile
Preliminary results snow vs. no snow
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Planet RGB
LiDAR-derived
snow mask
CNN prediction from
4-band Planet tile
Preliminary results snow vs. lake
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Preserving configuration and training for
further use
1. All algorithms and code will be preserved in a Github repository
2. Training data and results will be maintained in publicly available Amazon S3
buckets (and eventually moved to Glacier)
3. Model setup, packages, and installation will be available as both a Docker
image and Amazon Machine Image (AMI)
4. ESIP will fund Amazon S3, Glacier, and storage of AMI for up to 3 years
(estimated cost of $1k/year)
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Next steps
2. Scaling
1. Further testing
a. Train forested and open areas separately
b. Analyze performance on sloped terrain (viewing angle effects)
c. Reduce bands to one visible and one NIR
d. Consider Amazon Sagemaker
a. Extend analysis to other sites with LiDAR data but different climate/snow conditions.
b. Regional and continental scales (Sierra Nevada data volume could increase to 12TB for one
snow season)
c. Other applications (albedo feedback, climate)
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Thank you!
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR
SUMMIT
Annie Burgess, PhD
esipfed.org | #ESIPFed
lab@esipfed.org
Amanda Tan, PhD
escience.washington.edu
amandach@uw.edu
Matt Bartos
cee.umich.edu
mdbartos@umich.edu
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR
SUMMIT
Please complete the
session survey.
!
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R
S U M M I T
Images Used
• Slide4:
https://www.nasa.gov/multimedia/imagegallery/image_feature_2393.html
• Slide5: https://www.weather.gov/news/180409-hurricanes
• Slide8: https://www.usgs.gov/media/images/a-geologist-remembers-
mount-st-helens-eruption-37-years-ago

More Related Content

Similar to Increasing the Use and Value of Earth Science Data and Information

Enabling Resilience Through the Cloud: AWS Disaster Response Program
Enabling Resilience Through the Cloud: AWS Disaster Response ProgramEnabling Resilience Through the Cloud: AWS Disaster Response Program
Enabling Resilience Through the Cloud: AWS Disaster Response Program
Amazon Web Services
 
Reimagine the Public Cloud Experience with AWS Governance@Scale
Reimagine the Public Cloud Experience with AWS Governance@ScaleReimagine the Public Cloud Experience with AWS Governance@Scale
Reimagine the Public Cloud Experience with AWS Governance@Scale
Amazon Web Services
 
Community Tools for Analysis of Earth Science Data in the Cloud
Community Tools for Analysis of Earth Science Data in the CloudCommunity Tools for Analysis of Earth Science Data in the Cloud
Community Tools for Analysis of Earth Science Data in the Cloud
Amazon Web Services
 
SpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
SpaceNet: Accelerating Machine Learning for Foundational Mapping ChallengesSpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
SpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
Amazon Web Services
 
Running Geospatial Workloads on AWS - AWS Summit Sydney
Running Geospatial Workloads on AWS - AWS Summit SydneyRunning Geospatial Workloads on AWS - AWS Summit Sydney
Running Geospatial Workloads on AWS - AWS Summit Sydney
Amazon Web Services
 
Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
 Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight... Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
Amazon Web Services
 
Speeding Up Scientific Computation in Astrophysics with Amazon Web Services
Speeding Up Scientific Computation in Astrophysics with Amazon Web ServicesSpeeding Up Scientific Computation in Astrophysics with Amazon Web Services
Speeding Up Scientific Computation in Astrophysics with Amazon Web Services
Amazon Web Services
 
Working with Open Data in the Cloud
Working with Open Data in the CloudWorking with Open Data in the Cloud
Working with Open Data in the Cloud
Amazon Web Services
 
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
Amazon Web Services
 
Seeing the Stars Through the Cloud
Seeing the Stars Through the CloudSeeing the Stars Through the Cloud
Seeing the Stars Through the Cloud
Amazon Web Services
 
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
Amazon Web Services
 
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
Amazon Web Services
 
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
Amazon Web Services
 
A Tale of Two IT Modernization Strategies
A Tale of Two IT Modernization StrategiesA Tale of Two IT Modernization Strategies
A Tale of Two IT Modernization Strategies
Amazon Web Services
 
Optimize deep learning training and inferencing using GPU and Amazon SageMake...
Optimize deep learning training and inferencing using GPU and Amazon SageMake...Optimize deep learning training and inferencing using GPU and Amazon SageMake...
Optimize deep learning training and inferencing using GPU and Amazon SageMake...
Amazon Web Services
 
Creating Serverless apps for NASA in GovCloud
Creating Serverless apps for NASA in GovCloudCreating Serverless apps for NASA in GovCloud
Creating Serverless apps for NASA in GovCloud
Chris Shenton
 
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake FormationSecure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
Amazon Web Services
 
Snowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
Snowball Edge  Bringing Disconnected Cloud Capabilities to the EdgeSnowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
Snowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
Amazon Web Services
 
From Australia to Africa - A Digital Earth Journey
From Australia to Africa - A Digital Earth JourneyFrom Australia to Africa - A Digital Earth Journey
From Australia to Africa - A Digital Earth Journey
Amazon Web Services
 
Modernizing Your Application Development Environment with a Move to the Cloud
 Modernizing Your Application Development Environment with a Move to the Cloud Modernizing Your Application Development Environment with a Move to the Cloud
Modernizing Your Application Development Environment with a Move to the Cloud
Amazon Web Services
 

Similar to Increasing the Use and Value of Earth Science Data and Information (20)

Enabling Resilience Through the Cloud: AWS Disaster Response Program
Enabling Resilience Through the Cloud: AWS Disaster Response ProgramEnabling Resilience Through the Cloud: AWS Disaster Response Program
Enabling Resilience Through the Cloud: AWS Disaster Response Program
 
Reimagine the Public Cloud Experience with AWS Governance@Scale
Reimagine the Public Cloud Experience with AWS Governance@ScaleReimagine the Public Cloud Experience with AWS Governance@Scale
Reimagine the Public Cloud Experience with AWS Governance@Scale
 
Community Tools for Analysis of Earth Science Data in the Cloud
Community Tools for Analysis of Earth Science Data in the CloudCommunity Tools for Analysis of Earth Science Data in the Cloud
Community Tools for Analysis of Earth Science Data in the Cloud
 
SpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
SpaceNet: Accelerating Machine Learning for Foundational Mapping ChallengesSpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
SpaceNet: Accelerating Machine Learning for Foundational Mapping Challenges
 
Running Geospatial Workloads on AWS - AWS Summit Sydney
Running Geospatial Workloads on AWS - AWS Summit SydneyRunning Geospatial Workloads on AWS - AWS Summit Sydney
Running Geospatial Workloads on AWS - AWS Summit Sydney
 
Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
 Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight... Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
Networking Patterns and Practices: A Case Study of NASA Goddard Space Flight...
 
Speeding Up Scientific Computation in Astrophysics with Amazon Web Services
Speeding Up Scientific Computation in Astrophysics with Amazon Web ServicesSpeeding Up Scientific Computation in Astrophysics with Amazon Web Services
Speeding Up Scientific Computation in Astrophysics with Amazon Web Services
 
Working with Open Data in the Cloud
Working with Open Data in the CloudWorking with Open Data in the Cloud
Working with Open Data in the Cloud
 
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
Iowa Department of Public Health: Bringing a Data Platform Back to Life Throu...
 
Seeing the Stars Through the Cloud
Seeing the Stars Through the CloudSeeing the Stars Through the Cloud
Seeing the Stars Through the Cloud
 
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
Leveraging Earth Observations and Cloud Technology for Global Sustainable Dev...
 
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
Lessons from WuXi NextCODE Scales Up To Accelerate Data Sequencing in Their D...
 
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
Best Practices for Innovation in Public Sector: A Fireside Chat with Innovati...
 
A Tale of Two IT Modernization Strategies
A Tale of Two IT Modernization StrategiesA Tale of Two IT Modernization Strategies
A Tale of Two IT Modernization Strategies
 
Optimize deep learning training and inferencing using GPU and Amazon SageMake...
Optimize deep learning training and inferencing using GPU and Amazon SageMake...Optimize deep learning training and inferencing using GPU and Amazon SageMake...
Optimize deep learning training and inferencing using GPU and Amazon SageMake...
 
Creating Serverless apps for NASA in GovCloud
Creating Serverless apps for NASA in GovCloudCreating Serverless apps for NASA in GovCloud
Creating Serverless apps for NASA in GovCloud
 
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake FormationSecure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
Secure, Build and Deduplicate Your Data Lake Data with Amazon Lake Formation
 
Snowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
Snowball Edge  Bringing Disconnected Cloud Capabilities to the EdgeSnowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
Snowball Edge  Bringing Disconnected Cloud Capabilities to the Edge
 
From Australia to Africa - A Digital Earth Journey
From Australia to Africa - A Digital Earth JourneyFrom Australia to Africa - A Digital Earth Journey
From Australia to Africa - A Digital Earth Journey
 
Modernizing Your Application Development Environment with a Move to the Cloud
 Modernizing Your Application Development Environment with a Move to the Cloud Modernizing Your Application Development Environment with a Move to the Cloud
Modernizing Your Application Development Environment with a Move to the Cloud
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
Amazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
Amazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
Amazon Web Services
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Amazon Web Services
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
Amazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
Amazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Amazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
Amazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Amazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
Amazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Increasing the Use and Value of Earth Science Data and Information

  • 2. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR SUMMIT Increasing the Use and Value of Earth Science Data and Information Annie Burgess, PhD Lab Director ESIP 301009 Amanda Tan, PhD Cloud Technology Lead University of Washington Matthew Bartos PhD Candidate University of Michigan
  • 3. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Agenda Earth science data challenges ESIP: an Earth science data community AWS research cloud credits at work Real-time quality control for IoT data Improving snow covered area measurements
  • 4. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Scientists have the opportunity to analyze Tb/Pb scale data. Earth science data volumes are increasing
  • 5. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Management and analysis at scale Cloud computing solves many big-data management challenges and enables research acceleration.
  • 6. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T The technology exists Community Maximises Data Impact
  • 7. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Earth Science Information Partners (ESIP) By the numbers: 120+ Member Orgs 1000 Active Participants 30+ Working Groups Supported by:
  • 8. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T ESIP Lab as a catalyst Support and build cross-disciplinary teams to experiment with technology Projects receive visibility and rapid feedback from the Earth science data community
  • 9. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T AWS cloud credits for research
  • 10. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Cloud computing across disciplines It isn’t new that modelers are excited about BIG computers We need cloud-savvy data stewards and scientists across all disciplines
  • 11. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T AWS cloud credits for research at work Real-time Sensor Testbed for Improved Provenance and Data Quality https://github.com/ESIPFed/SensorDat M. Daniels1, A. Botnick1, C. Scully-Allison2, S. Strachan2, M. Bartos3, R. Brown4 1 National Center for Atmospheric Research 2 Department of Computer Science, University of Nevada, Reno 3 Department of Civil and Environmental Engineering, University of Michigan 4 McMurdo Dry Valleys LTER and Sevilleta Field Station, University of New Mexico Inferring detailed snow-covered areas for studying changes in ecosystems from high-resolution CubeSat imagery https://github.com/acannistra/planet-snowcover N. Cristea1, A. Tan2, A. Cannistra3, and K. Pradhan3 1 Civil and Environmental Engineering and eScience Institute, University of Washington 2 eScience Institute and IT Research Computing, University of Washington 3 Department of Biology, University of Washington
  • 12. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR SUMMIT Real-time Sensor Testbed for Improved Provenance and Data Quality
  • 13. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T
  • 14. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Quality control for streaming IoT data Challenge: Applied geoscientist need data that is timely and reliable Quality controlled measurements that arrive too late are of little use Approach: A real-time QAQC framework powered by AWS ‘Recipe’ documents describe operations to apply to data
  • 15. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Specify training and test datasets for machine learning Raw River Depth Measurements Transform raw measurements into useful data Quality control recipes Corrected Depth Measurements
  • 16. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Rapid & reliable dissemination of data to stakeholdersA static web map (Amazon Simple Storage Service (Amazon S3)) provides geospatial context for users. QAQC’d data are written to InfluxDB and visualized using Grafana (hosted on Amazon Elastic Compute Cloud (Amazon EC2)).
  • 17. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR SUMMIT Inferring detailed snow-covered areas for studying changes in ecosystems from high-resolution CubeSat imagery
  • 18. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T The Science Changes in snow coverage threaten montane biodiversity Our interest How is snow disappearance affecting plant communities in the mountains? What is needed? High resolution (m-scale) snow cover area masks
  • 19. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Data sources
  • 20. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Approach Can we use Machine Learning techniques to derive snow masks? ? Derive Snow Mask
  • 21. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Methodology
  • 22. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Workflow Architecture https://github.com/acannistra/planet-snowcover
  • 23. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Robosat https://github.com/mapbox/robosat • data preparation: creating a dataset for training feature extraction models (Slippy map) • training and modeling: segmentation models for feature extraction in images - convolutional neural networks trained on pairs of images and masks (PyTorch, GPU) • post-processing: turning segmentation results into cleaned and simple geometries Robosat: Machine learning pipeline for end-to-end feature extraction from aerial and satellite imagery
  • 24. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Preliminary results snow vs. no snow Planet RGB LiDAR-derived snow mask CNN prediction from 4-band Planet tile
  • 25. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Planet RGB LiDAR-derived snow mask CNN prediction from 4-band Planet tile Preliminary results snow vs. no snow
  • 26. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Planet RGB LiDAR-derived snow mask CNN prediction from 4-band Planet tile Preliminary results snow vs. lake
  • 27. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Preserving configuration and training for further use 1. All algorithms and code will be preserved in a Github repository 2. Training data and results will be maintained in publicly available Amazon S3 buckets (and eventually moved to Glacier) 3. Model setup, packages, and installation will be available as both a Docker image and Amazon Machine Image (AMI) 4. ESIP will fund Amazon S3, Glacier, and storage of AMI for up to 3 years (estimated cost of $1k/year)
  • 28. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Next steps 2. Scaling 1. Further testing a. Train forested and open areas separately b. Analyze performance on sloped terrain (viewing angle effects) c. Reduce bands to one visible and one NIR d. Consider Amazon Sagemaker a. Extend analysis to other sites with LiDAR data but different climate/snow conditions. b. Regional and continental scales (Sierra Nevada data volume could increase to 12TB for one snow season) c. Other applications (albedo feedback, climate)
  • 29. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T
  • 30. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Thank you! © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR SUMMIT Annie Burgess, PhD esipfed.org | #ESIPFed lab@esipfed.org Amanda Tan, PhD escience.washington.edu amandach@uw.edu Matt Bartos cee.umich.edu mdbartos@umich.edu
  • 31. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.PUBLIC SECTOR SUMMIT Please complete the session survey. !
  • 32. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C TO R S U M M I T Images Used • Slide4: https://www.nasa.gov/multimedia/imagegallery/image_feature_2393.html • Slide5: https://www.weather.gov/news/180409-hurricanes • Slide8: https://www.usgs.gov/media/images/a-geologist-remembers- mount-st-helens-eruption-37-years-ago