SlideShare a Scribd company logo
1 of 41
Team Omniscient
Original Problem
DCGS operators need an automated way to review
a larger quantity of collected imaging data in order
to surface actionable intelligence to leadership.
Sponsor Organization: US Air Force Tactical Exploitation of National Capabilities (AF TENCAP)
108
Interviews
Supported By: Maj Rose (Sponsor), COL Smith-Heys (Military Mentor), Kevin Ray (Business Mentor), Gus Hernandez
(Advisor)
Final Problem
Analysts lack the computer vision tools to augment
their ability to rapidly locate, identify, and analyze
objects of interest, which would allow them to
focus their time on higher order analysis tasks.
Nick Mirda | GSB ‘21
Prior Army Intelligence
Officer
Summer: BCG
Jon Braatz | MS CS ‘20
Computer Vision
Research
Summer: !
Andrew Fang | BS CS ‘22
Computer Vision
Products
Summer: Anduril
90+% of images never reviewed!
There’s too much data!
KEY PARTNERS
We will liaison with two
DCGS (Distributed Common
Ground/Surface System)
centers, located at Langley
AFB and Beale AFB
Other Potential Partners:
- Intelligence Analysts
- USAF Weapons School
- DARPA
- KesselRun
- Air Force Research Lab
- Sandia National Labs
- MIT Lincoln Lab
- DIU
- NASIC
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: the usability and
accuracy of our model on data provided by the Air Force
● Our beneficiaries will measure mission achievement by: the
adoption/ease-of-use for analysts whose jobs we will simplify
and ability to surface exploitable info in collected data.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time)
● Potential costs for proprietary software
BENEFICIARIES
1. Operators:
Intelligence
analysts who parse
through images
(NASIC, CENTCOM,
etc)
2. Decision Makers:
High level decision
makers who need
actionable
intelligence quickly
and efficiently
1. Narrow problem space
2. Access Data
3. Build model by
augmenting
YOLO/existing models
4. Test model
1. Analysts who manually
identify actionable intel
(to provide insight on
what is considered
valuable data + provide
robustly labeled data)
2. AWS/Azure for training
3. Lots of data
1. Workload Reduction:
Reduce human hours
currently spent on
identifying actionable
information in images
1. Decrease Intelligence
Processing Timeline:
Capture information
from images faster
than a human analyst
1. Reduce Data
Backlogs: Parse
image database
backlogs to surface
exploitable images
1. End Users: Analysts who
parse through images of
AF pilots who are willing
to test our software
2. Leadership: Budget
authority and operational
policy experts
1. Initial deployment:
command line service
2. Future deployments:
product with a
UI/clear instructions
for analysts
Mission Model Canvas: initial expectations
KEY PARTNERS
We will liaison with two
DCGS (Distributed Common
Ground/Surface System)
centers, located at Langley
AFB and Beale AFB
Other Potential Partners:
- Intelligence Analysts
- USAF Weapons School
- DARPA
- KesselRun
- Air Force Research Lab
- Sandia National Labs
- MIT Lincoln Lab
- DIU
- NASIC
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: the usability and
accuracy of our model on data provided by the Air Force
● Our beneficiaries will measure mission achievement by: the
adoption/ease-of-use for analysts whose jobs we will simplify
and ability to surface exploitable info in collected data.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time)
● Potential costs for proprietary software
BENEFICIARIES
1. Operators:
Intelligence
analysts who parse
through images
(NASIC, CENTCOM,
etc)
2. Decision Makers:
High level decision
makers who need
actionable
intelligence quickly
and efficiently
1. Narrow problem space
2. Access Data
3. Build model by
augmenting
YOLO/existing models
4. Test model
1. Analysts who manually
identify actionable intel
(to provide insight on
what is considered
valuable data + provide
robustly labeled data)
2. AWS/Azure for training
3. Lots of data
1. Workload Reduction:
Reduce human hours
currently spent on
identifying actionable
information in images
1. Decrease Intelligence
Processing Timeline:
Capture information
from images faster
than a human analyst
1. Reduce Data
Backlogs: Parse
image database
backlogs to surface
exploitable images
1. End Users: Analysts who
parse through images of
AF pilots who are willing
to test our software
2. Leadership: Budget
authority and operational
policy experts
1. Initial deployment:
command line service
2. Future deployments:
product with a
UI/clear instructions
for analysts
Mission Model Canvas: initial expectations
Initial Thoughts:
1. Help analysts look for
“needles in haystacks”
KEY PARTNERS
We will liaison with two
DCGS (Distributed Common
Ground/Surface System)
centers, located at Langley
AFB and Beale AFB
Other Potential Partners:
- Intelligence Analysts
- USAF Weapons School
- DARPA
- KesselRun
- Air Force Research Lab
- Sandia National Labs
- MIT Lincoln Lab
- DIU
- NASIC
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: the usability and
accuracy of our model on data provided by the Air Force
● Our beneficiaries will measure mission achievement by: the
adoption/ease-of-use for analysts whose jobs we will simplify
and ability to surface exploitable info in collected data.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time)
● Potential costs for proprietary software
BENEFICIARIES
1. Operators:
Intelligence
analysts who parse
through images
(NASIC, CENTCOM,
etc)
2. Decision Makers:
High level decision
makers who need
actionable
intelligence quickly
and efficiently
1. Narrow problem space
2. Access Data
3. Build model by
augmenting
YOLO/existing models
4. Test model
1. Analysts who manually
identify actionable intel
(to provide insight on
what is considered
valuable data + provide
robustly labeled data)
2. AWS/Azure for training
3. Lots of data
1. Workload Reduction:
Reduce human hours
currently spent on
identifying actionable
information in images
1. Decrease Intelligence
Processing Timeline:
Capture information
from images faster
than a human analyst
1. Reduce Data
Backlogs: Parse
image database
backlogs to surface
exploitable images
1. End Users: Analysts who
parse through images of
AF pilots who are willing
to test our software
2. Leadership: Budget
authority and operational
policy experts
1. Initial deployment:
command line service
2. Future deployments:
product with a
UI/clear instructions
for analysts
Mission Model Canvas: initial expectations
Initial Thoughts:
1. Help analysts look for
“needles in haystacks”
2. What do those
“needles” look like?
KEY PARTNERS
We will liaison with two
DCGS (Distributed Common
Ground/Surface System)
centers, located at Langley
AFB and Beale AFB
Other Potential Partners:
- Intelligence Analysts
- USAF Weapons School
- DARPA
- KesselRun
- Air Force Research Lab
- Sandia National Labs
- MIT Lincoln Lab
- DIU
- NASIC
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: the usability and
accuracy of our model on data provided by the Air Force
● Our beneficiaries will measure mission achievement by: the
adoption/ease-of-use for analysts whose jobs we will simplify
and ability to surface exploitable info in collected data.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time)
● Potential costs for proprietary software
BENEFICIARIES
1. Operators:
Intelligence
analysts who parse
through images
(NASIC, CENTCOM,
etc)
2. Decision Makers:
High level decision
makers who need
actionable
intelligence quickly
and efficiently
1. Narrow problem space
2. Access Data
3. Build model by
augmenting
YOLO/existing models
4. Test model
1. Analysts who manually
identify actionable intel
(to provide insight on
what is considered
valuable data + provide
robustly labeled data)
2. AWS/Azure for training
3. Lots of data
1. Workload Reduction:
Reduce human hours
currently spent on
identifying actionable
information in images
1. Decrease Intelligence
Processing Timeline:
Capture information
from images faster
than a human analyst
1. Reduce Data
Backlogs: Parse
image database
backlogs to surface
exploitable images
1. End Users: Analysts who
parse through images of
AF pilots who are willing
to test our software
2. Leadership: Budget
authority and operational
policy experts
1. Initial deployment:
command line service
2. Future deployments:
product with a
UI/clear instructions
for analysts
Mission Model Canvas: initial expectations
Initial Thoughts:
1. Help analysts look for
“needles in haystacks”
2. What do those
“needles” look like?
3. Get our hands on
imagery data to build
a solution
BENEFICIARIES BUYERS PARTNERS
We interviewed 108 people all holding a
different piece of the puzzle.
EXPERTS
How we’re feeling: we got this!
Everyone we talked to had a different problem.
Detect Changes
We were overwhelmed.
Everyone we talked to had a different problem.
Image Clarity Rating
(NIIRS)
Detect Changes
We were overwhelmed.
Everyone we talked to had a different problem.
Image Clarity Rating
(NIIRS)
North Korean MissilesDetect Changes
We were overwhelmed.
Everyone we talked to had a different problem.
Full-Motion Video
(Maven)
Image Clarity Rating
(NIIRS)
North Korean MissilesDetect Changes
We were overwhelmed.
Everyone we talked to had a different problem.
Full-Motion Video
(Maven)
Image Clarity Rating
(NIIRS)
North Korean MissilesDetect Changes
And there were a lot of imagery options.
We were overwhelmed.
Crisis!
We lost two teammates!
How we’re feeling: yikes
Air Force is shifting to higher level analysis.
Imagery Analysis
● Recording object position
● Annotating observations
Imagery Understanding
● Situational analysis
● Deep understanding
“Instead of counting objects that can be automatically detected, my analysts
can ask why those vehicles are there, really unleashes analytic horsepower.”
-Director of Operations @ 13th Intel Squadron
Machine learning can automate the drudge work.
● Tracking all aircraft in flight (NRO).
○ Unsuccessful.
● Project Maven: automatic full-motion video analysis.
○ Mixed results.
● Automatic airfield layout change detection (NGA).
○ Ongoing.
● Identify groupings of tanks (NGA).
○ Ongoing.
Previous efforts stumbled due to overambitious goals and improperly labelled data.
Many DoD programs to automate imagery
analysis, but most are still work-in-progress.
?
?
?
First MVP: a generic computer vision tool.
● it processes analyst imagery to detect objects.
● it runs in the background.
● it uses computer vision.
Feedback:
1) “I’ve heard this dozens of times.”
2) “I care less about innovation, more about
integration.”
We need a specific use case & a way to get in.
A bad pivot: we jumped on the first computer vision
solution we saw (computer vision to help bandwidth).
• We thought RQ-4 Global Hawks had significant bandwidth limitations that
hampered SAR imagery delivery to the base, after speaking with a pilot.
We pivoted too early, deviated from beneficiary insights, and
were invalidated with further interviews.
How we’re feeling: demoralized :/
Breakthrough!
Insight: The AN-2 is a proxy for what our
solution can deliver.
● This is a discrete, strategically relevant problem we
can sink our teeth into
● If we can track these, we expand to tracking other
equipment
● it’s not easy, but we think we could build it.
How do we get in? How do we execute?
3 meter resolution 50 centimeter resolution
Our algorithms would require a lot of good data.
We scraped a few thousand images. For free!
Taechon Airfield AN-2
Image #B4993
Date: 05MAY2020
Asset Quantity: 9
Asset Coordinates:
1. 51SYE1354920036
2. 51SYE1347120046
...
9. 51SYE1319020263c
First validated MVP automates AN-2 detection &
feeds into analyst workflow. .KML Outputs
KEY PARTNERS
Air Force DGS-3 AETs that
will be our customers/users.
Commercial satellite imagery
companies to acquire data to
train on. (Maxar, Planet).
Innovation and Research
organizations to accelerate
classified data/system access.
(DIU, CRADA, SBIR).
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: accuracy of AN-2
classifications from still imagery and anomaly alerts.
● Our beneficiaries will measure mission achievement by: the ability
to identify meaningful activity/objects of interest from large data
sets and adoption/ease-of-use for analysts.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time).
● Unclassified EO data/labels from commercial companies.
● Potential costs for proprietary software.
BENEFICIARIES
1. Operators: DGS-3
AET Analysts (Phase
1), ISR Pilots, Sensor
Operators, Collection
Managers
1. Decision Makers: US
Forces and Korea
leadership need
actionable intel fast.
1. Analysts who manually
analyze still imagery (to
provide insight on what is
data + provide robustly
labeled data).
2. Lots of commercial
satellite data (Maxar).
1. Decrease AN-2 Imagery
Process Time: Quickly
scan large images to
extract quantity/location
of assets of interest.
1. Get AN-2 Anomalies to
Analysts/Leaders Fast:
Alert analysts to enable
them to verify suspicious
activity ASAP.
1. Up-to-Date AN-2
Activity/Locations:
Know where all AN-2s
are and what they do
with reliable information.
1. End Users: Imagery
analysts & AETs at DGS-3.
1. Leadership: DGS-3
Collections Managers,
Combatant Commanders
setting ISR priorities.
1. Image Processing on
unclass computer.
2. Future deployments:
plugin for existing
analysis software
3. Continuously-running
anomaly notification
System
1. Access commercial
satellite data of NK
airfields.
2. Build and test model
on unclassified satellite
imagery.
3. Identify integration
pathway.
Mission Model Canvas: use case identified!
Allowed us to:
1. Articulate specific
value proposition
KEY PARTNERS
Air Force DGS-3 AETs that
will be our customers/users.
Commercial satellite imagery
companies to acquire data to
train on. (Maxar, Planet).
Innovation and Research
organizations to accelerate
classified data/system access.
(DIU, CRADA, SBIR).
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: accuracy of AN-2
classifications from still imagery and anomaly alerts.
● Our beneficiaries will measure mission achievement by: the ability
to identify meaningful activity/objects of interest from large data
sets and adoption/ease-of-use for analysts.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time).
● Unclassified EO data/labels from commercial companies.
● Potential costs for proprietary software.
BENEFICIARIES
1. Operators: DGS-3
AET Analysts (Phase
1), ISR Pilots, Sensor
Operators, Collection
Managers
1. Decision Makers: US
Forces and Korea
leadership need
actionable intel fast.
1. Analysts who manually
analyze still imagery (to
provide insight on what is
data + provide robustly
labeled data).
2. Lots of commercial
satellite data (Maxar).
1. Decrease AN-2 Imagery
Process Time: Quickly
scan large images to
extract quantity/location
of assets of interest.
1. Get AN-2 Anomalies to
Analysts/Leaders Fast:
Alert analysts to enable
them to verify suspicious
activity ASAP.
1. Up-to-Date AN-2
Activity/Locations:
Know where all AN-2s
are and what they do
with reliable information.
1. End Users: Imagery
analysts & AETs at DGS-3.
1. Leadership: DGS-3
Collections Managers,
Combatant Commanders
setting ISR priorities.
1. Image Processing on
unclass computer.
2. Future deployments:
plugin for existing
analysis software
3. Continuously-running
anomaly notification
System
1. Access commercial
satellite data of NK
airfields.
2. Build and test model
on unclassified satellite
imagery.
3. Identify integration
pathway.
Mission Model Canvas: use case identified!
Allowed us to:
1. Articulate specific
value proposition
2. Focus on the
appropriate end users
KEY PARTNERS
Air Force DGS-3 AETs that
will be our customers/users.
Commercial satellite imagery
companies to acquire data to
train on. (Maxar, Planet).
Innovation and Research
organizations to accelerate
classified data/system access.
(DIU, CRADA, SBIR).
KEY RESOURCES
VALUE PROPOSITIONSKEY ACTIVITIES
MISSION ACHIEVEMENT/IMPACT FACTORS
● We will measure mission achievement by: accuracy of AN-2
classifications from still imagery and anomaly alerts.
● Our beneficiaries will measure mission achievement by: the ability
to identify meaningful activity/objects of interest from large data
sets and adoption/ease-of-use for analysts.
DEPLOYMENT
BUY-IN & SUPPORT
MISSION BUDGET/COST
● Budget for training costs (AWS/Azure GPU time).
● Unclassified EO data/labels from commercial companies.
● Potential costs for proprietary software.
BENEFICIARIES
1. Operators: DGS-3
AET Analysts (Phase
1), ISR Pilots, Sensor
Operators, Collection
Managers
1. Decision Makers: US
Forces and Korea
leadership need
actionable intel fast.
1. Analysts who manually
analyze still imagery (to
provide insight on what is
data + provide robustly
labeled data).
2. Lots of commercial
satellite data (Maxar).
1. Decrease AN-2 Imagery
Process Time: Quickly
scan large images to
extract quantity/location
of assets of interest.
1. Get AN-2 Anomalies to
Analysts/Leaders Fast:
Alert analysts to enable
them to verify suspicious
activity ASAP.
1. Up-to-Date AN-2
Activity/Locations:
Know where all AN-2s
are and what they do
with reliable information.
1. End Users: Imagery
analysts & AETs at DGS-3.
1. Leadership: DGS-3
Collections Managers,
Combatant Commanders
setting ISR priorities.
1. Image Processing on
unclass computer.
2. Future deployments:
plugin for existing
analysis software
3. Continuously-running
anomaly notification
System
1. Access commercial
satellite data of NK
airfields.
2. Build and test model
on unclassified satellite
imagery.
3. Identify integration
pathway.
Mission Model Canvas: use case identified!
Allowed us to:
1. Articulate specific
value proposition
2. Focus on the
appropriate end users
3. Outline a specific
integration pathway
How we’re feeling: Yes! On the right track!
Unclassified
Satellite Imagery
NIPRnet (Unclassified)
Unclassified Tool, Integrates with Classified Systems
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
.KML
Output Files
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
Date
Location
Quantity
SIPRnet (Classified)
.KML
Output Files
Data Uploaded
to SIPRnet
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
Date
Location
Quantity
SIPRnet (Classified)
.KML
Output Files
.KMLs
Uploaded
Data Uploaded
to SIPRnet
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
Data integrates with analyst tools
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
Date
Location
Quantity
SIPRnet (Classified)
.KML
Output Files
.KMLs
Uploaded
Data Uploaded
to SIPRnet
Unclassified
Satellite Imagery
Entity
Detection
Algorithms
Data integrates with analyst tools
Intel products
are built more
quickly and
effectively.
NIPRnet (Unclassified)
Unclassified Integration into Existing Analyst Workflow
Historical
Baseline
Comparison
Date
Location
Quantity
SIPRnet (Classified)
.KML
Output Files
.KMLs
Uploaded
Credibility:
Computer Vision:
Working Towards
Unofficial Demo
with Air Combat
Command
(In 2-3 Weeks)
TENCAP
Mentorship
to TENCAP Letter
of Endorsement
Help us build omniscience.
MILITARY: Collaboration- how can we help you?
PRIMEs: Platforms and Partnerships- how can we work together?
NEXT STEPS:
COMMERCIAL: Dual use | Venture Funding- let’s chat!
Email: hello@omniscientlabs.io
$20k | Now $50k | 6 Months
Working over summer:
● Develop AN-2 algorithms
● Scope out dual use
applications

More Related Content

What's hot

Data Stewards – Defining and Assigning
Data Stewards – Defining and AssigningData Stewards – Defining and Assigning
Data Stewards – Defining and AssigningDATAVERSITY
 
Being a Data Driven Business
Being a Data Driven Business Being a Data Driven Business
Being a Data Driven Business Ali Sarrafi
 
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...Seeling Cheung
 
Owning Your Own (Data) Lake House
Owning Your Own (Data) Lake HouseOwning Your Own (Data) Lake House
Owning Your Own (Data) Lake HouseData Con LA
 
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...HostedbyConfluent
 
Large Scale Lakehouse Implementation Using Structured Streaming
Large Scale Lakehouse Implementation Using Structured StreamingLarge Scale Lakehouse Implementation Using Structured Streaming
Large Scale Lakehouse Implementation Using Structured StreamingDatabricks
 
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...DATAVERSITY
 
Let’s get to know Snowflake
Let’s get to know SnowflakeLet’s get to know Snowflake
Let’s get to know SnowflakeKnoldus Inc.
 
ApacheCon Europe Big Data 2016 – Parquet in practice & detail
ApacheCon Europe Big Data 2016 – Parquet in practice & detailApacheCon Europe Big Data 2016 – Parquet in practice & detail
ApacheCon Europe Big Data 2016 – Parquet in practice & detailUwe Korn
 
Data Loss Prevention from Symantec
Data Loss Prevention from SymantecData Loss Prevention from Symantec
Data Loss Prevention from SymantecArrow ECS UK
 
Hyperspace for Delta Lake
Hyperspace for Delta LakeHyperspace for Delta Lake
Hyperspace for Delta LakeDatabricks
 
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDatabricks
 
Sentry - An Introduction
Sentry - An Introduction Sentry - An Introduction
Sentry - An Introduction Alexander Alten
 
Change Data Feed in Delta
Change Data Feed in DeltaChange Data Feed in Delta
Change Data Feed in DeltaDatabricks
 
Data governance Program PowerPoint Presentation Slides
Data governance Program PowerPoint Presentation Slides Data governance Program PowerPoint Presentation Slides
Data governance Program PowerPoint Presentation Slides SlideTeam
 
Modernizing to a Cloud Data Architecture
Modernizing to a Cloud Data ArchitectureModernizing to a Cloud Data Architecture
Modernizing to a Cloud Data ArchitectureDatabricks
 
DataOps: Nine steps to transform your data science impact Strata London May 18
DataOps: Nine steps to transform your data science impact  Strata London May 18DataOps: Nine steps to transform your data science impact  Strata London May 18
DataOps: Nine steps to transform your data science impact Strata London May 18Harvinder Atwal
 

What's hot (20)

Data Stewards – Defining and Assigning
Data Stewards – Defining and AssigningData Stewards – Defining and Assigning
Data Stewards – Defining and Assigning
 
Being a Data Driven Business
Being a Data Driven Business Being a Data Driven Business
Being a Data Driven Business
 
Big data architectures
Big data architecturesBig data architectures
Big data architectures
 
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...
Citizens Bank: Data Lake Implementation – Selecting BigInsights ViON Spark/Ha...
 
Owning Your Own (Data) Lake House
Owning Your Own (Data) Lake HouseOwning Your Own (Data) Lake House
Owning Your Own (Data) Lake House
 
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...
Apache Kafka With Spark Structured Streaming With Emma Liu, Nitin Saksena, Ra...
 
Large Scale Lakehouse Implementation Using Structured Streaming
Large Scale Lakehouse Implementation Using Structured StreamingLarge Scale Lakehouse Implementation Using Structured Streaming
Large Scale Lakehouse Implementation Using Structured Streaming
 
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...
Keeping the Pulse of Your Data – Why You Need Data Observability to Improve D...
 
Let’s get to know Snowflake
Let’s get to know SnowflakeLet’s get to know Snowflake
Let’s get to know Snowflake
 
How to build a successful Data Lake
How to build a successful Data LakeHow to build a successful Data Lake
How to build a successful Data Lake
 
ApacheCon Europe Big Data 2016 – Parquet in practice & detail
ApacheCon Europe Big Data 2016 – Parquet in practice & detailApacheCon Europe Big Data 2016 – Parquet in practice & detail
ApacheCon Europe Big Data 2016 – Parquet in practice & detail
 
Data Loss Prevention from Symantec
Data Loss Prevention from SymantecData Loss Prevention from Symantec
Data Loss Prevention from Symantec
 
data warehouse vs data lake
data warehouse vs data lakedata warehouse vs data lake
data warehouse vs data lake
 
Hyperspace for Delta Lake
Hyperspace for Delta LakeHyperspace for Delta Lake
Hyperspace for Delta Lake
 
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized Platform
 
Sentry - An Introduction
Sentry - An Introduction Sentry - An Introduction
Sentry - An Introduction
 
Change Data Feed in Delta
Change Data Feed in DeltaChange Data Feed in Delta
Change Data Feed in Delta
 
Data governance Program PowerPoint Presentation Slides
Data governance Program PowerPoint Presentation Slides Data governance Program PowerPoint Presentation Slides
Data governance Program PowerPoint Presentation Slides
 
Modernizing to a Cloud Data Architecture
Modernizing to a Cloud Data ArchitectureModernizing to a Cloud Data Architecture
Modernizing to a Cloud Data Architecture
 
DataOps: Nine steps to transform your data science impact Strata London May 18
DataOps: Nine steps to transform your data science impact  Strata London May 18DataOps: Nine steps to transform your data science impact  Strata London May 18
DataOps: Nine steps to transform your data science impact Strata London May 18
 

Similar to Omniscient H4D 2020 Lessons Learned

Sentinel week 1 H4D Stanford 2016
Sentinel week 1 H4D Stanford 2016Sentinel week 1 H4D Stanford 2016
Sentinel week 1 H4D Stanford 2016Stanford University
 
Sentinel Week 7 H4D Stanford 2016
Sentinel Week 7 H4D Stanford 2016Sentinel Week 7 H4D Stanford 2016
Sentinel Week 7 H4D Stanford 2016Stanford University
 
Sentinel Lessons Learned
Sentinel Lessons LearnedSentinel Lessons Learned
Sentinel Lessons LearnedH4Diadmin
 
Sentinel Lessons Learned H4D Stanford 2016
Sentinel Lessons Learned H4D Stanford 2016Sentinel Lessons Learned H4D Stanford 2016
Sentinel Lessons Learned H4D Stanford 2016Stanford University
 
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera, Inc.
 
Sentinel Week 2 H4D Stanford 2016
Sentinel Week 2 H4D Stanford 2016Sentinel Week 2 H4D Stanford 2016
Sentinel Week 2 H4D Stanford 2016Stanford University
 
TASK 1In regards to part 1 of this assessment, please read t.docx
TASK 1In regards to part 1 of this assessment, please read t.docxTASK 1In regards to part 1 of this assessment, please read t.docx
TASK 1In regards to part 1 of this assessment, please read t.docxmattinsonjanel
 
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...(Web User Interfaces track) "Getting the Query Right: User Interface Design o...
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...icwe2015
 
Technology Threat Prediction
Technology Threat PredictionTechnology Threat Prediction
Technology Threat PredictionH4Diadmin
 
A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4jmorriso
 
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...Dr. Haxel Consult
 
Skynet Final Presentation
Skynet Final PresentationSkynet Final Presentation
Skynet Final PresentationH4Diadmin
 
Skynet Lessons Learned H4D Stanford 2016
Skynet Lessons Learned H4D Stanford 2016Skynet Lessons Learned H4D Stanford 2016
Skynet Lessons Learned H4D Stanford 2016Stanford University
 
Machine Learning + Analytics in Splunk
Machine Learning + Analytics in Splunk Machine Learning + Analytics in Splunk
Machine Learning + Analytics in Splunk Splunk
 
C19013010 the tutorial to build shared ai services session 1
C19013010  the tutorial to build shared ai services session 1C19013010  the tutorial to build shared ai services session 1
C19013010 the tutorial to build shared ai services session 1Bill Liu
 
Pathways Overview For Open House 19 Sep2010
Pathways Overview For Open House   19 Sep2010Pathways Overview For Open House   19 Sep2010
Pathways Overview For Open House 19 Sep2010jmorriso
 
Next Century Project Overview
Next Century Project OverviewNext Century Project Overview
Next Century Project Overviewjennhunter
 
how to build a Length of Stay model for a ProofOfConcept project
how to build a Length of Stay model for a ProofOfConcept projecthow to build a Length of Stay model for a ProofOfConcept project
how to build a Length of Stay model for a ProofOfConcept projectZenodia Charpy
 

Similar to Omniscient H4D 2020 Lessons Learned (20)

Sentinel week 1 H4D Stanford 2016
Sentinel week 1 H4D Stanford 2016Sentinel week 1 H4D Stanford 2016
Sentinel week 1 H4D Stanford 2016
 
Sentinel Week 7 H4D Stanford 2016
Sentinel Week 7 H4D Stanford 2016Sentinel Week 7 H4D Stanford 2016
Sentinel Week 7 H4D Stanford 2016
 
Sentinel Lessons Learned
Sentinel Lessons LearnedSentinel Lessons Learned
Sentinel Lessons Learned
 
Sentinel Lessons Learned H4D Stanford 2016
Sentinel Lessons Learned H4D Stanford 2016Sentinel Lessons Learned H4D Stanford 2016
Sentinel Lessons Learned H4D Stanford 2016
 
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
 
NASA Data Science Day Plenary: Applied Machine Learning (ML)
NASA Data Science Day Plenary: Applied Machine Learning (ML)NASA Data Science Day Plenary: Applied Machine Learning (ML)
NASA Data Science Day Plenary: Applied Machine Learning (ML)
 
Softwareproject planning
Softwareproject planningSoftwareproject planning
Softwareproject planning
 
Sentinel Week 2 H4D Stanford 2016
Sentinel Week 2 H4D Stanford 2016Sentinel Week 2 H4D Stanford 2016
Sentinel Week 2 H4D Stanford 2016
 
TASK 1In regards to part 1 of this assessment, please read t.docx
TASK 1In regards to part 1 of this assessment, please read t.docxTASK 1In regards to part 1 of this assessment, please read t.docx
TASK 1In regards to part 1 of this assessment, please read t.docx
 
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...(Web User Interfaces track) "Getting the Query Right: User Interface Design o...
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...
 
Technology Threat Prediction
Technology Threat PredictionTechnology Threat Prediction
Technology Threat Prediction
 
A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4A Space X Industry Day Briefing 7 Jul08 Jgm R4
A Space X Industry Day Briefing 7 Jul08 Jgm R4
 
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...
II-SDV 2014 Search and Data Mining Open Source Platforms (Patrick Beaucamp - ...
 
Skynet Final Presentation
Skynet Final PresentationSkynet Final Presentation
Skynet Final Presentation
 
Skynet Lessons Learned H4D Stanford 2016
Skynet Lessons Learned H4D Stanford 2016Skynet Lessons Learned H4D Stanford 2016
Skynet Lessons Learned H4D Stanford 2016
 
Machine Learning + Analytics in Splunk
Machine Learning + Analytics in Splunk Machine Learning + Analytics in Splunk
Machine Learning + Analytics in Splunk
 
C19013010 the tutorial to build shared ai services session 1
C19013010  the tutorial to build shared ai services session 1C19013010  the tutorial to build shared ai services session 1
C19013010 the tutorial to build shared ai services session 1
 
Pathways Overview For Open House 19 Sep2010
Pathways Overview For Open House   19 Sep2010Pathways Overview For Open House   19 Sep2010
Pathways Overview For Open House 19 Sep2010
 
Next Century Project Overview
Next Century Project OverviewNext Century Project Overview
Next Century Project Overview
 
how to build a Length of Stay model for a ProofOfConcept project
how to build a Length of Stay model for a ProofOfConcept projecthow to build a Length of Stay model for a ProofOfConcept project
how to build a Length of Stay model for a ProofOfConcept project
 

More from Stanford University

Team Networks - 2022 Technology, Innovation & Great Power Competition
Team Networks  - 2022 Technology, Innovation & Great Power CompetitionTeam Networks  - 2022 Technology, Innovation & Great Power Competition
Team Networks - 2022 Technology, Innovation & Great Power CompetitionStanford University
 
Team LiOn Batteries - 2022 Technology, Innovation & Great Power Competition
Team LiOn Batteries  - 2022 Technology, Innovation & Great Power CompetitionTeam LiOn Batteries  - 2022 Technology, Innovation & Great Power Competition
Team LiOn Batteries - 2022 Technology, Innovation & Great Power CompetitionStanford University
 
Team Quantum - 2022 Technology, Innovation & Great Power Competition
Team Quantum  - 2022 Technology, Innovation & Great Power CompetitionTeam Quantum  - 2022 Technology, Innovation & Great Power Competition
Team Quantum - 2022 Technology, Innovation & Great Power CompetitionStanford University
 
Team Disinformation - 2022 Technology, Innovation & Great Power Competition
Team Disinformation  - 2022 Technology, Innovation & Great Power CompetitionTeam Disinformation  - 2022 Technology, Innovation & Great Power Competition
Team Disinformation - 2022 Technology, Innovation & Great Power CompetitionStanford University
 
Team Wargames - 2022 Technology, Innovation & Great Power Competition
Team Wargames  - 2022 Technology, Innovation & Great Power CompetitionTeam Wargames  - 2022 Technology, Innovation & Great Power Competition
Team Wargames - 2022 Technology, Innovation & Great Power CompetitionStanford University
 
Team Acquistion - 2022 Technology, Innovation & Great Power Competition
Team Acquistion  - 2022 Technology, Innovation & Great Power Competition Team Acquistion  - 2022 Technology, Innovation & Great Power Competition
Team Acquistion - 2022 Technology, Innovation & Great Power Competition Stanford University
 
Team Climate Change - 2022 Technology, Innovation & Great Power Competition
Team Climate Change - 2022 Technology, Innovation & Great Power Competition Team Climate Change - 2022 Technology, Innovation & Great Power Competition
Team Climate Change - 2022 Technology, Innovation & Great Power Competition Stanford University
 
Altuna Engr245 2022 Lessons Learned
Altuna Engr245 2022 Lessons LearnedAltuna Engr245 2022 Lessons Learned
Altuna Engr245 2022 Lessons LearnedStanford University
 
Invisa Engr245 2022 Lessons Learned
Invisa Engr245 2022 Lessons LearnedInvisa Engr245 2022 Lessons Learned
Invisa Engr245 2022 Lessons LearnedStanford University
 
ānanda Engr245 2022 Lessons Learned
ānanda Engr245 2022 Lessons Learnedānanda Engr245 2022 Lessons Learned
ānanda Engr245 2022 Lessons LearnedStanford University
 
Gordian Knot Center Roundtable w/Depty SecDef
Gordian Knot Center Roundtable w/Depty SecDef Gordian Knot Center Roundtable w/Depty SecDef
Gordian Knot Center Roundtable w/Depty SecDef Stanford University
 
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Stanford University
 
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Stanford University
 
Team Catena - 2021 Technology, Innovation & Great Power Competition
Team Catena - 2021 Technology, Innovation & Great Power CompetitionTeam Catena - 2021 Technology, Innovation & Great Power Competition
Team Catena - 2021 Technology, Innovation & Great Power CompetitionStanford University
 
Team Apollo - 2021 Technology, Innovation & Great Power Competition
Team Apollo - 2021 Technology, Innovation & Great Power CompetitionTeam Apollo - 2021 Technology, Innovation & Great Power Competition
Team Apollo - 2021 Technology, Innovation & Great Power CompetitionStanford University
 
Team Drone - 2021 Technology, Innovation & Great Power Competition
Team Drone - 2021 Technology, Innovation & Great Power CompetitionTeam Drone - 2021 Technology, Innovation & Great Power Competition
Team Drone - 2021 Technology, Innovation & Great Power CompetitionStanford University
 
Team Short Circuit - 2021 Technology, Innovation & Great Power Competition
Team Short Circuit - 2021 Technology, Innovation & Great Power CompetitionTeam Short Circuit - 2021 Technology, Innovation & Great Power Competition
Team Short Circuit - 2021 Technology, Innovation & Great Power CompetitionStanford University
 
Team Aurora - 2021 Technology, Innovation & Great Power Competition
Team Aurora - 2021 Technology, Innovation & Great Power CompetitionTeam Aurora - 2021 Technology, Innovation & Great Power Competition
Team Aurora - 2021 Technology, Innovation & Great Power CompetitionStanford University
 
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...Stanford University
 
Lecture 8 - Technology, Innovation and Great Power Competition - Cyber
Lecture 8 - Technology, Innovation and Great Power Competition - CyberLecture 8 - Technology, Innovation and Great Power Competition - Cyber
Lecture 8 - Technology, Innovation and Great Power Competition - CyberStanford University
 

More from Stanford University (20)

Team Networks - 2022 Technology, Innovation & Great Power Competition
Team Networks  - 2022 Technology, Innovation & Great Power CompetitionTeam Networks  - 2022 Technology, Innovation & Great Power Competition
Team Networks - 2022 Technology, Innovation & Great Power Competition
 
Team LiOn Batteries - 2022 Technology, Innovation & Great Power Competition
Team LiOn Batteries  - 2022 Technology, Innovation & Great Power CompetitionTeam LiOn Batteries  - 2022 Technology, Innovation & Great Power Competition
Team LiOn Batteries - 2022 Technology, Innovation & Great Power Competition
 
Team Quantum - 2022 Technology, Innovation & Great Power Competition
Team Quantum  - 2022 Technology, Innovation & Great Power CompetitionTeam Quantum  - 2022 Technology, Innovation & Great Power Competition
Team Quantum - 2022 Technology, Innovation & Great Power Competition
 
Team Disinformation - 2022 Technology, Innovation & Great Power Competition
Team Disinformation  - 2022 Technology, Innovation & Great Power CompetitionTeam Disinformation  - 2022 Technology, Innovation & Great Power Competition
Team Disinformation - 2022 Technology, Innovation & Great Power Competition
 
Team Wargames - 2022 Technology, Innovation & Great Power Competition
Team Wargames  - 2022 Technology, Innovation & Great Power CompetitionTeam Wargames  - 2022 Technology, Innovation & Great Power Competition
Team Wargames - 2022 Technology, Innovation & Great Power Competition
 
Team Acquistion - 2022 Technology, Innovation & Great Power Competition
Team Acquistion  - 2022 Technology, Innovation & Great Power Competition Team Acquistion  - 2022 Technology, Innovation & Great Power Competition
Team Acquistion - 2022 Technology, Innovation & Great Power Competition
 
Team Climate Change - 2022 Technology, Innovation & Great Power Competition
Team Climate Change - 2022 Technology, Innovation & Great Power Competition Team Climate Change - 2022 Technology, Innovation & Great Power Competition
Team Climate Change - 2022 Technology, Innovation & Great Power Competition
 
Altuna Engr245 2022 Lessons Learned
Altuna Engr245 2022 Lessons LearnedAltuna Engr245 2022 Lessons Learned
Altuna Engr245 2022 Lessons Learned
 
Invisa Engr245 2022 Lessons Learned
Invisa Engr245 2022 Lessons LearnedInvisa Engr245 2022 Lessons Learned
Invisa Engr245 2022 Lessons Learned
 
ānanda Engr245 2022 Lessons Learned
ānanda Engr245 2022 Lessons Learnedānanda Engr245 2022 Lessons Learned
ānanda Engr245 2022 Lessons Learned
 
Gordian Knot Center Roundtable w/Depty SecDef
Gordian Knot Center Roundtable w/Depty SecDef Gordian Knot Center Roundtable w/Depty SecDef
Gordian Knot Center Roundtable w/Depty SecDef
 
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
 
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
Team Army venture capital - 2021 Technology, Innovation & Great Power Competi...
 
Team Catena - 2021 Technology, Innovation & Great Power Competition
Team Catena - 2021 Technology, Innovation & Great Power CompetitionTeam Catena - 2021 Technology, Innovation & Great Power Competition
Team Catena - 2021 Technology, Innovation & Great Power Competition
 
Team Apollo - 2021 Technology, Innovation & Great Power Competition
Team Apollo - 2021 Technology, Innovation & Great Power CompetitionTeam Apollo - 2021 Technology, Innovation & Great Power Competition
Team Apollo - 2021 Technology, Innovation & Great Power Competition
 
Team Drone - 2021 Technology, Innovation & Great Power Competition
Team Drone - 2021 Technology, Innovation & Great Power CompetitionTeam Drone - 2021 Technology, Innovation & Great Power Competition
Team Drone - 2021 Technology, Innovation & Great Power Competition
 
Team Short Circuit - 2021 Technology, Innovation & Great Power Competition
Team Short Circuit - 2021 Technology, Innovation & Great Power CompetitionTeam Short Circuit - 2021 Technology, Innovation & Great Power Competition
Team Short Circuit - 2021 Technology, Innovation & Great Power Competition
 
Team Aurora - 2021 Technology, Innovation & Great Power Competition
Team Aurora - 2021 Technology, Innovation & Great Power CompetitionTeam Aurora - 2021 Technology, Innovation & Great Power Competition
Team Aurora - 2021 Technology, Innovation & Great Power Competition
 
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...
Team Conflicted Capital Team - 2021 Technology, Innovation & Great Power Comp...
 
Lecture 8 - Technology, Innovation and Great Power Competition - Cyber
Lecture 8 - Technology, Innovation and Great Power Competition - CyberLecture 8 - Technology, Innovation and Great Power Competition - Cyber
Lecture 8 - Technology, Innovation and Great Power Competition - Cyber
 

Recently uploaded

ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701bronxfugly43
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfSherif Taha
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17Celine George
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin ClassesCeline George
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsMebane Rash
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfagholdier
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxnegromaestrong
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.christianmathematics
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Association for Project Management
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfPoh-Sun Goh
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Jisc
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdfQucHHunhnh
 

Recently uploaded (20)

ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Spatium Project Simulation student brief
Spatium Project Simulation student briefSpatium Project Simulation student brief
Spatium Project Simulation student brief
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
Asian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptxAsian American Pacific Islander Month DDSD 2024.pptx
Asian American Pacific Islander Month DDSD 2024.pptx
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 

Omniscient H4D 2020 Lessons Learned

  • 1. Team Omniscient Original Problem DCGS operators need an automated way to review a larger quantity of collected imaging data in order to surface actionable intelligence to leadership. Sponsor Organization: US Air Force Tactical Exploitation of National Capabilities (AF TENCAP) 108 Interviews Supported By: Maj Rose (Sponsor), COL Smith-Heys (Military Mentor), Kevin Ray (Business Mentor), Gus Hernandez (Advisor) Final Problem Analysts lack the computer vision tools to augment their ability to rapidly locate, identify, and analyze objects of interest, which would allow them to focus their time on higher order analysis tasks. Nick Mirda | GSB ‘21 Prior Army Intelligence Officer Summer: BCG Jon Braatz | MS CS ‘20 Computer Vision Research Summer: ! Andrew Fang | BS CS ‘22 Computer Vision Products Summer: Anduril
  • 2. 90+% of images never reviewed! There’s too much data!
  • 3. KEY PARTNERS We will liaison with two DCGS (Distributed Common Ground/Surface System) centers, located at Langley AFB and Beale AFB Other Potential Partners: - Intelligence Analysts - USAF Weapons School - DARPA - KesselRun - Air Force Research Lab - Sandia National Labs - MIT Lincoln Lab - DIU - NASIC KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: the usability and accuracy of our model on data provided by the Air Force ● Our beneficiaries will measure mission achievement by: the adoption/ease-of-use for analysts whose jobs we will simplify and ability to surface exploitable info in collected data. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time) ● Potential costs for proprietary software BENEFICIARIES 1. Operators: Intelligence analysts who parse through images (NASIC, CENTCOM, etc) 2. Decision Makers: High level decision makers who need actionable intelligence quickly and efficiently 1. Narrow problem space 2. Access Data 3. Build model by augmenting YOLO/existing models 4. Test model 1. Analysts who manually identify actionable intel (to provide insight on what is considered valuable data + provide robustly labeled data) 2. AWS/Azure for training 3. Lots of data 1. Workload Reduction: Reduce human hours currently spent on identifying actionable information in images 1. Decrease Intelligence Processing Timeline: Capture information from images faster than a human analyst 1. Reduce Data Backlogs: Parse image database backlogs to surface exploitable images 1. End Users: Analysts who parse through images of AF pilots who are willing to test our software 2. Leadership: Budget authority and operational policy experts 1. Initial deployment: command line service 2. Future deployments: product with a UI/clear instructions for analysts Mission Model Canvas: initial expectations
  • 4. KEY PARTNERS We will liaison with two DCGS (Distributed Common Ground/Surface System) centers, located at Langley AFB and Beale AFB Other Potential Partners: - Intelligence Analysts - USAF Weapons School - DARPA - KesselRun - Air Force Research Lab - Sandia National Labs - MIT Lincoln Lab - DIU - NASIC KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: the usability and accuracy of our model on data provided by the Air Force ● Our beneficiaries will measure mission achievement by: the adoption/ease-of-use for analysts whose jobs we will simplify and ability to surface exploitable info in collected data. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time) ● Potential costs for proprietary software BENEFICIARIES 1. Operators: Intelligence analysts who parse through images (NASIC, CENTCOM, etc) 2. Decision Makers: High level decision makers who need actionable intelligence quickly and efficiently 1. Narrow problem space 2. Access Data 3. Build model by augmenting YOLO/existing models 4. Test model 1. Analysts who manually identify actionable intel (to provide insight on what is considered valuable data + provide robustly labeled data) 2. AWS/Azure for training 3. Lots of data 1. Workload Reduction: Reduce human hours currently spent on identifying actionable information in images 1. Decrease Intelligence Processing Timeline: Capture information from images faster than a human analyst 1. Reduce Data Backlogs: Parse image database backlogs to surface exploitable images 1. End Users: Analysts who parse through images of AF pilots who are willing to test our software 2. Leadership: Budget authority and operational policy experts 1. Initial deployment: command line service 2. Future deployments: product with a UI/clear instructions for analysts Mission Model Canvas: initial expectations Initial Thoughts: 1. Help analysts look for “needles in haystacks”
  • 5. KEY PARTNERS We will liaison with two DCGS (Distributed Common Ground/Surface System) centers, located at Langley AFB and Beale AFB Other Potential Partners: - Intelligence Analysts - USAF Weapons School - DARPA - KesselRun - Air Force Research Lab - Sandia National Labs - MIT Lincoln Lab - DIU - NASIC KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: the usability and accuracy of our model on data provided by the Air Force ● Our beneficiaries will measure mission achievement by: the adoption/ease-of-use for analysts whose jobs we will simplify and ability to surface exploitable info in collected data. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time) ● Potential costs for proprietary software BENEFICIARIES 1. Operators: Intelligence analysts who parse through images (NASIC, CENTCOM, etc) 2. Decision Makers: High level decision makers who need actionable intelligence quickly and efficiently 1. Narrow problem space 2. Access Data 3. Build model by augmenting YOLO/existing models 4. Test model 1. Analysts who manually identify actionable intel (to provide insight on what is considered valuable data + provide robustly labeled data) 2. AWS/Azure for training 3. Lots of data 1. Workload Reduction: Reduce human hours currently spent on identifying actionable information in images 1. Decrease Intelligence Processing Timeline: Capture information from images faster than a human analyst 1. Reduce Data Backlogs: Parse image database backlogs to surface exploitable images 1. End Users: Analysts who parse through images of AF pilots who are willing to test our software 2. Leadership: Budget authority and operational policy experts 1. Initial deployment: command line service 2. Future deployments: product with a UI/clear instructions for analysts Mission Model Canvas: initial expectations Initial Thoughts: 1. Help analysts look for “needles in haystacks” 2. What do those “needles” look like?
  • 6. KEY PARTNERS We will liaison with two DCGS (Distributed Common Ground/Surface System) centers, located at Langley AFB and Beale AFB Other Potential Partners: - Intelligence Analysts - USAF Weapons School - DARPA - KesselRun - Air Force Research Lab - Sandia National Labs - MIT Lincoln Lab - DIU - NASIC KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: the usability and accuracy of our model on data provided by the Air Force ● Our beneficiaries will measure mission achievement by: the adoption/ease-of-use for analysts whose jobs we will simplify and ability to surface exploitable info in collected data. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time) ● Potential costs for proprietary software BENEFICIARIES 1. Operators: Intelligence analysts who parse through images (NASIC, CENTCOM, etc) 2. Decision Makers: High level decision makers who need actionable intelligence quickly and efficiently 1. Narrow problem space 2. Access Data 3. Build model by augmenting YOLO/existing models 4. Test model 1. Analysts who manually identify actionable intel (to provide insight on what is considered valuable data + provide robustly labeled data) 2. AWS/Azure for training 3. Lots of data 1. Workload Reduction: Reduce human hours currently spent on identifying actionable information in images 1. Decrease Intelligence Processing Timeline: Capture information from images faster than a human analyst 1. Reduce Data Backlogs: Parse image database backlogs to surface exploitable images 1. End Users: Analysts who parse through images of AF pilots who are willing to test our software 2. Leadership: Budget authority and operational policy experts 1. Initial deployment: command line service 2. Future deployments: product with a UI/clear instructions for analysts Mission Model Canvas: initial expectations Initial Thoughts: 1. Help analysts look for “needles in haystacks” 2. What do those “needles” look like? 3. Get our hands on imagery data to build a solution
  • 7. BENEFICIARIES BUYERS PARTNERS We interviewed 108 people all holding a different piece of the puzzle. EXPERTS
  • 8. How we’re feeling: we got this!
  • 9. Everyone we talked to had a different problem. Detect Changes We were overwhelmed.
  • 10. Everyone we talked to had a different problem. Image Clarity Rating (NIIRS) Detect Changes We were overwhelmed.
  • 11. Everyone we talked to had a different problem. Image Clarity Rating (NIIRS) North Korean MissilesDetect Changes We were overwhelmed.
  • 12. Everyone we talked to had a different problem. Full-Motion Video (Maven) Image Clarity Rating (NIIRS) North Korean MissilesDetect Changes We were overwhelmed.
  • 13. Everyone we talked to had a different problem. Full-Motion Video (Maven) Image Clarity Rating (NIIRS) North Korean MissilesDetect Changes And there were a lot of imagery options. We were overwhelmed.
  • 15. We lost two teammates!
  • 17. Air Force is shifting to higher level analysis. Imagery Analysis ● Recording object position ● Annotating observations Imagery Understanding ● Situational analysis ● Deep understanding
  • 18. “Instead of counting objects that can be automatically detected, my analysts can ask why those vehicles are there, really unleashes analytic horsepower.” -Director of Operations @ 13th Intel Squadron Machine learning can automate the drudge work.
  • 19. ● Tracking all aircraft in flight (NRO). ○ Unsuccessful. ● Project Maven: automatic full-motion video analysis. ○ Mixed results. ● Automatic airfield layout change detection (NGA). ○ Ongoing. ● Identify groupings of tanks (NGA). ○ Ongoing. Previous efforts stumbled due to overambitious goals and improperly labelled data. Many DoD programs to automate imagery analysis, but most are still work-in-progress. ? ? ?
  • 20. First MVP: a generic computer vision tool. ● it processes analyst imagery to detect objects. ● it runs in the background. ● it uses computer vision. Feedback: 1) “I’ve heard this dozens of times.” 2) “I care less about innovation, more about integration.” We need a specific use case & a way to get in.
  • 21. A bad pivot: we jumped on the first computer vision solution we saw (computer vision to help bandwidth). • We thought RQ-4 Global Hawks had significant bandwidth limitations that hampered SAR imagery delivery to the base, after speaking with a pilot. We pivoted too early, deviated from beneficiary insights, and were invalidated with further interviews.
  • 22. How we’re feeling: demoralized :/
  • 24. Insight: The AN-2 is a proxy for what our solution can deliver. ● This is a discrete, strategically relevant problem we can sink our teeth into ● If we can track these, we expand to tracking other equipment ● it’s not easy, but we think we could build it. How do we get in? How do we execute?
  • 25. 3 meter resolution 50 centimeter resolution Our algorithms would require a lot of good data. We scraped a few thousand images. For free!
  • 26. Taechon Airfield AN-2 Image #B4993 Date: 05MAY2020 Asset Quantity: 9 Asset Coordinates: 1. 51SYE1354920036 2. 51SYE1347120046 ... 9. 51SYE1319020263c First validated MVP automates AN-2 detection & feeds into analyst workflow. .KML Outputs
  • 27. KEY PARTNERS Air Force DGS-3 AETs that will be our customers/users. Commercial satellite imagery companies to acquire data to train on. (Maxar, Planet). Innovation and Research organizations to accelerate classified data/system access. (DIU, CRADA, SBIR). KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: accuracy of AN-2 classifications from still imagery and anomaly alerts. ● Our beneficiaries will measure mission achievement by: the ability to identify meaningful activity/objects of interest from large data sets and adoption/ease-of-use for analysts. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time). ● Unclassified EO data/labels from commercial companies. ● Potential costs for proprietary software. BENEFICIARIES 1. Operators: DGS-3 AET Analysts (Phase 1), ISR Pilots, Sensor Operators, Collection Managers 1. Decision Makers: US Forces and Korea leadership need actionable intel fast. 1. Analysts who manually analyze still imagery (to provide insight on what is data + provide robustly labeled data). 2. Lots of commercial satellite data (Maxar). 1. Decrease AN-2 Imagery Process Time: Quickly scan large images to extract quantity/location of assets of interest. 1. Get AN-2 Anomalies to Analysts/Leaders Fast: Alert analysts to enable them to verify suspicious activity ASAP. 1. Up-to-Date AN-2 Activity/Locations: Know where all AN-2s are and what they do with reliable information. 1. End Users: Imagery analysts & AETs at DGS-3. 1. Leadership: DGS-3 Collections Managers, Combatant Commanders setting ISR priorities. 1. Image Processing on unclass computer. 2. Future deployments: plugin for existing analysis software 3. Continuously-running anomaly notification System 1. Access commercial satellite data of NK airfields. 2. Build and test model on unclassified satellite imagery. 3. Identify integration pathway. Mission Model Canvas: use case identified! Allowed us to: 1. Articulate specific value proposition
  • 28. KEY PARTNERS Air Force DGS-3 AETs that will be our customers/users. Commercial satellite imagery companies to acquire data to train on. (Maxar, Planet). Innovation and Research organizations to accelerate classified data/system access. (DIU, CRADA, SBIR). KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: accuracy of AN-2 classifications from still imagery and anomaly alerts. ● Our beneficiaries will measure mission achievement by: the ability to identify meaningful activity/objects of interest from large data sets and adoption/ease-of-use for analysts. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time). ● Unclassified EO data/labels from commercial companies. ● Potential costs for proprietary software. BENEFICIARIES 1. Operators: DGS-3 AET Analysts (Phase 1), ISR Pilots, Sensor Operators, Collection Managers 1. Decision Makers: US Forces and Korea leadership need actionable intel fast. 1. Analysts who manually analyze still imagery (to provide insight on what is data + provide robustly labeled data). 2. Lots of commercial satellite data (Maxar). 1. Decrease AN-2 Imagery Process Time: Quickly scan large images to extract quantity/location of assets of interest. 1. Get AN-2 Anomalies to Analysts/Leaders Fast: Alert analysts to enable them to verify suspicious activity ASAP. 1. Up-to-Date AN-2 Activity/Locations: Know where all AN-2s are and what they do with reliable information. 1. End Users: Imagery analysts & AETs at DGS-3. 1. Leadership: DGS-3 Collections Managers, Combatant Commanders setting ISR priorities. 1. Image Processing on unclass computer. 2. Future deployments: plugin for existing analysis software 3. Continuously-running anomaly notification System 1. Access commercial satellite data of NK airfields. 2. Build and test model on unclassified satellite imagery. 3. Identify integration pathway. Mission Model Canvas: use case identified! Allowed us to: 1. Articulate specific value proposition 2. Focus on the appropriate end users
  • 29. KEY PARTNERS Air Force DGS-3 AETs that will be our customers/users. Commercial satellite imagery companies to acquire data to train on. (Maxar, Planet). Innovation and Research organizations to accelerate classified data/system access. (DIU, CRADA, SBIR). KEY RESOURCES VALUE PROPOSITIONSKEY ACTIVITIES MISSION ACHIEVEMENT/IMPACT FACTORS ● We will measure mission achievement by: accuracy of AN-2 classifications from still imagery and anomaly alerts. ● Our beneficiaries will measure mission achievement by: the ability to identify meaningful activity/objects of interest from large data sets and adoption/ease-of-use for analysts. DEPLOYMENT BUY-IN & SUPPORT MISSION BUDGET/COST ● Budget for training costs (AWS/Azure GPU time). ● Unclassified EO data/labels from commercial companies. ● Potential costs for proprietary software. BENEFICIARIES 1. Operators: DGS-3 AET Analysts (Phase 1), ISR Pilots, Sensor Operators, Collection Managers 1. Decision Makers: US Forces and Korea leadership need actionable intel fast. 1. Analysts who manually analyze still imagery (to provide insight on what is data + provide robustly labeled data). 2. Lots of commercial satellite data (Maxar). 1. Decrease AN-2 Imagery Process Time: Quickly scan large images to extract quantity/location of assets of interest. 1. Get AN-2 Anomalies to Analysts/Leaders Fast: Alert analysts to enable them to verify suspicious activity ASAP. 1. Up-to-Date AN-2 Activity/Locations: Know where all AN-2s are and what they do with reliable information. 1. End Users: Imagery analysts & AETs at DGS-3. 1. Leadership: DGS-3 Collections Managers, Combatant Commanders setting ISR priorities. 1. Image Processing on unclass computer. 2. Future deployments: plugin for existing analysis software 3. Continuously-running anomaly notification System 1. Access commercial satellite data of NK airfields. 2. Build and test model on unclassified satellite imagery. 3. Identify integration pathway. Mission Model Canvas: use case identified! Allowed us to: 1. Articulate specific value proposition 2. Focus on the appropriate end users 3. Outline a specific integration pathway
  • 30. How we’re feeling: Yes! On the right track!
  • 31. Unclassified Satellite Imagery NIPRnet (Unclassified) Unclassified Tool, Integrates with Classified Systems
  • 33. Unclassified Satellite Imagery Entity Detection Algorithms NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison
  • 34. Unclassified Satellite Imagery Entity Detection Algorithms NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison .KML Output Files
  • 35. Unclassified Satellite Imagery Entity Detection Algorithms NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison Date Location Quantity SIPRnet (Classified) .KML Output Files
  • 36. Data Uploaded to SIPRnet Unclassified Satellite Imagery Entity Detection Algorithms NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison Date Location Quantity SIPRnet (Classified) .KML Output Files .KMLs Uploaded
  • 37. Data Uploaded to SIPRnet Unclassified Satellite Imagery Entity Detection Algorithms Data integrates with analyst tools NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison Date Location Quantity SIPRnet (Classified) .KML Output Files .KMLs Uploaded
  • 38. Data Uploaded to SIPRnet Unclassified Satellite Imagery Entity Detection Algorithms Data integrates with analyst tools Intel products are built more quickly and effectively. NIPRnet (Unclassified) Unclassified Integration into Existing Analyst Workflow Historical Baseline Comparison Date Location Quantity SIPRnet (Classified) .KML Output Files .KMLs Uploaded
  • 39. Credibility: Computer Vision: Working Towards Unofficial Demo with Air Combat Command (In 2-3 Weeks) TENCAP Mentorship to TENCAP Letter of Endorsement
  • 40.
  • 41. Help us build omniscience. MILITARY: Collaboration- how can we help you? PRIMEs: Platforms and Partnerships- how can we work together? NEXT STEPS: COMMERCIAL: Dual use | Venture Funding- let’s chat! Email: hello@omniscientlabs.io $20k | Now $50k | 6 Months Working over summer: ● Develop AN-2 algorithms ● Scope out dual use applications