SlideShare a Scribd company logo
1 of 35
Download to read offline
1
ESA UNCLASSIFIED – For ESA Official Use Only
Unifying Space Mission Knowledge
with NLP & Knowledge Graphs
Dr. Audrey Berquand & Ana Victoria Ladeira
23/08/2022
Disclaimer: The views and opinions expressed in this
presentation are those of the speakers and do not
necessarily reflect the views and position of ESA.
2
Context – Mission Analysis and Design
Example challenge:
ESA needs a more effective way of detecting and monitoring potentially dangerous wildfires
Mission Operations element
DETERMINE:
Spacecraft element
Orbit and Trajectories
Launch element Spacecraft element
Instrumentation & Payloads
3
Context – Missions Variety
Cassini-Huygens
• Powered by nuclear fuel
• 6.8m x 4m
• Instruments for cosmic dust analysis, plasma
spectrometry, visible and ultraviolet light
• Included lander to land on Titan, one of Saturn’s
moons
• 7 years on route, 3 years orbiting Saturn
Cubesats
• 2kg max
• 10cm side cube
• Uses mostly off-the-shelf components
• Generates around 10W of power for instruments
• Very short lived – 1 to 3 years
Specifications of Space Missions can vary wildly!
4
Context – Increasing number of missions
An increasing number of space missions is
being designed and launched.
Each mission comes with a large data bundle of
reports, presentations, ...
© ESA/CNES/Arianespace/Optique Video du CSG/S Martin
Problem:
How do experts keep-up with all this data,
without losing sight of the Bigger Picture?
5
Our vision
From scattered and heterogenous
information...
...To a structured and unified view of
the space ecosystem
6
I. Background
II. Approach
Summary
Language Models
LMs applications
Knowledge Graphs &
Space
A manually defined schema
Population with the GPT-3 model
Our Knowledge Graphs
Demo & Use Cases
III. Corpus
IV. Results
V. Discussion
7
ESA UNCLASSIFIED - For ESA Official Use Only 7
BACKGROUND
8
Background – Language Models
A Language Model is a probability distribution over words or word sequences.
"In space no can hear you …"
Scream 0.89
Speak 0.75
…
Octopus 0.01
Why should you care about LMs?
• Pretrained LMs in Natural Language Processing (NLP) have pushed the limits of language
understanding and generation.
• It has become a main trend in NLP research
• Famous LMs include BERT, RoBERTa, T5, GPT-2, GPT-3, …
even SpaceRoBERTa and CosmicRoBERTa
9
Background – LMs Applications in your daily life
Code generation Content Generation
Headlime.com
Debuild
Semantic Search
Casetext.com
10
Background – LMs Applications Examples
1. Text Summarisation:
3. Text Parser:
2. Text Generation:
* These examples were all generated through
the OpenAI playground
11
Background – KGs & Space
From Engineering Models To
Knowledge Graph: Delivering
New Insights Into Models –
Migrates Engineering Models
of CubeSats to a KG
NASA’s Space Talent KG
helps them find the right
space expertise for their
projects
NASA’s Lessons
Learned KG combines
NLP and KG to
categorize their lessons
12
ESA UNCLASSIFIED – For ESA Official Use Only
APPROACH
13
Approach Overview
14
Approach - KG Schema
Manually defined to reflect both technical and
economical characteristics of missions.
Visualised with TypeDB Studio
15
Approach – KG Population
1. Each mission description is parsed with the Davinci engine of the GPT-3 model, through the OpenAI API
*In reality, we use
the Few-Shot
Learning approach,
and we have 16
parameters parsed.
16 Parameters Parsed:
Entity Attribute Example
Mission
missionName BIOMASS
missionStatus Operational
program Earth Explorer
objectives determine the amount
of biomass and carbon
stored in forests
launchDate 08/2023
endOfLife 10/2030
Stakeholder
StakeholderName
(agency, prime Contractor)
ESA, NASA,
Thales, Airbus,...
Entity Attribute Example
Instrument
instrumentName P-band Synthetic Aperture Radar
instrumentStatus Operational
instrumentType Hyperspectral camera, SAR
measurementApp measure forest biomass
Orbit
orbitType Sun-synchronous
orbitInclination 98 deg
orbitAltitude 660 km
orbitRepeatCycle 3 days
16
Approach – KG Population
3. Using the Vaticle Python API, insert queries are
generated to populate the KG
2. The parsed outputs are saved
into a JSON file with the following format:
17
ESA UNCLASSIFIED – For ESA Official Use Only
CORPUS
18
Corpus
• 1200+ Articles, 895 selected for this project
• Each article contains a textual description of mission
• Pages do not follow a template nor contain
structurec data
• 335 missions
• Structured tables with information about
instruments, agencies, orbit and etc
• Maintained by CEOS and ESA
EoPortal Directory CEOS EO Handbook Database
19
ESA UNCLASSIFIED – For ESA Official Use Only
RESULTS
20
Results – eoPortal Directory Knowledge Graph
The description of 237 mission descriptions are parsed.
The model provided an output for a majority of the parsing request.
Parameter [%] parsed
Agencies 100
Mission Objectives 100
Mission Status 99.6
Launch Date 98.7
Program 92.4
Instrument Name 90.7
Orbit Type 89.9
Instrument Applications 86.9
Parameter [%] parsed
Instrument Status 85.65
Instrument Type 85.65
Orbit Altitude 81
Prime Contractor 80.6
EOL Date 79.75
Orbit Inclination 78.1
Orbit Repeat Cycle 63.29
Instrument Manufacturer 63.29
21
Results – CEOS Knowledge Graph
The description of 335 missions were ingested from the Missions Table in the CEOS DB
The description of 936 instruments were ingested from the Instruments Table in the CEOS DB
Descriptions were not parsed but directly ingested using the TypeDB Python API given their
structured format.
22
Results – Comparing KGs
• GPT3 is able to capture certain relationships not
present on the CEOS database, like information
about who is the prime of certain missions
• The GPT3 KG captures way more
information about industry in general, CEOS
contains more information about agencies
• CEOS KG contains more information about other
instruments in the mission, while GPT3 only focus
on the main instruments
• GPT3 could be queried for more instruments
in the future
• Overall, the two KGs are very different!
23
ESA UNCLASSIFIED - For ESA Official Use Only 23
DEMO
24
Basic Queries (1)
Inferring all missions handled by a Prime Contractor:
Visualised with TypeDB Studio
Console and Graph Outputs:
25
Basic Queries (2)
Inferring missions with similar objectives:
Outputs:
Visualised with TypeDB Studio
26
Results – Use Case 1 – Inference
27
Results – Use Case 2
Collaborating stakeholders were identified using TypeDB’s rules and inference engine. The new relationship can
be used to find collaborators that own instruments with desired applications or specifications. For example, we can
find ESA partners that own wind measuring instruments:
match
$sh1 isa stakeholder, has stakeholderName
"ESA";
$sh2 isa stakeholder, has stakeholderName
$sh2-name;
$inst isa instrument, has instrumentName
$inst-name;
$app isa application, has applicationType
contains "wind measurement", has applicationType
$apptype;
$ownsinst (agency: $sh2, payload: $inst) isa
ownsInstrument;
$enapp (goal: $app, goalFulfiller: $inst)
isa enables;
$collab (collaborator: $sh1,
collaborator:$sh2) isa collaboratesWith;
get $sh2-name; group $sh2-name; count;
Partner No of Instruments
CNES 4
NOAA 15
JAXA 11
UKSA 2
EUMETSAT 3
NASA 29
Partner No of Instruments
nec corporation 1
toshiba corporation 1
NASA 2
TAS 1
Los Alamos national
laboratory 1
batc 1
LusoSpace 1
CEOS
KG
GPT3
KG
CEOS
KG
GPT3
KG
28
Results – Use Case 2 – Combining KGs
• Both graphs share some mission names.
GPT3 is able to capture contractor information
not included on the CEOS database. These
relationships and extra stakeholders were
added to the CEOS KG to further enrich it.
• In the future, a more extensive merge of both
graphs will be attempted
Class Type GPT3 CEOS CEOS+GPT3
Entity stakeholder 389 86 389
Relationship ownsInstrument 165 1117 1154
Relationship isPrimeOf 193 0 193
29
ESA UNCLASSIFIED – For ESA Official Use Only
DISCUSSION & CONCLUSION
30
Discussion
GPT-3 limitations:
• Only takes 2k tokens as input
• Human validation is often necessary
• Not open-source
Positive points:
• High parsing rate (86% over all parameters)
• Encouraging results
• Crucial support in populating a KG from text
31
Future Work
Parsing the whole EoDirectory page with GPT3 instead of only first 2000 tokens
Parsing the whole EoDirectory page with GPT3 instead of only first 2000 tokens
Using Open Source models like T5 or BLOOM instead of GPT3
Align the KG with the ESA Space System Ontology
Exploring different KG merging techniques to combine both KGs developed for this study
Adapting GPT3 script to extract more than one instance of each variable where applicable
32
Conclusion
Should we trust the GPT-3 models outputs?
Can Language Models support our vision of providing a unified overview of the space ecosystem?
The generated data should be validated by humans. However, it is impressive
how the model trained on general data understands domain-specific concepts,
Parsing with LMs is a tremendous time saver.
LMs' performances are still improving, and more open-source models are appearing.
So, definitely yes!
33
33
The End
Thank you for your attention,
For more information, see our paper: "From Mission Description to Knowledge Graph: Applying Transformer-
based models to map knowledge from publicly available satellite datasets" to be presented at the 10th
International Systems & Concurrent Engineering for Space Applications (SECESA 2022)
Contact:
Audrey.berquand@esa.int
Anavictoria.ladeira@esa.int
34
ESA UNCLASSIFIED - For ESA Official Use Only 34
Extra slides
35
Approach – Validation of the GPT-3 outputs
For a subset of missions, we compared the generated text of the GPT-3 model with the CEOS database (manually verified). The CEOS
data is used as reference text. Below are the BLEU and ROUGE scores:
The BLEU and ROUGE scores are not always adapted for comparing strings, so we also used sentence-transformer model and cosine
similarity for the objective and the application parameters:

More Related Content

What's hot

TypeDB Academy- Getting Started with Schema Design
TypeDB Academy- Getting Started with Schema DesignTypeDB Academy- Getting Started with Schema Design
TypeDB Academy- Getting Started with Schema DesignVaticle
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersJulien SIMON
 
How Graph Data Science can turbocharge your Knowledge Graph
How Graph Data Science can turbocharge your Knowledge GraphHow Graph Data Science can turbocharge your Knowledge Graph
How Graph Data Science can turbocharge your Knowledge GraphNeo4j
 
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)Sergey Karayev
 
LanGCHAIN Framework
LanGCHAIN FrameworkLanGCHAIN Framework
LanGCHAIN FrameworkKeymate.AI
 
Microsoft AI Platform Overview
Microsoft AI Platform OverviewMicrosoft AI Platform Overview
Microsoft AI Platform OverviewDavid Chou
 
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...Neo4j
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Naoki (Neo) SATO
 
Introduction to Knowledge Graphs
Introduction to Knowledge GraphsIntroduction to Knowledge Graphs
Introduction to Knowledge Graphsmukuljoshi
 
Knowledge Graphs and Generative AI
Knowledge Graphs and Generative AIKnowledge Graphs and Generative AI
Knowledge Graphs and Generative AINeo4j
 
Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Databricks
 
ChatGPT vs. GPT-3.pdf
ChatGPT vs. GPT-3.pdfChatGPT vs. GPT-3.pdf
ChatGPT vs. GPT-3.pdfAddepto
 
Leveraging Generative AI to Accelerate Graph Innovation for National Security...
Leveraging Generative AI to Accelerate Graph Innovation for National Security...Leveraging Generative AI to Accelerate Graph Innovation for National Security...
Leveraging Generative AI to Accelerate Graph Innovation for National Security...Neo4j
 
AI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAndre Muscat
 
GPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge GraphGPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge GraphNeo4j
 
Unlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
 
Introduction to MLflow
Introduction to MLflowIntroduction to MLflow
Introduction to MLflowDatabricks
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Krishnaram Kenthapadi
 
Mother of Language`s Langchain
Mother of Language`s LangchainMother of Language`s Langchain
Mother of Language`s LangchainJun-hang Lee
 

What's hot (20)

TypeDB Academy- Getting Started with Schema Design
TypeDB Academy- Getting Started with Schema DesignTypeDB Academy- Getting Started with Schema Design
TypeDB Academy- Getting Started with Schema Design
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face Transformers
 
How Graph Data Science can turbocharge your Knowledge Graph
How Graph Data Science can turbocharge your Knowledge GraphHow Graph Data Science can turbocharge your Knowledge Graph
How Graph Data Science can turbocharge your Knowledge Graph
 
Introducing MLOps.pdf
Introducing MLOps.pdfIntroducing MLOps.pdf
Introducing MLOps.pdf
 
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
 
LanGCHAIN Framework
LanGCHAIN FrameworkLanGCHAIN Framework
LanGCHAIN Framework
 
Microsoft AI Platform Overview
Microsoft AI Platform OverviewMicrosoft AI Platform Overview
Microsoft AI Platform Overview
 
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...
The perfect couple: Uniting Large Language Models and Knowledge Graphs for En...
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
 
Introduction to Knowledge Graphs
Introduction to Knowledge GraphsIntroduction to Knowledge Graphs
Introduction to Knowledge Graphs
 
Knowledge Graphs and Generative AI
Knowledge Graphs and Generative AIKnowledge Graphs and Generative AI
Knowledge Graphs and Generative AI
 
Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™Web-Scale Graph Analytics with Apache® Spark™
Web-Scale Graph Analytics with Apache® Spark™
 
ChatGPT vs. GPT-3.pdf
ChatGPT vs. GPT-3.pdfChatGPT vs. GPT-3.pdf
ChatGPT vs. GPT-3.pdf
 
Leveraging Generative AI to Accelerate Graph Innovation for National Security...
Leveraging Generative AI to Accelerate Graph Innovation for National Security...Leveraging Generative AI to Accelerate Graph Innovation for National Security...
Leveraging Generative AI to Accelerate Graph Innovation for National Security...
 
AI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERS
 
GPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge GraphGPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge Graph
 
Unlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdf
 
Introduction to MLflow
Introduction to MLflowIntroduction to MLflow
Introduction to MLflow
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)
 
Mother of Language`s Langchain
Mother of Language`s LangchainMother of Language`s Langchain
Mother of Language`s Langchain
 

Similar to Unifying Space Mission Knowledge with NLP & KGs

Big Data, Big Computing, AI, and Environmental Science
Big Data, Big Computing, AI, and Environmental ScienceBig Data, Big Computing, AI, and Environmental Science
Big Data, Big Computing, AI, and Environmental ScienceIan Foster
 
Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Anubhav Jain
 
Scientific
Scientific Scientific
Scientific marpierc
 
Development Infographic
Development InfographicDevelopment Infographic
Development InfographicRealMassive
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsDatabricks
 
What is a Data Commons and Why Should You Care?
What is a Data Commons and Why Should You Care? What is a Data Commons and Why Should You Care?
What is a Data Commons and Why Should You Care? Robert Grossman
 
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...Unai Lopez-Novoa
 
Big Linked Data Federation - ExtremeEarth Open Workshop
Big Linked Data Federation - ExtremeEarth Open WorkshopBig Linked Data Federation - ExtremeEarth Open Workshop
Big Linked Data Federation - ExtremeEarth Open WorkshopExtremeEarth
 
HPC Cluster Computing from 64 to 156,000 Cores 
HPC Cluster Computing from 64 to 156,000 Cores HPC Cluster Computing from 64 to 156,000 Cores 
HPC Cluster Computing from 64 to 156,000 Cores inside-BigData.com
 
Pablo Gomez - Solving Large-scale Challenges with ESA Datalabs
Pablo Gomez - Solving Large-scale Challenges with ESA DatalabsPablo Gomez - Solving Large-scale Challenges with ESA Datalabs
Pablo Gomez - Solving Large-scale Challenges with ESA DatalabsAdvanced-Concepts-Team
 
Astronomical Data Processing on the LSST Scale with Apache Spark
Astronomical Data Processing on the LSST Scale with Apache SparkAstronomical Data Processing on the LSST Scale with Apache Spark
Astronomical Data Processing on the LSST Scale with Apache SparkDatabricks
 
Max Fagin Project Portfolio
Max Fagin Project PortfolioMax Fagin Project Portfolio
Max Fagin Project PortfolioMax Fagin
 
Analysis Ready Data workshop - OGC presentation
Analysis Ready Data workshop - OGC presentation Analysis Ready Data workshop - OGC presentation
Analysis Ready Data workshop - OGC presentation George Percivall
 
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...Accumulo Summit
 
Cycle Computing Record-breaking Petascale HPC Run
Cycle Computing Record-breaking Petascale HPC RunCycle Computing Record-breaking Petascale HPC Run
Cycle Computing Record-breaking Petascale HPC Runinside-BigData.com
 
Agile Systems Engineering & Agile at SKA Scale
Agile Systems Engineering & Agile at SKA ScaleAgile Systems Engineering & Agile at SKA Scale
Agile Systems Engineering & Agile at SKA ScaleJoint ALMA Observatory
 
NASA Advanced Computing Environment for Science & Engineering
NASA Advanced Computing Environment for Science & EngineeringNASA Advanced Computing Environment for Science & Engineering
NASA Advanced Computing Environment for Science & Engineeringinside-BigData.com
 
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...SoftwarePractice
 

Similar to Unifying Space Mission Knowledge with NLP & KGs (20)

Big Data, Big Computing, AI, and Environmental Science
Big Data, Big Computing, AI, and Environmental ScienceBig Data, Big Computing, AI, and Environmental Science
Big Data, Big Computing, AI, and Environmental Science
 
Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...
 
Scientific
Scientific Scientific
Scientific
 
Development Infographic
Development InfographicDevelopment Infographic
Development Infographic
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science Workflows
 
What is a Data Commons and Why Should You Care?
What is a Data Commons and Why Should You Care? What is a Data Commons and Why Should You Care?
What is a Data Commons and Why Should You Care?
 
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...
Contributions to the Efficient Use of General Purpose Coprocessors: KDE as Ca...
 
Big Linked Data Federation - ExtremeEarth Open Workshop
Big Linked Data Federation - ExtremeEarth Open WorkshopBig Linked Data Federation - ExtremeEarth Open Workshop
Big Linked Data Federation - ExtremeEarth Open Workshop
 
HPC Cluster Computing from 64 to 156,000 Cores 
HPC Cluster Computing from 64 to 156,000 Cores HPC Cluster Computing from 64 to 156,000 Cores 
HPC Cluster Computing from 64 to 156,000 Cores 
 
Pablo Gomez - Solving Large-scale Challenges with ESA Datalabs
Pablo Gomez - Solving Large-scale Challenges with ESA DatalabsPablo Gomez - Solving Large-scale Challenges with ESA Datalabs
Pablo Gomez - Solving Large-scale Challenges with ESA Datalabs
 
NASA's Movement Towards Cloud Computing
NASA's Movement Towards Cloud ComputingNASA's Movement Towards Cloud Computing
NASA's Movement Towards Cloud Computing
 
Astronomical Data Processing on the LSST Scale with Apache Spark
Astronomical Data Processing on the LSST Scale with Apache SparkAstronomical Data Processing on the LSST Scale with Apache Spark
Astronomical Data Processing on the LSST Scale with Apache Spark
 
Max Fagin Project Portfolio
Max Fagin Project PortfolioMax Fagin Project Portfolio
Max Fagin Project Portfolio
 
Analysis Ready Data workshop - OGC presentation
Analysis Ready Data workshop - OGC presentation Analysis Ready Data workshop - OGC presentation
Analysis Ready Data workshop - OGC presentation
 
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...
Accumulo Summit 2016: GeoMesa: Using Accumulo for Optimized Spatio-Temporal P...
 
Cycle Computing Record-breaking Petascale HPC Run
Cycle Computing Record-breaking Petascale HPC RunCycle Computing Record-breaking Petascale HPC Run
Cycle Computing Record-breaking Petascale HPC Run
 
Agile Systems Engineering & Agile at SKA Scale
Agile Systems Engineering & Agile at SKA ScaleAgile Systems Engineering & Agile at SKA Scale
Agile Systems Engineering & Agile at SKA Scale
 
NASA Advanced Computing Environment for Science & Engineering
NASA Advanced Computing Environment for Science & EngineeringNASA Advanced Computing Environment for Science & Engineering
NASA Advanced Computing Environment for Science & Engineering
 
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...
Adoption of Software By A User Community: The Montage Image Mosaic Engine Exa...
 
Horizons doc
Horizons docHorizons doc
Horizons doc
 

More from Vaticle

Building Biomedical Knowledge Graphs for In-Silico Drug Discovery
Building Biomedical Knowledge Graphs for In-Silico Drug DiscoveryBuilding Biomedical Knowledge Graphs for In-Silico Drug Discovery
Building Biomedical Knowledge Graphs for In-Silico Drug DiscoveryVaticle
 
Loading Huge Amounts of Data
Loading Huge Amounts of DataLoading Huge Amounts of Data
Loading Huge Amounts of DataVaticle
 
Natural Language Interface to Knowledge Graph
Natural Language Interface to Knowledge GraphNatural Language Interface to Knowledge Graph
Natural Language Interface to Knowledge GraphVaticle
 
The Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityThe Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityVaticle
 
Building a Cyber Threat Intelligence Knowledge Graph
Building a Cyber Threat Intelligence Knowledge GraphBuilding a Cyber Threat Intelligence Knowledge Graph
Building a Cyber Threat Intelligence Knowledge GraphVaticle
 
Knowledge Graphs for Supply Chain Operations.pdf
Knowledge Graphs for Supply Chain Operations.pdfKnowledge Graphs for Supply Chain Operations.pdf
Knowledge Graphs for Supply Chain Operations.pdfVaticle
 
Building a Distributed Database with Raft.pdf
Building a Distributed Database with Raft.pdfBuilding a Distributed Database with Raft.pdf
Building a Distributed Database with Raft.pdfVaticle
 
Enabling the Computational Future of Biology.pdf
Enabling the Computational Future of Biology.pdfEnabling the Computational Future of Biology.pdf
Enabling the Computational Future of Biology.pdfVaticle
 
TypeDB Academy | Inference with Rules
TypeDB Academy | Inference with RulesTypeDB Academy | Inference with Rules
TypeDB Academy | Inference with RulesVaticle
 
Beyond SQL - Comparing SQL to TypeQL
Beyond SQL - Comparing SQL to TypeQLBeyond SQL - Comparing SQL to TypeQL
Beyond SQL - Comparing SQL to TypeQLVaticle
 
Comparing Semantic Web Technologies to TypeDB
Comparing Semantic Web Technologies to TypeDBComparing Semantic Web Technologies to TypeDB
Comparing Semantic Web Technologies to TypeDBVaticle
 
Reasoner, Meet Actors | TypeDB's Native Reasoning Engine
Reasoner, Meet Actors | TypeDB's Native Reasoning EngineReasoner, Meet Actors | TypeDB's Native Reasoning Engine
Reasoner, Meet Actors | TypeDB's Native Reasoning EngineVaticle
 
Intro to TypeDB and TypeQL | A strongly-typed database
Intro to TypeDB and TypeQL | A strongly-typed databaseIntro to TypeDB and TypeQL | A strongly-typed database
Intro to TypeDB and TypeQL | A strongly-typed databaseVaticle
 
Graph Databases vs TypeDB | What you can't do with graphs
Graph Databases vs TypeDB | What you can't do with graphsGraph Databases vs TypeDB | What you can't do with graphs
Graph Databases vs TypeDB | What you can't do with graphsVaticle
 
Pandora Paper Leaks With TypeDB
 Pandora Paper Leaks With TypeDB Pandora Paper Leaks With TypeDB
Pandora Paper Leaks With TypeDBVaticle
 
Strongly Typed Data for Machine Learning
Strongly Typed Data for Machine LearningStrongly Typed Data for Machine Learning
Strongly Typed Data for Machine LearningVaticle
 
Open World Robotics
Open World RoboticsOpen World Robotics
Open World RoboticsVaticle
 
Combining Causal and Knowledge Modeling for Digital Transformation
Combining Causal and Knowledge Modeling for Digital TransformationCombining Causal and Knowledge Modeling for Digital Transformation
Combining Causal and Knowledge Modeling for Digital TransformationVaticle
 
How can we complete a Knowledge Graph?
How can we complete a Knowledge Graph?How can we complete a Knowledge Graph?
How can we complete a Knowledge Graph?Vaticle
 
Text-Mined Data in a Knowledge Graph
Text-Mined Data in a Knowledge GraphText-Mined Data in a Knowledge Graph
Text-Mined Data in a Knowledge GraphVaticle
 

More from Vaticle (20)

Building Biomedical Knowledge Graphs for In-Silico Drug Discovery
Building Biomedical Knowledge Graphs for In-Silico Drug DiscoveryBuilding Biomedical Knowledge Graphs for In-Silico Drug Discovery
Building Biomedical Knowledge Graphs for In-Silico Drug Discovery
 
Loading Huge Amounts of Data
Loading Huge Amounts of DataLoading Huge Amounts of Data
Loading Huge Amounts of Data
 
Natural Language Interface to Knowledge Graph
Natural Language Interface to Knowledge GraphNatural Language Interface to Knowledge Graph
Natural Language Interface to Knowledge Graph
 
The Next Big Thing in AI - Causality
The Next Big Thing in AI - CausalityThe Next Big Thing in AI - Causality
The Next Big Thing in AI - Causality
 
Building a Cyber Threat Intelligence Knowledge Graph
Building a Cyber Threat Intelligence Knowledge GraphBuilding a Cyber Threat Intelligence Knowledge Graph
Building a Cyber Threat Intelligence Knowledge Graph
 
Knowledge Graphs for Supply Chain Operations.pdf
Knowledge Graphs for Supply Chain Operations.pdfKnowledge Graphs for Supply Chain Operations.pdf
Knowledge Graphs for Supply Chain Operations.pdf
 
Building a Distributed Database with Raft.pdf
Building a Distributed Database with Raft.pdfBuilding a Distributed Database with Raft.pdf
Building a Distributed Database with Raft.pdf
 
Enabling the Computational Future of Biology.pdf
Enabling the Computational Future of Biology.pdfEnabling the Computational Future of Biology.pdf
Enabling the Computational Future of Biology.pdf
 
TypeDB Academy | Inference with Rules
TypeDB Academy | Inference with RulesTypeDB Academy | Inference with Rules
TypeDB Academy | Inference with Rules
 
Beyond SQL - Comparing SQL to TypeQL
Beyond SQL - Comparing SQL to TypeQLBeyond SQL - Comparing SQL to TypeQL
Beyond SQL - Comparing SQL to TypeQL
 
Comparing Semantic Web Technologies to TypeDB
Comparing Semantic Web Technologies to TypeDBComparing Semantic Web Technologies to TypeDB
Comparing Semantic Web Technologies to TypeDB
 
Reasoner, Meet Actors | TypeDB's Native Reasoning Engine
Reasoner, Meet Actors | TypeDB's Native Reasoning EngineReasoner, Meet Actors | TypeDB's Native Reasoning Engine
Reasoner, Meet Actors | TypeDB's Native Reasoning Engine
 
Intro to TypeDB and TypeQL | A strongly-typed database
Intro to TypeDB and TypeQL | A strongly-typed databaseIntro to TypeDB and TypeQL | A strongly-typed database
Intro to TypeDB and TypeQL | A strongly-typed database
 
Graph Databases vs TypeDB | What you can't do with graphs
Graph Databases vs TypeDB | What you can't do with graphsGraph Databases vs TypeDB | What you can't do with graphs
Graph Databases vs TypeDB | What you can't do with graphs
 
Pandora Paper Leaks With TypeDB
 Pandora Paper Leaks With TypeDB Pandora Paper Leaks With TypeDB
Pandora Paper Leaks With TypeDB
 
Strongly Typed Data for Machine Learning
Strongly Typed Data for Machine LearningStrongly Typed Data for Machine Learning
Strongly Typed Data for Machine Learning
 
Open World Robotics
Open World RoboticsOpen World Robotics
Open World Robotics
 
Combining Causal and Knowledge Modeling for Digital Transformation
Combining Causal and Knowledge Modeling for Digital TransformationCombining Causal and Knowledge Modeling for Digital Transformation
Combining Causal and Knowledge Modeling for Digital Transformation
 
How can we complete a Knowledge Graph?
How can we complete a Knowledge Graph?How can we complete a Knowledge Graph?
How can we complete a Knowledge Graph?
 
Text-Mined Data in a Knowledge Graph
Text-Mined Data in a Knowledge GraphText-Mined Data in a Knowledge Graph
Text-Mined Data in a Knowledge Graph
 

Recently uploaded

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfjimielynbastida
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 

Recently uploaded (20)

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdf
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 

Unifying Space Mission Knowledge with NLP & KGs

  • 1. 1 ESA UNCLASSIFIED – For ESA Official Use Only Unifying Space Mission Knowledge with NLP & Knowledge Graphs Dr. Audrey Berquand & Ana Victoria Ladeira 23/08/2022 Disclaimer: The views and opinions expressed in this presentation are those of the speakers and do not necessarily reflect the views and position of ESA.
  • 2. 2 Context – Mission Analysis and Design Example challenge: ESA needs a more effective way of detecting and monitoring potentially dangerous wildfires Mission Operations element DETERMINE: Spacecraft element Orbit and Trajectories Launch element Spacecraft element Instrumentation & Payloads
  • 3. 3 Context – Missions Variety Cassini-Huygens • Powered by nuclear fuel • 6.8m x 4m • Instruments for cosmic dust analysis, plasma spectrometry, visible and ultraviolet light • Included lander to land on Titan, one of Saturn’s moons • 7 years on route, 3 years orbiting Saturn Cubesats • 2kg max • 10cm side cube • Uses mostly off-the-shelf components • Generates around 10W of power for instruments • Very short lived – 1 to 3 years Specifications of Space Missions can vary wildly!
  • 4. 4 Context – Increasing number of missions An increasing number of space missions is being designed and launched. Each mission comes with a large data bundle of reports, presentations, ... © ESA/CNES/Arianespace/Optique Video du CSG/S Martin Problem: How do experts keep-up with all this data, without losing sight of the Bigger Picture?
  • 5. 5 Our vision From scattered and heterogenous information... ...To a structured and unified view of the space ecosystem
  • 6. 6 I. Background II. Approach Summary Language Models LMs applications Knowledge Graphs & Space A manually defined schema Population with the GPT-3 model Our Knowledge Graphs Demo & Use Cases III. Corpus IV. Results V. Discussion
  • 7. 7 ESA UNCLASSIFIED - For ESA Official Use Only 7 BACKGROUND
  • 8. 8 Background – Language Models A Language Model is a probability distribution over words or word sequences. "In space no can hear you …" Scream 0.89 Speak 0.75 … Octopus 0.01 Why should you care about LMs? • Pretrained LMs in Natural Language Processing (NLP) have pushed the limits of language understanding and generation. • It has become a main trend in NLP research • Famous LMs include BERT, RoBERTa, T5, GPT-2, GPT-3, … even SpaceRoBERTa and CosmicRoBERTa
  • 9. 9 Background – LMs Applications in your daily life Code generation Content Generation Headlime.com Debuild Semantic Search Casetext.com
  • 10. 10 Background – LMs Applications Examples 1. Text Summarisation: 3. Text Parser: 2. Text Generation: * These examples were all generated through the OpenAI playground
  • 11. 11 Background – KGs & Space From Engineering Models To Knowledge Graph: Delivering New Insights Into Models – Migrates Engineering Models of CubeSats to a KG NASA’s Space Talent KG helps them find the right space expertise for their projects NASA’s Lessons Learned KG combines NLP and KG to categorize their lessons
  • 12. 12 ESA UNCLASSIFIED – For ESA Official Use Only APPROACH
  • 14. 14 Approach - KG Schema Manually defined to reflect both technical and economical characteristics of missions. Visualised with TypeDB Studio
  • 15. 15 Approach – KG Population 1. Each mission description is parsed with the Davinci engine of the GPT-3 model, through the OpenAI API *In reality, we use the Few-Shot Learning approach, and we have 16 parameters parsed. 16 Parameters Parsed: Entity Attribute Example Mission missionName BIOMASS missionStatus Operational program Earth Explorer objectives determine the amount of biomass and carbon stored in forests launchDate 08/2023 endOfLife 10/2030 Stakeholder StakeholderName (agency, prime Contractor) ESA, NASA, Thales, Airbus,... Entity Attribute Example Instrument instrumentName P-band Synthetic Aperture Radar instrumentStatus Operational instrumentType Hyperspectral camera, SAR measurementApp measure forest biomass Orbit orbitType Sun-synchronous orbitInclination 98 deg orbitAltitude 660 km orbitRepeatCycle 3 days
  • 16. 16 Approach – KG Population 3. Using the Vaticle Python API, insert queries are generated to populate the KG 2. The parsed outputs are saved into a JSON file with the following format:
  • 17. 17 ESA UNCLASSIFIED – For ESA Official Use Only CORPUS
  • 18. 18 Corpus • 1200+ Articles, 895 selected for this project • Each article contains a textual description of mission • Pages do not follow a template nor contain structurec data • 335 missions • Structured tables with information about instruments, agencies, orbit and etc • Maintained by CEOS and ESA EoPortal Directory CEOS EO Handbook Database
  • 19. 19 ESA UNCLASSIFIED – For ESA Official Use Only RESULTS
  • 20. 20 Results – eoPortal Directory Knowledge Graph The description of 237 mission descriptions are parsed. The model provided an output for a majority of the parsing request. Parameter [%] parsed Agencies 100 Mission Objectives 100 Mission Status 99.6 Launch Date 98.7 Program 92.4 Instrument Name 90.7 Orbit Type 89.9 Instrument Applications 86.9 Parameter [%] parsed Instrument Status 85.65 Instrument Type 85.65 Orbit Altitude 81 Prime Contractor 80.6 EOL Date 79.75 Orbit Inclination 78.1 Orbit Repeat Cycle 63.29 Instrument Manufacturer 63.29
  • 21. 21 Results – CEOS Knowledge Graph The description of 335 missions were ingested from the Missions Table in the CEOS DB The description of 936 instruments were ingested from the Instruments Table in the CEOS DB Descriptions were not parsed but directly ingested using the TypeDB Python API given their structured format.
  • 22. 22 Results – Comparing KGs • GPT3 is able to capture certain relationships not present on the CEOS database, like information about who is the prime of certain missions • The GPT3 KG captures way more information about industry in general, CEOS contains more information about agencies • CEOS KG contains more information about other instruments in the mission, while GPT3 only focus on the main instruments • GPT3 could be queried for more instruments in the future • Overall, the two KGs are very different!
  • 23. 23 ESA UNCLASSIFIED - For ESA Official Use Only 23 DEMO
  • 24. 24 Basic Queries (1) Inferring all missions handled by a Prime Contractor: Visualised with TypeDB Studio Console and Graph Outputs:
  • 25. 25 Basic Queries (2) Inferring missions with similar objectives: Outputs: Visualised with TypeDB Studio
  • 26. 26 Results – Use Case 1 – Inference
  • 27. 27 Results – Use Case 2 Collaborating stakeholders were identified using TypeDB’s rules and inference engine. The new relationship can be used to find collaborators that own instruments with desired applications or specifications. For example, we can find ESA partners that own wind measuring instruments: match $sh1 isa stakeholder, has stakeholderName "ESA"; $sh2 isa stakeholder, has stakeholderName $sh2-name; $inst isa instrument, has instrumentName $inst-name; $app isa application, has applicationType contains "wind measurement", has applicationType $apptype; $ownsinst (agency: $sh2, payload: $inst) isa ownsInstrument; $enapp (goal: $app, goalFulfiller: $inst) isa enables; $collab (collaborator: $sh1, collaborator:$sh2) isa collaboratesWith; get $sh2-name; group $sh2-name; count; Partner No of Instruments CNES 4 NOAA 15 JAXA 11 UKSA 2 EUMETSAT 3 NASA 29 Partner No of Instruments nec corporation 1 toshiba corporation 1 NASA 2 TAS 1 Los Alamos national laboratory 1 batc 1 LusoSpace 1 CEOS KG GPT3 KG CEOS KG GPT3 KG
  • 28. 28 Results – Use Case 2 – Combining KGs • Both graphs share some mission names. GPT3 is able to capture contractor information not included on the CEOS database. These relationships and extra stakeholders were added to the CEOS KG to further enrich it. • In the future, a more extensive merge of both graphs will be attempted Class Type GPT3 CEOS CEOS+GPT3 Entity stakeholder 389 86 389 Relationship ownsInstrument 165 1117 1154 Relationship isPrimeOf 193 0 193
  • 29. 29 ESA UNCLASSIFIED – For ESA Official Use Only DISCUSSION & CONCLUSION
  • 30. 30 Discussion GPT-3 limitations: • Only takes 2k tokens as input • Human validation is often necessary • Not open-source Positive points: • High parsing rate (86% over all parameters) • Encouraging results • Crucial support in populating a KG from text
  • 31. 31 Future Work Parsing the whole EoDirectory page with GPT3 instead of only first 2000 tokens Parsing the whole EoDirectory page with GPT3 instead of only first 2000 tokens Using Open Source models like T5 or BLOOM instead of GPT3 Align the KG with the ESA Space System Ontology Exploring different KG merging techniques to combine both KGs developed for this study Adapting GPT3 script to extract more than one instance of each variable where applicable
  • 32. 32 Conclusion Should we trust the GPT-3 models outputs? Can Language Models support our vision of providing a unified overview of the space ecosystem? The generated data should be validated by humans. However, it is impressive how the model trained on general data understands domain-specific concepts, Parsing with LMs is a tremendous time saver. LMs' performances are still improving, and more open-source models are appearing. So, definitely yes!
  • 33. 33 33 The End Thank you for your attention, For more information, see our paper: "From Mission Description to Knowledge Graph: Applying Transformer- based models to map knowledge from publicly available satellite datasets" to be presented at the 10th International Systems & Concurrent Engineering for Space Applications (SECESA 2022) Contact: Audrey.berquand@esa.int Anavictoria.ladeira@esa.int
  • 34. 34 ESA UNCLASSIFIED - For ESA Official Use Only 34 Extra slides
  • 35. 35 Approach – Validation of the GPT-3 outputs For a subset of missions, we compared the generated text of the GPT-3 model with the CEOS database (manually verified). The CEOS data is used as reference text. Below are the BLEU and ROUGE scores: The BLEU and ROUGE scores are not always adapted for comparing strings, so we also used sentence-transformer model and cosine similarity for the objective and the application parameters: