BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data

Big Data Value Association
Big Data Value AssociationBig Data Value Association
Rocking the boat with big
data
www.bigdataocean.eu
Dr. Spiros Mouzakitis (NTUA)
Deputy Project Manager
GiannisTsapelas(NTUA)
Senior Researcher
Around 80% of global trade by volume is carried
by sEA
….and around 70% of global
trade by value
CHALLEN
GESo Undeveloped sharing of Blue Data between
enterprises and entities of the maritime domain
and other domains
o Lack of agreed standards and formats
o Huge potential from cross-sectorial blue data
applications – still unexploited
o Out-of-the-box Big Data solution that enables
advanced queries and analytics on cross-sector
data - missing
Develop a Maritime Big Data platform
that delivers out-of-the-box, value-added data and
analytic services for maritime applications
by exploiting cross-sector data streams
4
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BigDataOcean platform (services)
Find maritime data
Query / interlink datasets Compose analytic services
Visualize datasets
Create (real-time) dashboards
Request on-demand services
Port
Authorities
Maritime
Research
Centers
Ship-owning
companies
Maritime
software
suppliers
Service
providers at
sea level
Maritime
advisory firms
BigDataOcean end-user applications
Vessel Fault
Detection,
Predictive
Maintenance
and Fuel
Consumption
Reduction
Maritime
security and
anomaly
detection
Oil spill
modeling
Wave power
generation
8BDV PPP Technical Committee Meeting
Case 1 - Fault Prediction & Proactive Maintenance
and Fuel Consumption
9
Case 1 - Fault Prediction & Proactive Maintenance
and Fuel Consumption
10
• Damage and mechanical failures detection and predictive
maintenance of vessel equipment
• Investigation of the impact of the environmental conditions
and the operational decisions taken on the vessel's fuel
consumption
Goal
• Ship owners, Maritime EquipmentConstructors
Stakeholders
BigDataOcean Solution
Analytics and knowledge
base about fuel
consumption and repairs
Prediction models for
maintenance and fuel
consumption
Maritime Regulations, Flag
& Ship Classification
Provisions
Plant Maintenance
System for Main Engine
& spare parts
Vessel
routes
In-situ Observations
Cross-domain
Forecast Data
Port information
BigDataOcean
Solution
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
Business Benefits
● Shipping companies and Maritime Equipment Constructors
 Minimum repairs, maintenance cost and fuel consumption
 Maximum vessels’ use and financial benefit
 Minimize environment impact
 Reliability and innovation
 Advanced Data analytics related to maintenance and fuel
consumption
Case 2 – Mare protection – Oil Spill dispersion
forecast
16
Case 2 – Mare protection – Oil Spill dispersion
forecast
17
• Provide to the end users oil spill drift forecasting and
simulation services for the marine environment
• Enhance the efficiency in managing oil spill pollution risks.
Goal
• Emergency Response Companies, National Entities
(PublicAuthorities), NGOs, Marine Research Institutes,
Shipping companies and Oil drilling companies
Stakeholders
Natura /
Protecte
d areas
In-situ Observations
BigDataOcean Solution
Graphical output
Cross-domain
Forecast Data
POSEIDON
OSM
Oil spill scenario
submission
Location, Rate,
Nature & characteristics
Ocean Circulation
Forecast
Weather
Forecast
BigDataOcean
Solution
AIS
Data
BigDataOcean
Wave
Forecast
Oil Spill Dispersion Forecast
Acquisition
High Risk PollutionAreas
UnderwaterAccident
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
Business Benefits
● Extended knowledge, models and enriched datasets
● New products addressed to environment protection
organizations and maritime authorities for rapid intervention
against oil spills in the sea
● Control and limit impact and damage on the coast and on
essential resources and structures.
● Efficiency in the protection of the marine environment and of
the marine life.
Case 3 – Wave Power as Clean Energy Source
23
Case 3 – Wave Power as Clean Energy Source
24
• Evaluation of wave energy potential and contribution to
development of wave energy solutions.
Goal
• Offshore Renewables Service Providers, Offshore Pilot
Zone Concessionaires,WEC developers, Energy
Producers, Hydrographic Centres
Stakeholders
BigDataOcean Solution
Waves In-situ
Observations
Cross-domain
Vessel
routes
Port
s
Protected
areas
Wave models
output
Instruments
Data
BigDataOcean
Solution
Wave ResourceAssessment
Wave Energy study and
Forecast
DataVisualisations
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
Business Benefits
● Wave resource characterization in your selected location or
area, based in historical data.
● Wave forecast.
● Assessment of Wave Energy Converters energy generation,
allowing to compare your device with others.
● Forecast of energy generation for your WEC device.
Case 4 – Security and anomaly path detection
Case 4 – Security and anomaly path detection
• Identify vessel routes based on their motion patterns to act
proactively and minimise threats at sea.
Goal
• Port authorities, Ocean Observatories, Port/Cargo
Community systems,Transport and Logistics companies,
Harbour Pilots and Maritime Consultants
Stakeholders
BigDataOcean solution
AIS
Anomaly Detection
BigDataOcean
Solution
Visualization
Anomaly
detection
services
Analytics
AIS
data
Weather Data
Location of Sea Ports
List of “High Risk” Vessels
List of security
incidents & vessels
implicated
Nautical Information Maps
Feedback from vessel’s
crew & domain experts
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data
Business Benefits
● Effectively handle the information volume from tracking
technologies and AIS data
● identify patterns of behavior and vessel risk profile
● proactively minimize the impact of possible threats
BigDataOcean Consortium
35
35
Development
Semantics
Pilot
Pilot
PilotPilot
Requirements
Exploitation
Coordination &
Development
Pilot
Timeplan
Analysis and Development
2017 6/2019
Start
MS4:
Prototype
MS2:
Requirements
and needs
Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2
MS1:
Maritime data
value chain
definition
MS3:
Methodology
& Architecture
MS5: Final
Platform
MS6:
Business
Plan,
Lessons
Learnt
Evaluation
Market preparation
We are here
Lessons learned: exploitation
37
BDO Commercial Partnership for the platform
1. BDO Platform Services
2. BDO End-UsersApplication Services
3. BDO On-Demand Data Services and custom solutions
4. BDO Non-Technical Package
• Training
• Consulting
• Data science coaching
• Contract deals with maritime companies
• Focus on B2B applications
Semantic Challenges
● Plethora of file formats and metadata standards coming from diverse data sources
● Ability to perform advanced queries that combine those big datasets
● Enable ad hoc queries
Our Approach
● Automatic ingestion system to a harmonized, semantically aware schema (BDO
canonical Model)
● Based on DCAT, NETCDF convention standards (cfconventions.org)
Performance Challenges
● Performance issues
 POSTGRESQL and relational databases typically used in legacy maritime applications –
Serious scalability issues for the size of the datasets
 NoSQL databases -> Good performance for simple queries, but bad performance for
queries that combine data
 Distributed, wide column stores (e.g. Cassandra) -> better optimised for known queries
Our Approach
● Presto with Apache Hive
Lessons learned: current solution
Solution for Query Designer
queries
Solution for further query
optimization
● Caching JOIN queries performed by
users
● Pre-join datasets for pilot
applications
● Adoption of Apache Parquet storage
and ORF file formats
HDFS
Query performance over million of rows: from 5 minutes to 5 seconds!
BDO Architecture
Demo
www.bigdataocean.eu
Questions
www.bigdataocean.eu
1 of 43

Recommended

Dstl Academic Engagement (Prof. Tom McCutcheon) by
Dstl Academic Engagement (Prof. Tom McCutcheon)Dstl Academic Engagement (Prof. Tom McCutcheon)
Dstl Academic Engagement (Prof. Tom McCutcheon)scirexcenter
688 views10 slides
Collaborative Research with UK MOD - an Academic's Experience ((John Fitzgerald) by
Collaborative Research with UK MOD - an Academic's Experience ((John Fitzgerald)Collaborative Research with UK MOD - an Academic's Experience ((John Fitzgerald)
Collaborative Research with UK MOD - an Academic's Experience ((John Fitzgerald)scirexcenter
578 views19 slides
Accelerator Autonomous last mile resupply Challenge overview - 23 May 2017 by
Accelerator Autonomous last mile resupply Challenge overview - 23 May 2017Accelerator Autonomous last mile resupply Challenge overview - 23 May 2017
Accelerator Autonomous last mile resupply Challenge overview - 23 May 2017Heather-Fiona Egan
3.4K views33 slides
Metis at Open Coffee Athens XCIV by
Metis at Open Coffee Athens XCIVMetis at Open Coffee Athens XCIV
Metis at Open Coffee Athens XCIVOpen Coffee Greece
5.2K views29 slides
Irelands Digital Ocean Programme - Developing Digital Twin Capabilities.pptx by
Irelands Digital Ocean Programme - Developing Digital Twin Capabilities.pptxIrelands Digital Ocean Programme - Developing Digital Twin Capabilities.pptx
Irelands Digital Ocean Programme - Developing Digital Twin Capabilities.pptxEoin O'Grady
6 views12 slides

More Related Content

Similar to BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data

Vessel Efficiency competition company elevator pitches - London by
Vessel Efficiency competition company elevator pitches - LondonVessel Efficiency competition company elevator pitches - London
Vessel Efficiency competition company elevator pitches - LondonKTN
795 views25 slides
SeaDataCloud - Introduction to SeaDataNet infrastructure by
SeaDataCloud - Introduction to SeaDataNet infrastructureSeaDataCloud - Introduction to SeaDataNet infrastructure
SeaDataCloud - Introduction to SeaDataNet infrastructureEUDAT
104 views20 slides
DSD-INT 2019 Global Data Services and Analysis Frameworks-Luijendijk by
DSD-INT 2019 Global Data Services and Analysis Frameworks-LuijendijkDSD-INT 2019 Global Data Services and Analysis Frameworks-Luijendijk
DSD-INT 2019 Global Data Services and Analysis Frameworks-LuijendijkDeltares
124 views22 slides
The Roadmap to a Lifesaving Digital Ecosystem by
The Roadmap to a Lifesaving Digital EcosystemThe Roadmap to a Lifesaving Digital Ecosystem
The Roadmap to a Lifesaving Digital EcosystemWilliam Roberts
827 views45 slides
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.Cau by
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.CauProgetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.Cau
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.CauSardegna Ricerche
736 views54 slides
Handling Big Data in Ship Performance & Navigation Monitoring. by
Handling Big Data in Ship Performance & Navigation Monitoring.Handling Big Data in Ship Performance & Navigation Monitoring.
Handling Big Data in Ship Performance & Navigation Monitoring.Lokukaluge Prasad Perera
783 views34 slides

Similar to BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data(20)

Vessel Efficiency competition company elevator pitches - London by KTN
Vessel Efficiency competition company elevator pitches - LondonVessel Efficiency competition company elevator pitches - London
Vessel Efficiency competition company elevator pitches - London
KTN 795 views
SeaDataCloud - Introduction to SeaDataNet infrastructure by EUDAT
SeaDataCloud - Introduction to SeaDataNet infrastructureSeaDataCloud - Introduction to SeaDataNet infrastructure
SeaDataCloud - Introduction to SeaDataNet infrastructure
EUDAT104 views
DSD-INT 2019 Global Data Services and Analysis Frameworks-Luijendijk by Deltares
DSD-INT 2019 Global Data Services and Analysis Frameworks-LuijendijkDSD-INT 2019 Global Data Services and Analysis Frameworks-Luijendijk
DSD-INT 2019 Global Data Services and Analysis Frameworks-Luijendijk
Deltares124 views
The Roadmap to a Lifesaving Digital Ecosystem by William Roberts
The Roadmap to a Lifesaving Digital EcosystemThe Roadmap to a Lifesaving Digital Ecosystem
The Roadmap to a Lifesaving Digital Ecosystem
William Roberts827 views
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.Cau by Sardegna Ricerche
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.CauProgetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.Cau
Progetto INNO ed esempi di applicazioni nel campo della GEOMATICA - P.Cau
Sardegna Ricerche736 views
Ocean Data Factory - Application for Funding by Robin Teigland
Ocean Data Factory - Application for FundingOcean Data Factory - Application for Funding
Ocean Data Factory - Application for Funding
Robin Teigland953 views
Big Data in Oil and Gas: How to Tap Its Full Potential by Hitachi Vantara
Big Data in Oil and Gas: How to Tap Its Full PotentialBig Data in Oil and Gas: How to Tap Its Full Potential
Big Data in Oil and Gas: How to Tap Its Full Potential
Hitachi Vantara7.6K views
Introduction to the GSDI Marine SDI Best Practice Webinar by GSDI Association
Introduction to the GSDI Marine SDI Best Practice WebinarIntroduction to the GSDI Marine SDI Best Practice Webinar
Introduction to the GSDI Marine SDI Best Practice Webinar
GSDI Association163 views
TGS Corporate Capabilities by TGS
TGS Corporate CapabilitiesTGS Corporate Capabilities
TGS Corporate Capabilities
TGS642 views
Offshore lytics rolloos_midih_presentation_oc2 by MIDIH_EU
Offshore lytics rolloos_midih_presentation_oc2Offshore lytics rolloos_midih_presentation_oc2
Offshore lytics rolloos_midih_presentation_oc2
MIDIH_EU110 views
Aerial Data Management and The Digital Enterprise by Advisian
Aerial Data Management and The Digital EnterpriseAerial Data Management and The Digital Enterprise
Aerial Data Management and The Digital Enterprise
Advisian225 views
Using Data Integration to Deliver Intelligence to Anyone, Anywhere by Safe Software
Using Data Integration to Deliver Intelligence to Anyone, AnywhereUsing Data Integration to Deliver Intelligence to Anyone, Anywhere
Using Data Integration to Deliver Intelligence to Anyone, Anywhere
Safe Software1.3K views

More from Big Data Value Association

Data Privacy, Security in personal data sharing by
Data Privacy, Security in personal data sharingData Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharingBig Data Value Association
446 views7 slides
Key Modules for a trsuted and privacy preserving personal data marketplace by
Key Modules for a trsuted and privacy preserving personal data marketplaceKey Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplaceBig Data Value Association
142 views11 slides
GDPR and Data Ethics considerations in personal data sharing by
GDPR and Data Ethics considerations in personal data sharingGDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharingBig Data Value Association
151 views12 slides
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an... by
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Big Data Value Association
234 views3 slides
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy by
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyThree pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyBig Data Value Association
168 views29 slides
Market into context - Three pillars for building a Smart Data Ecosystem: Trus... by
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Big Data Value Association
159 views15 slides

More from Big Data Value Association(20)

Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an... by Big Data Value Association
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy by Big Data Value Association
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyThree pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Market into context - Three pillars for building a Smart Data Ecosystem: Trus... by Big Data Value Association
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ... by Big Data Value Association
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie... by Big Data Value Association
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe... by Big Data Value Association
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar by Big Data Value Association
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector WebinarBigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi... by Big Data Value Association
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli... by Big Data Value Association
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...

Recently uploaded

Deep analytics via learning to reason by
Deep analytics via learning to reasonDeep analytics via learning to reason
Deep analytics via learning to reasonDeakin University
5 views57 slides
Product Research sample.pdf by
Product Research sample.pdfProduct Research sample.pdf
Product Research sample.pdfAllenSingson
35 views29 slides
META.pptx by
META.pptxMETA.pptx
META.pptxvasanthan19012003
7 views10 slides
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf by
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf10urkyr34
7 views259 slides
GDG Community Day 2023 - Interpretable ML in production by
GDG Community Day 2023 - Interpretable ML in productionGDG Community Day 2023 - Interpretable ML in production
GDG Community Day 2023 - Interpretable ML in productionSARADINDU SENGUPTA
5 views19 slides
Customer Data Cleansing Project.pptx by
Customer Data Cleansing Project.pptxCustomer Data Cleansing Project.pptx
Customer Data Cleansing Project.pptxNat O
6 views23 slides

Recently uploaded(20)

Product Research sample.pdf by AllenSingson
Product Research sample.pdfProduct Research sample.pdf
Product Research sample.pdf
AllenSingson35 views
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf by 10urkyr34
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf
10urkyr347 views
GDG Community Day 2023 - Interpretable ML in production by SARADINDU SENGUPTA
GDG Community Day 2023 - Interpretable ML in productionGDG Community Day 2023 - Interpretable ML in production
GDG Community Day 2023 - Interpretable ML in production
Customer Data Cleansing Project.pptx by Nat O
Customer Data Cleansing Project.pptxCustomer Data Cleansing Project.pptx
Customer Data Cleansing Project.pptx
Nat O6 views
[DSC Europe 23] Ilija Duni - How Foursquare Builds Meaningful Bridges Between... by DataScienceConferenc1
[DSC Europe 23] Ilija Duni - How Foursquare Builds Meaningful Bridges Between...[DSC Europe 23] Ilija Duni - How Foursquare Builds Meaningful Bridges Between...
[DSC Europe 23] Ilija Duni - How Foursquare Builds Meaningful Bridges Between...
Best Home Security Systems.pptx by mogalang
Best Home Security Systems.pptxBest Home Security Systems.pptx
Best Home Security Systems.pptx
mogalang9 views
Games, Queries, and Argumentation Frameworks: Time for a Family Reunion by Bertram Ludäscher
Games, Queries, and Argumentation Frameworks: Time for a Family ReunionGames, Queries, and Argumentation Frameworks: Time for a Family Reunion
Games, Queries, and Argumentation Frameworks: Time for a Family Reunion
Analytics Center of Excellence | Data CoE |Analytics CoE| WNS Triange by RNayak3
Analytics Center of Excellence | Data CoE |Analytics CoE| WNS TriangeAnalytics Center of Excellence | Data CoE |Analytics CoE| WNS Triange
Analytics Center of Excellence | Data CoE |Analytics CoE| WNS Triange
RNayak35 views
[DSC Europe 23] Irena Cerovic - AI in International Development.pdf by DataScienceConferenc1
[DSC Europe 23] Irena Cerovic - AI in International Development.pdf[DSC Europe 23] Irena Cerovic - AI in International Development.pdf
[DSC Europe 23] Irena Cerovic - AI in International Development.pdf
Listed Instruments Survey 2022.pptx by secretariat4
Listed Instruments Survey  2022.pptxListed Instruments Survey  2022.pptx
Listed Instruments Survey 2022.pptx
secretariat4130 views
4_4_WP_4_06_ND_Model.pptx by d6fmc6kwd4
4_4_WP_4_06_ND_Model.pptx4_4_WP_4_06_ND_Model.pptx
4_4_WP_4_06_ND_Model.pptx
d6fmc6kwd47 views
Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language... by patiladiti752
Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language...Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language...
Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language...
patiladiti7528 views
K-Drama Recommendation Using Python by FridaPutriassa
K-Drama Recommendation Using PythonK-Drama Recommendation Using Python
K-Drama Recommendation Using Python
FridaPutriassa7 views

BDVe Webinar Series - Big Data Ocean - Rocking the boat with Big Data

  • 1. Rocking the boat with big data www.bigdataocean.eu Dr. Spiros Mouzakitis (NTUA) Deputy Project Manager GiannisTsapelas(NTUA) Senior Researcher
  • 2. Around 80% of global trade by volume is carried by sEA ….and around 70% of global trade by value
  • 3. CHALLEN GESo Undeveloped sharing of Blue Data between enterprises and entities of the maritime domain and other domains o Lack of agreed standards and formats o Huge potential from cross-sectorial blue data applications – still unexploited o Out-of-the-box Big Data solution that enables advanced queries and analytics on cross-sector data - missing
  • 4. Develop a Maritime Big Data platform that delivers out-of-the-box, value-added data and analytic services for maritime applications by exploiting cross-sector data streams 4
  • 6. BigDataOcean platform (services) Find maritime data Query / interlink datasets Compose analytic services Visualize datasets Create (real-time) dashboards Request on-demand services
  • 8. BigDataOcean end-user applications Vessel Fault Detection, Predictive Maintenance and Fuel Consumption Reduction Maritime security and anomaly detection Oil spill modeling Wave power generation 8BDV PPP Technical Committee Meeting
  • 9. Case 1 - Fault Prediction & Proactive Maintenance and Fuel Consumption 9
  • 10. Case 1 - Fault Prediction & Proactive Maintenance and Fuel Consumption 10 • Damage and mechanical failures detection and predictive maintenance of vessel equipment • Investigation of the impact of the environmental conditions and the operational decisions taken on the vessel's fuel consumption Goal • Ship owners, Maritime EquipmentConstructors Stakeholders
  • 11. BigDataOcean Solution Analytics and knowledge base about fuel consumption and repairs Prediction models for maintenance and fuel consumption Maritime Regulations, Flag & Ship Classification Provisions Plant Maintenance System for Main Engine & spare parts Vessel routes In-situ Observations Cross-domain Forecast Data Port information BigDataOcean Solution
  • 15. Business Benefits ● Shipping companies and Maritime Equipment Constructors  Minimum repairs, maintenance cost and fuel consumption  Maximum vessels’ use and financial benefit  Minimize environment impact  Reliability and innovation  Advanced Data analytics related to maintenance and fuel consumption
  • 16. Case 2 – Mare protection – Oil Spill dispersion forecast 16
  • 17. Case 2 – Mare protection – Oil Spill dispersion forecast 17 • Provide to the end users oil spill drift forecasting and simulation services for the marine environment • Enhance the efficiency in managing oil spill pollution risks. Goal • Emergency Response Companies, National Entities (PublicAuthorities), NGOs, Marine Research Institutes, Shipping companies and Oil drilling companies Stakeholders
  • 18. Natura / Protecte d areas In-situ Observations BigDataOcean Solution Graphical output Cross-domain Forecast Data POSEIDON OSM Oil spill scenario submission Location, Rate, Nature & characteristics Ocean Circulation Forecast Weather Forecast BigDataOcean Solution AIS Data BigDataOcean Wave Forecast Oil Spill Dispersion Forecast Acquisition High Risk PollutionAreas UnderwaterAccident
  • 22. Business Benefits ● Extended knowledge, models and enriched datasets ● New products addressed to environment protection organizations and maritime authorities for rapid intervention against oil spills in the sea ● Control and limit impact and damage on the coast and on essential resources and structures. ● Efficiency in the protection of the marine environment and of the marine life.
  • 23. Case 3 – Wave Power as Clean Energy Source 23
  • 24. Case 3 – Wave Power as Clean Energy Source 24 • Evaluation of wave energy potential and contribution to development of wave energy solutions. Goal • Offshore Renewables Service Providers, Offshore Pilot Zone Concessionaires,WEC developers, Energy Producers, Hydrographic Centres Stakeholders
  • 25. BigDataOcean Solution Waves In-situ Observations Cross-domain Vessel routes Port s Protected areas Wave models output Instruments Data BigDataOcean Solution Wave ResourceAssessment Wave Energy study and Forecast DataVisualisations
  • 28. Business Benefits ● Wave resource characterization in your selected location or area, based in historical data. ● Wave forecast. ● Assessment of Wave Energy Converters energy generation, allowing to compare your device with others. ● Forecast of energy generation for your WEC device.
  • 29. Case 4 – Security and anomaly path detection
  • 30. Case 4 – Security and anomaly path detection • Identify vessel routes based on their motion patterns to act proactively and minimise threats at sea. Goal • Port authorities, Ocean Observatories, Port/Cargo Community systems,Transport and Logistics companies, Harbour Pilots and Maritime Consultants Stakeholders
  • 31. BigDataOcean solution AIS Anomaly Detection BigDataOcean Solution Visualization Anomaly detection services Analytics AIS data Weather Data Location of Sea Ports List of “High Risk” Vessels List of security incidents & vessels implicated Nautical Information Maps Feedback from vessel’s crew & domain experts
  • 34. Business Benefits ● Effectively handle the information volume from tracking technologies and AIS data ● identify patterns of behavior and vessel risk profile ● proactively minimize the impact of possible threats
  • 36. Timeplan Analysis and Development 2017 6/2019 Start MS4: Prototype MS2: Requirements and needs Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 MS1: Maritime data value chain definition MS3: Methodology & Architecture MS5: Final Platform MS6: Business Plan, Lessons Learnt Evaluation Market preparation We are here
  • 37. Lessons learned: exploitation 37 BDO Commercial Partnership for the platform 1. BDO Platform Services 2. BDO End-UsersApplication Services 3. BDO On-Demand Data Services and custom solutions 4. BDO Non-Technical Package • Training • Consulting • Data science coaching • Contract deals with maritime companies • Focus on B2B applications
  • 38. Semantic Challenges ● Plethora of file formats and metadata standards coming from diverse data sources ● Ability to perform advanced queries that combine those big datasets ● Enable ad hoc queries Our Approach ● Automatic ingestion system to a harmonized, semantically aware schema (BDO canonical Model) ● Based on DCAT, NETCDF convention standards (cfconventions.org)
  • 39. Performance Challenges ● Performance issues  POSTGRESQL and relational databases typically used in legacy maritime applications – Serious scalability issues for the size of the datasets  NoSQL databases -> Good performance for simple queries, but bad performance for queries that combine data  Distributed, wide column stores (e.g. Cassandra) -> better optimised for known queries Our Approach ● Presto with Apache Hive
  • 40. Lessons learned: current solution Solution for Query Designer queries Solution for further query optimization ● Caching JOIN queries performed by users ● Pre-join datasets for pilot applications ● Adoption of Apache Parquet storage and ORF file formats HDFS Query performance over million of rows: from 5 minutes to 5 seconds!

Editor's Notes

  1. Using the capabilities of the big data ocean platform we have created 4 applications that deal with crucial challenges for the maritime industry – these applications are our flagship products to kickstart promote the platform
  2. Its main goal is to support the first and most important step of the wave energy convertors. Where is the best place to place the WEC and and it’s the potential of the installation depending on the location at sea. Its stakeholders are….