0
Cautionary Note
The companies in which Royal Dutch Shell plc directly and indirectly owns investments are separate legal entities. In this presentation “Shell”, “Shell group” and “Royal Dutch Shell” are
sometimes used for convenience where references are made to Royal Dutch Shell plc and its subsidiaries in general. Likewise, the words “we”, “us” and “our” are also used to refer to Royal
Dutch Shell plc and subsidiaries in general or to those who work for them. These terms are also used where no useful purpose is served by identifying the particular entity or entities.
‘‘Subsidiaries’’, “Shell subsidiaries” and “Shell companies” as used in this presentation refer to entities over which Royal Dutch Shell plc either directly or indirectly has control. Entities and
unincorporated arrangements over which Shell has joint control are generally referred to as “joint ventures” and “joint operations”, respectively. Entities over which Shell has significant influence
but neither control nor joint control are referred to as “associates”. The term “Shell interest” is used for convenience to indicate the direct and/or indirect ownership interest held by Shell in an
entity or unincorporated joint arrangement, after exclusion of all third-party interest.
This presentation contains forward-looking statements (within the meaning of the U.S. Private Securities Litigation Reform Act of 1995) concerning the financial condition, results of operations and
businesses of Royal Dutch Shell. All statements other than statements of historical fact are, or may be deemed to be, forward-looking statements. Forward-looking statements are statements of
future expectations that are based on management’s current expectations and assumptions and involve known and unknown risks and uncertainties that could cause actual results, performance
or events to differ materially from those expressed or implied in these statements. Forward-looking statements include, among other things, statements concerning the potential exposure of Royal
Dutch Shell to market risks and statements expressing management’s expectations, beliefs, estimates, forecasts, projections and assumptions. These forward-looking statements are identified by
their use of terms and phrases such as “aim”, “ambition’, ‘‘anticipate’’, ‘‘believe’’, ‘‘could’’, ‘‘estimate’’, ‘‘expect’’, ‘‘goals’’, ‘‘intend’’, ‘‘may’’, ‘‘objectives’’, ‘‘outlook’’, ‘‘plan’’, ‘‘probably’’,
‘‘project’’, ‘‘risks’’, “schedule”, ‘‘seek’’, ‘‘should’’, ‘‘target’’, ‘‘will’’ and similar terms and phrases. There are a number of factors that could affect the future operations of Royal Dutch Shell and
could cause those results to differ materially from those expressed in the forward-looking statements included in this [report], including (without limitation): (a) price fluctuations in crude oil and
natural gas; (b) changes in demand for Shell’s products; (c) currency fluctuations; (d) drilling and production results; (e) reserves estimates; (f) loss of market share and industry competition; (g)
environmental and physical risks; (h) risks associated with the identification of suitable potential acquisition properties and targets, and successful negotiation and completion of such transactions;
(i) the risk of doing business in developing countries and countries subject to international sanctions; (j) legislative, fiscal and regulatory developments including regulatory measures addressing
climate change; (k) economic and financial market conditions in various countries and regions; (l) political risks, including the risks of expropriation and renegotiation of the terms of contracts
with governmental entities, delays or advancements in the approval of projects and delays in the reimbursement for shared costs; and (m) changes in trading conditions. No assurance is
provided that future dividend payments will match or exceed previous dividend payments. All forward-looking statements contained in this [report] are expressly qualified in their entirety by the
cautionary statements contained or referred to in this section. Readers should not place undue reliance on forward-looking statements. Additional risk factors that may affect future results are
contained in Royal Dutch Shell’s 20-F for the year ended December 31, 2017 (available at www.shell.com/investor and www.sec.gov ). These risk factors also expressly qualify all forward
looking statements contained in this presentation and should be considered by the reader. Each forward-looking statement speaks only as of the date of this presentation, 03-OCT-2018. Neither
Royal Dutch Shell plc nor any of its subsidiaries undertake any obligation to publicly update or revise any forward-looking statement as a result of new information, future events or other
information. In light of these risks, results could differ materially from those stated, implied or inferred from the forward-looking statements contained in this presentation.
We may have used certain terms, such as resources, in this presentation that United States Securities and Exchange Commission (SEC) strictly prohibits us from including in our filings with the
SEC. U.S. Investors are urged to consider closely the disclosure in our Form 20-F, File No 1-32575, available on the SEC website www.sec.gov.
0
Copyright of Shell International
Scaling Advanced Analytics @
Shell
Oct 2018
Krishna Somasundaram – Software Engineering Architect
Bryce Bartmann – Senior Data Engineer
2
Shell’s Digital Strategy
OPERATING MODEL
AND WAYS OF
WORKING
CAPABILITIES
LEADERSHIP, MIND-
SETS AND
BEHAVIOUR
UNDERPINNING
CRITICAL SUCCESS
FACTORS
BUSINESSES
OWN DIGITAL
ACT OUR WAY
INTO THE
FUTURE
BUILD IN-
HOUSE
CAPABILITY
CUSTOMER/USE
R IS CENTRAL
FIVE DIGITAL DESIGN PRINCIPLES
A coherent approach across Shell to realise and accelerate value through digital
led by business and supported by Digital COE
DATA IS AN
ASSET
3
Role of the Data Science CoE
1
Select Foundational
Technologies
2 Showcase ‘Art of the Possible’ 3
Facilitate Best Practice
Sharing across Shell
Strategic
Objective
Enablers
Innovation Remit
Core Team with
Technical &
Commercial Skillset
Development of
Digital
Networks
Creation of Digital
Labs for
Experimentation
External Partnerships
and Developing the
Eco System
4
From an idea to an embedded business capability
6 October, 2018 4
Business
Needs,
Opportunities
& Challenges
MVP R2 R3
R&D
Design
Sprint
Proof of
Concept
PROBLEMS WORTH SOLVING LEARNING AND DELIVERING FAST TOGETHER DELIVERING VALUE
Digital IT
5
Digitalisation
playground & PoC
incubator sandbox
environment
5
Shiny
500+ users
across Shell
Businesses
Digitalisation Lab
We want as close
integration between
all offerings as
possible
66
Operationalise - Databricks
Lab Support
7
Making
the most of
existing
data
Rightsizing
inventory
Copyright of Shell Global Solutions International B.V.
8
8Footer October 18Copyright of Shell Global Solutions International B.V.
Machine
Learning to
enable ‘grey
stock’
identification
Pipe
Counting
9
Augmenting pipe counting & grey stock identification using MV
techniques
Primary value-flow:
February 2018
Collect Data
Store in
Public Cloud
Apply Machine
Learning and
leverage Machine
Vision
Create actionable
insight
Support
Decision Making
leading to
Value Creation
Algorithm performs with >90% accuracy
10
1
0
Footer October
18
Copyright of Shell Global Solutions International B.V.
Optimizing
HSSE
Video
Analytics for
incident
tracking &
management
11September 2016 11
12
September 201612
Combination
with Robotics
Asset
monitoring
13
Business challenge: how can we 1) consistently identify equipment
& 2) maintenance history without significant manual effort?
13
LABOUR &
OPEX COST
REDUCTION
PRODUCTIVIT
Y INCREASE
SAFETY
INCREAS
E
14
Leak Detection
Volumetric
Abnormal Heat Signatures
Site Security and Surrounding Conditions
Corrosion Detection
Plume Detection
September 2016 14
Other Machine Vision Possibilities
Scaling Advanced Analytics at Shell with Krishna Somasundaram and Bryce Bartmann
Scaling Advanced Analytics at Shell with Krishna Somasundaram and Bryce Bartmann

More Related Content

PDF
Putting the Ops in DataOps: Orchestrate the Flow of Data Across Data Pipelines
PDF
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
PPTX
DW Migration Webinar-March 2022.pptx
PPTX
Demystifying Data Warehouse as a Service
PPTX
Snowflake Overview
PDF
Snowflake for Data Engineering
PDF
Azure Hybid
PPTX
Best Practices in DataOps: How to Create Agile, Automated Data Pipelines
Putting the Ops in DataOps: Orchestrate the Flow of Data Across Data Pipelines
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
DW Migration Webinar-March 2022.pptx
Demystifying Data Warehouse as a Service
Snowflake Overview
Snowflake for Data Engineering
Azure Hybid
Best Practices in DataOps: How to Create Agile, Automated Data Pipelines

What's hot (20)

PDF
Data Platform Architecture Principles and Evaluation Criteria
PDF
Modernizing to a Cloud Data Architecture
PDF
Building a Logical Data Fabric using Data Virtualization (ASEAN)
PDF
SDWAN.pdf
PDF
Building Data Quality pipelines with Apache Spark and Delta Lake
PDF
DataOps - The Foundation for Your Agile Data Architecture
PDF
Data Mess to Data Mesh | Jay Kreps, CEO, Confluent | Kafka Summit Americas 20...
PPTX
Design Principles for a Modern Data Warehouse
PDF
Modern Data Flow
PPTX
Building the Data Lake with Azure Data Factory and Data Lake Analytics
PPTX
Getting Started with ThousandEyes Proof of Concepts
PDF
Data Mesh Part 4 Monolith to Mesh
PPTX
Data platform modernization with Databricks.pptx
PDF
Intuit's Data Mesh - Data Mesh Leaning Community meetup 5.13.2021
PDF
Design Guidelines for Data Mesh and Decentralized Data Organizations
PPTX
Data ops in practice
PDF
A Cloud Journey - Move to the Oracle Cloud
PDF
Lambda Architecture in the Cloud with Azure Databricks with Andrei Varanovich
PPTX
Azure data platform overview
PDF
Why Data Virtualization? An Introduction
Data Platform Architecture Principles and Evaluation Criteria
Modernizing to a Cloud Data Architecture
Building a Logical Data Fabric using Data Virtualization (ASEAN)
SDWAN.pdf
Building Data Quality pipelines with Apache Spark and Delta Lake
DataOps - The Foundation for Your Agile Data Architecture
Data Mess to Data Mesh | Jay Kreps, CEO, Confluent | Kafka Summit Americas 20...
Design Principles for a Modern Data Warehouse
Modern Data Flow
Building the Data Lake with Azure Data Factory and Data Lake Analytics
Getting Started with ThousandEyes Proof of Concepts
Data Mesh Part 4 Monolith to Mesh
Data platform modernization with Databricks.pptx
Intuit's Data Mesh - Data Mesh Leaning Community meetup 5.13.2021
Design Guidelines for Data Mesh and Decentralized Data Organizations
Data ops in practice
A Cloud Journey - Move to the Oracle Cloud
Lambda Architecture in the Cloud with Azure Databricks with Andrei Varanovich
Azure data platform overview
Why Data Virtualization? An Introduction
Ad

Similar to Scaling Advanced Analytics at Shell with Krishna Somasundaram and Bryce Bartmann (20)

PDF
Moving Towards AI at Shell with Daniel Jeavons (Shell)
PPTX
Sarah Coleman & Tom Frost: Project Leadership and Delivery Performance
PDF
2014.12.01 - NAEC-Strategic Foresight Workshop_Session 4_Wim Thomas
PDF
Royal Dutch Shell plc Downstream Open House webcast
PDF
Shell scenarios, modelling and decision-making
PDF
Energy Consumption - Scenario Planning
PDF
II-PIC 2017: Commercialization Potential of Emerging Technologies: Insights B...
PDF
Leveraging FME for Enhanced Decision Making in Offshore Operations
PDF
Introducing Delta Live Tables: Make Reliable ETL Easy on Delta Lake
PDF
Shell responsible investor briefing in London – April 16, 2018
PDF
Shell responsible investor briefing in London – April 16, 2018
PDF
Shell launches LNG Outlook 2018
PDF
ISES 2013 - Day 2 - Mitchell Winkler (Director Arctic, Shell) - Arctic Drilling
PDF
Royal Dutch Shell plc fourth quarter 2017 results webcast presentation
PDF
Michelle van der Duin (Shell) WiPM240915
PDF
Energy for a Changing World
PPTX
Presentation by Nick Lynch, Shell at the Supply Chain Insights Global Summit ...
PDF
AVEVA World Conference NA - Mike Curtin, Shell
PDF
AVEVA World Conference NA - Mike Curtin, Shell
PDF
Retail wealth management investor presentation
Moving Towards AI at Shell with Daniel Jeavons (Shell)
Sarah Coleman & Tom Frost: Project Leadership and Delivery Performance
2014.12.01 - NAEC-Strategic Foresight Workshop_Session 4_Wim Thomas
Royal Dutch Shell plc Downstream Open House webcast
Shell scenarios, modelling and decision-making
Energy Consumption - Scenario Planning
II-PIC 2017: Commercialization Potential of Emerging Technologies: Insights B...
Leveraging FME for Enhanced Decision Making in Offshore Operations
Introducing Delta Live Tables: Make Reliable ETL Easy on Delta Lake
Shell responsible investor briefing in London – April 16, 2018
Shell responsible investor briefing in London – April 16, 2018
Shell launches LNG Outlook 2018
ISES 2013 - Day 2 - Mitchell Winkler (Director Arctic, Shell) - Arctic Drilling
Royal Dutch Shell plc fourth quarter 2017 results webcast presentation
Michelle van der Duin (Shell) WiPM240915
Energy for a Changing World
Presentation by Nick Lynch, Shell at the Supply Chain Insights Global Summit ...
AVEVA World Conference NA - Mike Curtin, Shell
AVEVA World Conference NA - Mike Curtin, Shell
Retail wealth management investor presentation
Ad

More from Databricks (20)

PPTX
Data Lakehouse Symposium | Day 1 | Part 1
PPT
Data Lakehouse Symposium | Day 1 | Part 2
PPTX
Data Lakehouse Symposium | Day 2
PPTX
Data Lakehouse Symposium | Day 4
PDF
Democratizing Data Quality Through a Centralized Platform
PDF
Learn to Use Databricks for Data Science
PDF
Why APM Is Not the Same As ML Monitoring
PDF
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
PDF
Stage Level Scheduling Improving Big Data and AI Integration
PDF
Simplify Data Conversion from Spark to TensorFlow and PyTorch
PDF
Scaling your Data Pipelines with Apache Spark on Kubernetes
PDF
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
PDF
Sawtooth Windows for Feature Aggregations
PDF
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
PDF
Re-imagine Data Monitoring with whylogs and Spark
PDF
Raven: End-to-end Optimization of ML Prediction Queries
PDF
Processing Large Datasets for ADAS Applications using Apache Spark
PDF
Massive Data Processing in Adobe Using Delta Lake
PDF
Machine Learning CI/CD for Email Attack Detection
PDF
Jeeves Grows Up: An AI Chatbot for Performance and Quality
Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 4
Democratizing Data Quality Through a Centralized Platform
Learn to Use Databricks for Data Science
Why APM Is Not the Same As ML Monitoring
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
Stage Level Scheduling Improving Big Data and AI Integration
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Scaling your Data Pipelines with Apache Spark on Kubernetes
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Sawtooth Windows for Feature Aggregations
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Re-imagine Data Monitoring with whylogs and Spark
Raven: End-to-end Optimization of ML Prediction Queries
Processing Large Datasets for ADAS Applications using Apache Spark
Massive Data Processing in Adobe Using Delta Lake
Machine Learning CI/CD for Email Attack Detection
Jeeves Grows Up: An AI Chatbot for Performance and Quality

Recently uploaded (20)

PDF
Transcultural that can help you someday.
PPTX
A Complete Guide to Streamlining Business Processes
PDF
Data Engineering Interview Questions & Answers Batch Processing (Spark, Hadoo...
PDF
Introduction to the R Programming Language
PPTX
Business_Capability_Map_Collection__pptx
PDF
Introduction to Data Science and Data Analysis
PPTX
Copy of 16 Timeline & Flowchart Templates – HubSpot.pptx
PPTX
SET 1 Compulsory MNH machine learning intro
PPTX
Introduction to Inferential Statistics.pptx
PPTX
modul_python (1).pptx for professional and student
PPTX
(Ali Hamza) Roll No: (F24-BSCS-1103).pptx
PDF
Systems Analysis and Design, 12th Edition by Scott Tilley Test Bank.pdf
PPTX
Topic 5 Presentation 5 Lesson 5 Corporate Fin
PDF
Capcut Pro Crack For PC Latest Version {Fully Unlocked 2025}
PPTX
Phase1_final PPTuwhefoegfohwfoiehfoegg.pptx
DOCX
Factor Analysis Word Document Presentation
PDF
Data Engineering Interview Questions & Answers Cloud Data Stacks (AWS, Azure,...
PPTX
Leprosy and NLEP programme community medicine
PPTX
retention in jsjsksksksnbsndjddjdnFPD.pptx
PDF
OneRead_20250728_1808.pdfhdhddhshahwhwwjjaaja
Transcultural that can help you someday.
A Complete Guide to Streamlining Business Processes
Data Engineering Interview Questions & Answers Batch Processing (Spark, Hadoo...
Introduction to the R Programming Language
Business_Capability_Map_Collection__pptx
Introduction to Data Science and Data Analysis
Copy of 16 Timeline & Flowchart Templates – HubSpot.pptx
SET 1 Compulsory MNH machine learning intro
Introduction to Inferential Statistics.pptx
modul_python (1).pptx for professional and student
(Ali Hamza) Roll No: (F24-BSCS-1103).pptx
Systems Analysis and Design, 12th Edition by Scott Tilley Test Bank.pdf
Topic 5 Presentation 5 Lesson 5 Corporate Fin
Capcut Pro Crack For PC Latest Version {Fully Unlocked 2025}
Phase1_final PPTuwhefoegfohwfoiehfoegg.pptx
Factor Analysis Word Document Presentation
Data Engineering Interview Questions & Answers Cloud Data Stacks (AWS, Azure,...
Leprosy and NLEP programme community medicine
retention in jsjsksksksnbsndjddjdnFPD.pptx
OneRead_20250728_1808.pdfhdhddhshahwhwwjjaaja

Scaling Advanced Analytics at Shell with Krishna Somasundaram and Bryce Bartmann

  • 1. 0 Cautionary Note The companies in which Royal Dutch Shell plc directly and indirectly owns investments are separate legal entities. In this presentation “Shell”, “Shell group” and “Royal Dutch Shell” are sometimes used for convenience where references are made to Royal Dutch Shell plc and its subsidiaries in general. Likewise, the words “we”, “us” and “our” are also used to refer to Royal Dutch Shell plc and subsidiaries in general or to those who work for them. These terms are also used where no useful purpose is served by identifying the particular entity or entities. ‘‘Subsidiaries’’, “Shell subsidiaries” and “Shell companies” as used in this presentation refer to entities over which Royal Dutch Shell plc either directly or indirectly has control. Entities and unincorporated arrangements over which Shell has joint control are generally referred to as “joint ventures” and “joint operations”, respectively. Entities over which Shell has significant influence but neither control nor joint control are referred to as “associates”. The term “Shell interest” is used for convenience to indicate the direct and/or indirect ownership interest held by Shell in an entity or unincorporated joint arrangement, after exclusion of all third-party interest. This presentation contains forward-looking statements (within the meaning of the U.S. Private Securities Litigation Reform Act of 1995) concerning the financial condition, results of operations and businesses of Royal Dutch Shell. All statements other than statements of historical fact are, or may be deemed to be, forward-looking statements. Forward-looking statements are statements of future expectations that are based on management’s current expectations and assumptions and involve known and unknown risks and uncertainties that could cause actual results, performance or events to differ materially from those expressed or implied in these statements. Forward-looking statements include, among other things, statements concerning the potential exposure of Royal Dutch Shell to market risks and statements expressing management’s expectations, beliefs, estimates, forecasts, projections and assumptions. These forward-looking statements are identified by their use of terms and phrases such as “aim”, “ambition’, ‘‘anticipate’’, ‘‘believe’’, ‘‘could’’, ‘‘estimate’’, ‘‘expect’’, ‘‘goals’’, ‘‘intend’’, ‘‘may’’, ‘‘objectives’’, ‘‘outlook’’, ‘‘plan’’, ‘‘probably’’, ‘‘project’’, ‘‘risks’’, “schedule”, ‘‘seek’’, ‘‘should’’, ‘‘target’’, ‘‘will’’ and similar terms and phrases. There are a number of factors that could affect the future operations of Royal Dutch Shell and could cause those results to differ materially from those expressed in the forward-looking statements included in this [report], including (without limitation): (a) price fluctuations in crude oil and natural gas; (b) changes in demand for Shell’s products; (c) currency fluctuations; (d) drilling and production results; (e) reserves estimates; (f) loss of market share and industry competition; (g) environmental and physical risks; (h) risks associated with the identification of suitable potential acquisition properties and targets, and successful negotiation and completion of such transactions; (i) the risk of doing business in developing countries and countries subject to international sanctions; (j) legislative, fiscal and regulatory developments including regulatory measures addressing climate change; (k) economic and financial market conditions in various countries and regions; (l) political risks, including the risks of expropriation and renegotiation of the terms of contracts with governmental entities, delays or advancements in the approval of projects and delays in the reimbursement for shared costs; and (m) changes in trading conditions. No assurance is provided that future dividend payments will match or exceed previous dividend payments. All forward-looking statements contained in this [report] are expressly qualified in their entirety by the cautionary statements contained or referred to in this section. Readers should not place undue reliance on forward-looking statements. Additional risk factors that may affect future results are contained in Royal Dutch Shell’s 20-F for the year ended December 31, 2017 (available at www.shell.com/investor and www.sec.gov ). These risk factors also expressly qualify all forward looking statements contained in this presentation and should be considered by the reader. Each forward-looking statement speaks only as of the date of this presentation, 03-OCT-2018. Neither Royal Dutch Shell plc nor any of its subsidiaries undertake any obligation to publicly update or revise any forward-looking statement as a result of new information, future events or other information. In light of these risks, results could differ materially from those stated, implied or inferred from the forward-looking statements contained in this presentation. We may have used certain terms, such as resources, in this presentation that United States Securities and Exchange Commission (SEC) strictly prohibits us from including in our filings with the SEC. U.S. Investors are urged to consider closely the disclosure in our Form 20-F, File No 1-32575, available on the SEC website www.sec.gov. 0
  • 2. Copyright of Shell International Scaling Advanced Analytics @ Shell Oct 2018 Krishna Somasundaram – Software Engineering Architect Bryce Bartmann – Senior Data Engineer
  • 3. 2 Shell’s Digital Strategy OPERATING MODEL AND WAYS OF WORKING CAPABILITIES LEADERSHIP, MIND- SETS AND BEHAVIOUR UNDERPINNING CRITICAL SUCCESS FACTORS BUSINESSES OWN DIGITAL ACT OUR WAY INTO THE FUTURE BUILD IN- HOUSE CAPABILITY CUSTOMER/USE R IS CENTRAL FIVE DIGITAL DESIGN PRINCIPLES A coherent approach across Shell to realise and accelerate value through digital led by business and supported by Digital COE DATA IS AN ASSET
  • 4. 3 Role of the Data Science CoE 1 Select Foundational Technologies 2 Showcase ‘Art of the Possible’ 3 Facilitate Best Practice Sharing across Shell Strategic Objective Enablers Innovation Remit Core Team with Technical & Commercial Skillset Development of Digital Networks Creation of Digital Labs for Experimentation External Partnerships and Developing the Eco System
  • 5. 4 From an idea to an embedded business capability 6 October, 2018 4 Business Needs, Opportunities & Challenges MVP R2 R3 R&D Design Sprint Proof of Concept PROBLEMS WORTH SOLVING LEARNING AND DELIVERING FAST TOGETHER DELIVERING VALUE Digital IT
  • 6. 5 Digitalisation playground & PoC incubator sandbox environment 5 Shiny 500+ users across Shell Businesses Digitalisation Lab We want as close integration between all offerings as possible
  • 8. 7 Making the most of existing data Rightsizing inventory Copyright of Shell Global Solutions International B.V.
  • 9. 8 8Footer October 18Copyright of Shell Global Solutions International B.V. Machine Learning to enable ‘grey stock’ identification Pipe Counting
  • 10. 9 Augmenting pipe counting & grey stock identification using MV techniques Primary value-flow: February 2018 Collect Data Store in Public Cloud Apply Machine Learning and leverage Machine Vision Create actionable insight Support Decision Making leading to Value Creation Algorithm performs with >90% accuracy
  • 11. 10 1 0 Footer October 18 Copyright of Shell Global Solutions International B.V. Optimizing HSSE Video Analytics for incident tracking & management
  • 14. 13 Business challenge: how can we 1) consistently identify equipment & 2) maintenance history without significant manual effort? 13 LABOUR & OPEX COST REDUCTION PRODUCTIVIT Y INCREASE SAFETY INCREAS E
  • 15. 14 Leak Detection Volumetric Abnormal Heat Signatures Site Security and Surrounding Conditions Corrosion Detection Plume Detection September 2016 14 Other Machine Vision Possibilities