Data’s Journey — Part 5: Data Visualization and Consumption

Author
Justin Lee
8
min read
|
Nov 15, 2023
Data Analysis
Detect, in partnership with Newfoundland & Labrador Hydro (NLH) and Stantec, is excited to introduce a new series: “Data’s Journey”. This is a five-part series that takes you behind the scenes of our critical inspection processes. We’ll provide you with a deep dive into each of our steps, starting from the initial planning phase to visualizing collected and organized data on our platform, SCOPE.

Overall Project Stats

  • Structures Inspected: 1314
  • Photos Taken: 39,401
  • Defects Detected (compared to previous inspection): 10X
  • Total Distance: 220 km
  • Total Inspection Time: 22 Days
  • In-field Team Composition: Pilot, Safety Officer, and Data Manager
    ‍
“The greatest value of a picture is when it forces us to notice what we never expected to see” — John Tukey


In this fifth and final installment, we’ll discuss data consumption. Our project, which includes over 39,000 photos, many marked with defects, underscores the need for efficient data organization clarity and ease of interpretation. This project involved two parallel transmission lines, L23(A) and L24(A), spanning approximately 220 km between Wabush and Churchill Falls, NL.
‍

Transforming data into actionable intelligence

In the realm of utility asset management, dealing with vast amounts of data is a given. Across the 1314 structures, we have photos providing unique perspectives on the structure’s condition, GPS data pinpointing their locations all supplemented with metadata detailing the structure’s characteristics. For each structure, they are inspected by our certified powerline technicians where they may identify multiple defects and severities across multiple images. As one can imagine, this is a lot of information and without having it be easily interpretable, it can be very difficult to make important decisions including maintenance scheduling and prioritization. This diversity and volume of data, while invaluable, presents a significant challenge: how to distill it into actionable intelligence for effective decision making.

The idea of actionable intelligence is especially important in cases like these. Raw data needs to be refined, focused and interpreted to be useful for decision making. Consider this data as an expansive ocean, vast and deep. Navigating this ocean without direction is akin to attempting decision-making amidst all of this raw data — daunting, directionless and fraught with risks of misinterpretation and missed opportunities. By having a skilled navigator not only map the ocean but interpret the upcoming obstacles, they can derive meaningful insights and make the correct decisions for an optimal outcome.

With Detect, we aim to not only collect and make all of this data available but to help you interpret it in a way that helps you make the best decisions through mapping and visualization tools. In this case, our platform allows you to understand exactly what is important and more specifically help you prioritize. Just as a skilled navigator employs tools and expertise to chart a course through the ocean, Detect uses advanced mapping and visualization tools to transform raw data into clear, prioritized insights, guiding decision making processes with precision and insight.
‍

Visual Tools: Clarifying Data Complexity

For utility asset management and specifically asset inspections, the primary objective is to repair and maintain high risk assets and to minimize any uncertainty in the field. As a result, there are three specific question users want answered quickly and efficiently:

1. Which structures require immediate attention?

2. Where are these structures located?

3. What are the specific issues identified and what parts are needed?

Heat map indicating structure severity

We’ve built multiple tools to answer each of these questions, with the aim to minimize the time needed to interpret the data. Heat maps allow users to quickly see where the high severity structures were located. This tool can help identify any regions where there are multiple high risk structures and give a quick overview on nearby access roads and possible restrictions using satellite imagery.

Structure review tool showing different deficiencies and severities

In addition, our platform looks at summarizing information as neatly as possible for a given structure. Breakdowns on the number of defects by severity are given for each structure, with details on the deficiencies and the member IDs. Furthermore, images show exactly the defects identified, eliminating the need to search through thousands of photos to see exactly what the defect is.

Additional insights — Reports and Images

In this use case, weekly reports were needed to enable other downstream processes including structure modelling and planning future construction work. Given the prior efforts in building robust data models, automated CSV reports were generated for various end users highlighting the structure number, defect, leg number, member ID as well as the image name showing the defects. These reports gave a clear overview of the entire inspection in a format end users like powerline technicians and engineers were familiar with.

As mentioned above, our platform looks at providing only the most important images to the user but oftentimes, users may want access to all the images collected for auditing and review purposes. The platform also has a file management system allowing users to see all the images, organized by structures, all online. These are excellent in the use cases where a user may want to see multiple angles of the same deficiency or if they want to confirm the annotation.
‍

Data’s Journey — What is next?

This marks the end of our data’s journey (for this project), from planning and collection all the way to consumption. As you can see, the problem of data consumption is an important one and Detect is constantly looking for ways to better enable our users with actionable intelligence. New advances including better live inspection tracking, annotation feedback tools and monitoring tools are being developed and being soon made available for our users to better the inspection experience.

This post was part of a series detailing Detect’s data journey, produced in partnership with Newfoundland & Labrador Hydro and Stantec.

No items found.

Overall Project Stats

  • Structures Inspected: 1314
  • Photos Taken: 39,401
  • Defects Detected (compared to previous inspection): 10X
  • Total Distance: 220 km
  • Total Inspection Time: 22 Days
  • In-field Team Composition: Pilot, Safety Officer, and Data Manager
    ‍
“The greatest value of a picture is when it forces us to notice what we never expected to see” — John Tukey


In this fifth and final installment, we’ll discuss data consumption. Our project, which includes over 39,000 photos, many marked with defects, underscores the need for efficient data organization clarity and ease of interpretation. This project involved two parallel transmission lines, L23(A) and L24(A), spanning approximately 220 km between Wabush and Churchill Falls, NL.
‍

Transforming data into actionable intelligence

In the realm of utility asset management, dealing with vast amounts of data is a given. Across the 1314 structures, we have photos providing unique perspectives on the structure’s condition, GPS data pinpointing their locations all supplemented with metadata detailing the structure’s characteristics. For each structure, they are inspected by our certified powerline technicians where they may identify multiple defects and severities across multiple images. As one can imagine, this is a lot of information and without having it be easily interpretable, it can be very difficult to make important decisions including maintenance scheduling and prioritization. This diversity and volume of data, while invaluable, presents a significant challenge: how to distill it into actionable intelligence for effective decision making.

The idea of actionable intelligence is especially important in cases like these. Raw data needs to be refined, focused and interpreted to be useful for decision making. Consider this data as an expansive ocean, vast and deep. Navigating this ocean without direction is akin to attempting decision-making amidst all of this raw data — daunting, directionless and fraught with risks of misinterpretation and missed opportunities. By having a skilled navigator not only map the ocean but interpret the upcoming obstacles, they can derive meaningful insights and make the correct decisions for an optimal outcome.

With Detect, we aim to not only collect and make all of this data available but to help you interpret it in a way that helps you make the best decisions through mapping and visualization tools. In this case, our platform allows you to understand exactly what is important and more specifically help you prioritize. Just as a skilled navigator employs tools and expertise to chart a course through the ocean, Detect uses advanced mapping and visualization tools to transform raw data into clear, prioritized insights, guiding decision making processes with precision and insight.
‍

Visual Tools: Clarifying Data Complexity

For utility asset management and specifically asset inspections, the primary objective is to repair and maintain high risk assets and to minimize any uncertainty in the field. As a result, there are three specific question users want answered quickly and efficiently:

1. Which structures require immediate attention?

2. Where are these structures located?

3. What are the specific issues identified and what parts are needed?

Heat map indicating structure severity

We’ve built multiple tools to answer each of these questions, with the aim to minimize the time needed to interpret the data. Heat maps allow users to quickly see where the high severity structures were located. This tool can help identify any regions where there are multiple high risk structures and give a quick overview on nearby access roads and possible restrictions using satellite imagery.

Structure review tool showing different deficiencies and severities

In addition, our platform looks at summarizing information as neatly as possible for a given structure. Breakdowns on the number of defects by severity are given for each structure, with details on the deficiencies and the member IDs. Furthermore, images show exactly the defects identified, eliminating the need to search through thousands of photos to see exactly what the defect is.

Additional insights — Reports and Images

In this use case, weekly reports were needed to enable other downstream processes including structure modelling and planning future construction work. Given the prior efforts in building robust data models, automated CSV reports were generated for various end users highlighting the structure number, defect, leg number, member ID as well as the image name showing the defects. These reports gave a clear overview of the entire inspection in a format end users like powerline technicians and engineers were familiar with.

As mentioned above, our platform looks at providing only the most important images to the user but oftentimes, users may want access to all the images collected for auditing and review purposes. The platform also has a file management system allowing users to see all the images, organized by structures, all online. These are excellent in the use cases where a user may want to see multiple angles of the same deficiency or if they want to confirm the annotation.
‍

Data’s Journey — What is next?

This marks the end of our data’s journey (for this project), from planning and collection all the way to consumption. As you can see, the problem of data consumption is an important one and Detect is constantly looking for ways to better enable our users with actionable intelligence. New advances including better live inspection tracking, annotation feedback tools and monitoring tools are being developed and being soon made available for our users to better the inspection experience.

This post was part of a series detailing Detect’s data journey, produced in partnership with Newfoundland & Labrador Hydro and Stantec.