How AI powered data insights can help improve vegetation management

Enhance your vegetation management strategy with more-accurate forecasts

For many organizations, vegetation management (VM) is the largest non-fuel-related operating cost. To prioritize VM work, organizations must capture and merge data from multiple sources, including images, data from work management systems, regulatory requirements, weather information, risk models, geospatial data, and more. They must then be able to use this data to accurately plan and forecast the distance between assets and vegetation by carefully registering and combining 3D models of the network and its surrounding vegetation. By leveraging data from topographic surveys alongside analytics (for example, plant health indices), utilities can optimize their vegetation maintenance resources, budgets, and work routines.

Reduce costs and improve vegetation management strategies with advanced image processing techniques

Evaluating tree canopy height, and more generally the height of any type of vegetation, as part of a vegetation management plan is one of the most widely known applications of both light detection and ranging (LiDAR) and photogrammetry. Both techniques, which are often combined, require advanced classification and filtering algorithms to accurately derive vegetation height and condition. Utilities use these techniques to identify structurally unsound trees, analyze climbing vines that might impact wires and switchgear components, and manage vegetation that might attract unwanted wildlife near critical equipment.

The following architecture demonstrates how we can use Oracle Modern Data Platform in conjunction with advanced ML/AI techniques and NVIDIA GPUs to not only derive a two-dimensional picture of vegetation but also add a third dimension that provides finer-grained detail. This detail allows us to determine the type of tree, its growth, and its distance from the infrastructure, as well as other details, more accurately.

This image shows how Oracle Data Platform for energy and water can be used to support a vegetation management use case. The platform includes the following five pillars:

1. 1. Data Sources, Discovery
2. 2. Ingest, Transform
3. 3. Persist, Curate, Create
4. 4. Analyze, Learn, Predict
5. 5. Measure, Act

The Data Sources, Discovery pillar includes three categories of data.

1. 1. First-Party data is comprised of asset metadata, GIS data, LiDAR images, and satellite images.
2. 2. Applications includes outage and maintenance management systems.
3. 3. Third-party data includes data from weather sources.

The Ingest, Transform pillar comprises two capabilities.

1. 1. Batch ingestion uses Oracle Integration Cloud, Spatial Studio, OCI Data Integration, and Data Studio.
2. 2. Change data capture uses OCI GoldenGate and Oracle Data Integrator.

Both capabilities connect unidirectionally into the serving data store, and cloud storage within the Persist, Curate, Create pillar.

The Persist, Curate, Create pillar comprises four capabilities.

1. 1. The serving data store uses Autonomous Data Warehouse.
2. 2. Cloud storage uses OCI Object Storage.
3. 3. Batch processing uses OCI Data Integration, Functions, and Data Flow.
4. 4.Governance uses OCI Data Catalog.

These capabilities are connected within the pillar. Cloud storage is unidirectionally connected to the serving data store; it is also bidirectionally connected to batch processing.

The metadata lines unidirectionally connect from the serving data store and cloud storage to governance.

Two capabilities connect into the Analyze, Learn, Predict pillar: The serving data store and cloud storage unidirectionally connect to the analytics and visualization, low-code AppDev, predict , learn and AI services.

The Analyze, Learn, Predict pillar comprises six capabilities.

1. 1. Analytics and visualization use Spatial Studio, Oracle Analytics Cloud, and ISVs.
2. 2. Data products, APIs uses OCI API Gateway, Oracle Integration Cloud, and OCI Functions.
3. 3. Low-code AppDev uses APEX and Oracle Visual Builder.
4. 4. Predict uses OCI Data Science and Oracle Machine Learning services.
5. 5. Learn uses OCI Data Science and Oracle Machine Learning notebooks.
6. 6. AI services uses OCI Vision, OCI Language, and third-party.

The data products, APIs capability is unidirectionally connected to the predict capability.

The serving data store and object storage supply metadata to the OCI Data Catalog.

The Measure, Act pillar captures how the data analysis may be applied to support a vegetation management delivery model and monitor performance. These applications are divided into two groups.

1. 1. The first group Peoples and Partners includes vegetation management team, system reliability, and operations and maintenance.
2. 2. The second group Applications includes Oracle Field Service, Oracle Utilities Work and Asset Management, enterprise asset management, work management system, and field service management.

The three central pillars—Ingest, Transform; Persist, Curate, Create; and Analyze, Learn, Predict—are supported by infrastructure, network, security, and IAM.

Vegetation management logical architecture

There are two main ways to inject data into an architecture to enable utilities to effectively develop a vegetation management strategy.

• We’ll use batch ingestion to import data from systems that can’t support streaming (for example, older supervisory control and data acquisition (SCADA) systems or maintenance management systems). In this use case, high-resolution images, weather data, and data from GPS, maintenance, and outage management systems will be ingested at varying intervals. We’ll use Oracle Integration Cloud to load these data sets into Oracle Cloud Infrastructure (OCI) Object Storage or directly into Oracle Autonomous Data Warehouse (ADW). We’ll also capture LiDAR and other images of the relevant infrastructure and surrounding vegetation and load them into OCI Object Storage, usually via an API or the OCI command-line interface.
• In addition, we’ll use Oracle Cloud Infrastructure GoldenGate to ingest data from operational systems, such as outage systems, maintenance management systems, and resource planning systems, via change data capture.

Data persistence and processing is built on three components.

• Ingested raw data from all sources is stored in cloud storage. We’ll initially label or annotate the images directly using OCI Vision or a third-party option. During the annotation process, different areas of each image will be classified by vegetation type, transmission line, distribution line, utility pole, and so on. In this use case, we’re using a combination of OCI Data Science and the NVIDIA platform and libraries to provide a three-dimensional image. We’ll then use OCI Data Integration or OCI Data Flow for batch processing to consolidate, curate, or enhance the collected data as needed. OCI Data Integration is where the data pipelines are built and maintained. Though OCI Data Integration comes with a wide array of connectors for varied data assets (databases, applications, object storage, REST APIs, and so on) it may not meet all your needs. If this is the case, you can build an OCI Data Flow application to take advantage of all the connectors that are available via Spark. In this example, the results of the image processing, GPS, historical outage, and maintenance data are combined to build a model to identify the physical asset locations requiring attention, which can be used as part of a vegetation management solution.
• We have now created processed data sets that are ready to be persisted in optimized relational form for curation and query performance in the serving data store provided by ADW. This enables us to visualize the results of the model predictions. We can even use the built-in spatial capabilities to visualize possible hotspots that may require immediate attention.

The ability to analyze, learn, and predict is facilitated by three technologies.

• Analytics and visualization services such as Oracle Analytics Cloud, Spatial Studio, and Oracle APEX can deliver interactive dashboards we can use to visualize image information and predict the future impact of vegetation on specific transmission or transfer assets. These services provide
  • Descriptive analytics, which we can use to illustrate current growth and encroachment rates with histograms and charts to help identify areas requiring immediate maintenance
  • Predictive analytics, which we can use to plan and determine longer-term maintenance needs by predicting future growth and encroachment, identifying trends, and determining the probability of uncertain outcomes
  • Prescriptive analytics, which can propose suitable actions to help optimize strategic vegetation management decision-making
• Alongside the use of advanced analytics, machine learning models are developed, trained, and deployed using OCI Data Science. These models use artificial intelligence to analyze large amounts of LiDAR image data to develop three-dimensional pictures so we can understand exactly how far away vegetation is from critical infrastructure. This fine-grained measurement, when combined with regulatory requirements, weather data, maintenance schedules, and other valuable data, can help utilities continually prioritize the work to be done and the teams required to do it in the most efficient and cost-effective manner. Once these models are trained, they can be deployed in several ways depending on the user’s preference. The models can be called via REST endpoints using the OCI Data Science platform or the in-database Oracle Machine Learning Services REST API. Additionally, the user can package these models up in an Open Neural Network Exchange (ONNX) format and deploy them as part of an application.
• Our curated, tested, and high-quality data and models can have governance rules and policies applied using OCI Data Catalog in conjunction with other services and can be exposed as a “data product” (API) within a data mesh architecture for distribution across the organization.

Level up your vegetation management strategy with the Oracle Modern Data Platform

Efficient and timely asset management is always essential, but it’s even more critical when assets include power lines that could spark a fire or outage due to vegetation overgrowth. For power utilities in the United States, vegetation management is the largest preventive maintenance expense, exceeding $100 million annually at many larger utility companies. However, VM is also the greatest contributor to utility system reliability and effective outage management. With Oracle Modern Data Platform, you can gather fine-grained details of your infrastructure and its surrounding vegetation and use this data to help improve your VM strategy and results in the following ways:

• Reduce vegetation infringement on power lines
• Validate expected vegetation growth rates
• Foster effective vegetation planning and monitoring
• Reduce revenue loss from power outages
• Reduce your annual vegetation management budget
• Increase customer satisfaction and worker safety