Nearmap

Learning Objectives

• Understand how frequently refreshed aerial imagery plus machine learning turns pictures of rooftops into structured property data
• See how Nearmap Roof Assessment evaluates roof condition across large property portfolios without a site visit
• Recognize the limits of remote assessment and why ground truth still matters for high-stakes decisions

What Is Nearmap?

Nearmap is a location-intelligence company that captures high-resolution aerial imagery of large populated areas several times a year and runs machine-learning models over that imagery to extract structured facts about each property. Instead of an insurer, roofer, government agency, or real-estate team sending a person to look at a building, Nearmap turns a current overhead image into hundreds of measurable attributes — roof material and geometry, surface condition, vegetation overhang, solar potential, and more. The concrete problem it solves is scale: assessing thousands of properties one visit at a time is slow and expensive, while a fresh image plus automated attribute extraction can describe an entire region in a fraction of the time.

Nearmap was founded in Australia in 2007 and operates a large aerial-survey program spanning the United States, Australia, New Zealand, and Canada, with a US base in Salt Lake City. In 2023 it was taken private by the software investment firm Thoma Bravo, which accelerated investment in capture technology and its in-house AI platform. Nearmap is now one of the ten largest aerial-survey companies in the world by annual data-collection volume. In February 2026 it launched Nearmap Roof Assessment, extending its property-intelligence platform to remote, portfolio-scale roof-condition evaluation.

Core Capabilities

Frequently refreshed high-resolution imagery

Nearmap flies survey aircraft to recapture populated areas multiple times per year, producing crisp overhead and oblique imagery. Because the library is refreshed on a schedule rather than captured once, users can compare current and historical views of the same property to see change over time.

Machine-learning attribute extraction

Nearmap's AI models read the imagery and return structured facts about each address — reportedly hundreds of attributes per property, covering roof characteristics, debris, surface permeability, vegetation, and more. This converts raw pixels into queryable data that downstream systems can use for underwriting, planning, or outreach.

Roof Assessment for portfolios

Nearmap Roof Assessment identifies dozens of roof characteristics — including ponding, rust, debris, and tree overhang — and produces a Roof Spotlight Index that scores each roof from 0 to 100 based on visible condition. Teams managing many buildings can triage which roofs need attention first without dispatching an inspector to every site.

Strengths

• Scale without site visits: A single refreshed image plus automated extraction can describe thousands of properties, making portfolio-wide assessment practical where physical inspection is not.
• Change over time: Regular recapture lets users track how a roof or property has degraded or improved, which one-time captures cannot show.
• Structured, actionable data: The models return measurable attributes and a numeric roof score rather than a picture to interpret, so results feed directly into underwriting and planning workflows.
• In-house AI and capture: Owning both the imagery program and the AI platform lets Nearmap tune models to its own consistent, high-resolution data.

Limitations & Considerations

• Remote assessment has real limits. Overhead imagery cannot see under a roof, inside an attic, or detect a leak that leaves no visible surface signal; a Roof Spotlight score flags likely condition, not a certified inspection, and high-stakes decisions still warrant ground truth.
• A score is a probability, not a verdict. The index reflects what the model sees from above at a point in time; unusual roof types, shadow, or recent repairs can skew a reading, so results should be reviewed rather than acted on blindly.
• It competes directly with other aerial-AI providers. Firms such as EagleView and CAPE Analytics offer overlapping roof and property intelligence, so coverage recency, model accuracy, and pricing should be compared for a given region.
• Coverage and recency vary by area. Dense urban and suburban regions are captured often; rural or less-populated areas may be flown less frequently, which affects how current the data is.

Best Use Cases

Getting Started

1. Define the coverage area and property portfolio you need to assess and confirm Nearmap's capture recency there.
2. Choose the imagery and AI products that fit your workflow, such as Roof Assessment for condition scoring.
3. Review the extracted attributes and Roof Spotlight scores, then prioritize properties for closer human inspection.
4. Integrate the structured data into your underwriting, planning, or maintenance systems and re-check as new captures land.

Key Takeaways

• Nearmap captures high-resolution aerial imagery several times a year and uses machine learning to extract hundreds of property attributes.
• Its 2026 Roof Assessment scores roof condition across whole portfolios remotely using a 0-to-100 Roof Spotlight Index.
• Founded in Australia in 2007 and taken private by Thoma Bravo in 2023, it is among the largest aerial-survey firms in the world.
• Remote assessment is fast and scalable, but a score is not a certified inspection, and it competes directly with other aerial-AI providers.