Overview
The Nearmap Damage Classifications AI provides AI-driven insights into the damage caused by a catastrophic event.
The analysis comprises a selection of Nearmap AI data which can assist in a quick triage and assessment of damages caused by a catastrophic event to plan the appropriate response. The insights are available in CSV format. This AI-driven damage insights information is delivered via the Nearmap Transactional Content API.
NOTE: Damage Classifications AI provides insights specific to the survey date and does not take into consideration the imagery from any earlier or later dates.
NOTE: We recommend that you cross-check the results from this with MapBrowser imagery or imagery from another source. For more information, see Statistical Performance.
You can access the damage detection data in Damage Classifications AI if you have a subscription for both the Nearmap ImpactResponse Imagery and Transactional Content API product.
Damage Classifications AI Data
The following Nearmap AI data is available in the Damage Classifications AI product for cyclone, tornado and hurricanes events:
NOTE: Damage classification is based on evaluating the primary structure of the given parcel. The extent of damage is classified using a 5-tier classification scale. This scale and the descriptions are based on the Federal Emergency Management Agency's (FEMA) damage assessment guidelines.
Triage Class | NM Score | Category | Description |
|---|
No Damage | 0 | No Damage | The building does not appear to be impacted and is livable. |
Assessment Needed | 1 | Affected | - Minimal missing tiles or shingles - May be minimal structural damage to garage/carport, deck |
Assessment Needed | 2 | Minor | - No structural damage - Some missing roof covering material (tile, shingle) - Some minor damage to associated roof objects including chimney, air conditioner, solar panel, solar hot water, skylight. |
Assessment Needed/Unlivable | 3 | Major | - Building has structural damage or loss, however overall structure still standing and can be used for shelter - Parts of interior may be visible |
Unlivable | 4 | Destroyed | - Structure can no longer be used for shelter - Majority of structure compromised (that is, walls, roof); interior exposed - Building frame bent, twisted, or broken - Only foundation remains |
NOTE: As a default, Nearmap displays 5-tier classification. However, you can use the API if you choose to view a 3-tier classification. This is described in the sections below.
The 3-tier classification is derived from the thresholds in the table above with the following classification levels:
- Unaffected
- Partial Loss
- Total Loss
Accessing Damage Classifications AI
To access Damage Classifications AI data, complete the following steps:
- Generate a transaction token and aiResourceid - The parameters that need to be passed to generate a transaction token are explained below. The transaction token is valid for 30 days and can be used any number of times in that duration.
- Request imagery using the AI Feature API - You must have a transaction token to do this. The parameters that need to be passed to generate an output file are explained below.
Mandatory parameters are indicated with a ✔️, while ❌ indicates optional parameters.
Authentication
Access to Nearmap data and imagery is only available to authenticated subscribers. Damage Classifications AI data and imagery may be requested from Nearmap servers with an API Key. Refer to the API Key Authentication article for details.
Generating the transaction token
Required | Name | Type | Description |
|---|
✔️ | address | string | Complete address of the parcel including the country. For example, 333 Guadalupe st, Austin, TX 78701, USA. Note that you can specify this in any case. |
✔️ | country | string | This can take the value US or AU. This is not case sensitive and is only valid for an address. |
✔️ | resources | string | Set this to aiImpactTriage:damagerating. |
Example URL to request the transaction token
https://api.nearmap.com/coverage/v2/tx/address?country={country}&city={city}&state={state}&postcode={postcode}&streetAddress={streetAddress}&resources=aiImpactTriage:damageRating&dates=all&apikey={APIKEY}
Once generated, the transaction token is a long sequence of numbers, letters and symbols stored in the transactionToken field.
Requesting data
Use the following URL to request data using the AI Feature API:
https://api.nearmap.com/ai/damage/v1/tx/surveyresources/{aiResourceId}/rating.csv?transactionToken={transactionToken}&classification=3tier
All available Damage Classifications AI data will be returned as a CSV file as shown below.
CSV file contents
Attribute | Description | Value |
|---|
Damage Class | The classification of the level of damage of the building. This damage class is provided for the building that we could most closely match with the provided latitude and longitude. The building latitude, building longitude and MapBrowser link can be used to determine which building each classification refers to. Note that the damage classification only takes into consideration damage to the single building and does not include damage to other buildings or objects on the property such as fences. | One of the following: - No Damage - Affected - Minor Damage - Major Damage - Destroyed |
Survey date | The date of the imagery used to determine the damage classification. Note that the classification is specific to this date and does not take into consideration the imagery from any earlier or later dates. | Date format DD/MM/YYYY |
MapBrowser link | Link to the relevant building in MapBrowser imagery. For locations with imagery available for a date prior to the disaster event, this is a split view with the earlier date on the left and the event date on which the classification was performed on the right. If no earlier imagery is available for an area, this shows the imagery for the single disaster date. | URL |
Building Latitude | Latitude of the center of the building identified by our model, for which the damage class has been calculated. | Numeric |
Building Longitude | Longitude of the center of the building identified by our model, for which the damage class has been calculated. | Numeric |
Building Structural Loss % | The percent of the identified building that was classified as suffering structural loss. This is defined as sections of the building where the structure no longer exists or can serve its purpose. | Numeric (0-100%) |
Building with Structural Damage % | The percent of the identified building that was classified as building with structural damage. This is defined as destruction exposing the interior of a structure to the elements, that does not prevent the structure from performing its function. | Numeric (0-100%) |
Structurally Damaged Roof % | The percent of the identified building that was classified as structurally damaged roof. This is defined as any part of a roof with structural damage that could cause water leakage. | Numeric (0-100%) |
Missing Roof Tile or Shingle % | The percent of the identified building that was classified as missing roof tiles or shingles. This is defined as an area of exposed underlay where one or more expected pieces of roof covering are not found. | Numeric (0-100%) |
Roof with Temporary Repair % | The percent of the identified building that was classified as roof with temporary repair. This is defined as any part of a roof with temporary repair work, such as tarpaulin over damaged parts | Numeric (0-100%) |
Junk and Wreckage % | The percent of the identified building that was classified as junk and wreckage. This is defined as any junk or rubbish manufactured by humans, and now discarded from its original use. This includes any building that has been damaged so badly that it no longer has a clear building structure. Note that this only includes junk and wreckage that is inside the defined outline of the building itself, not anything in the surrounds of the building. | Numeric (0-100%) |
Vegetation Debris % | The percent of the identified building that was classified as vegetation debris. This is defined as any natural debris because of storms, flooding, or other reasons where vegetation is uprooted or damaged. Note that this only includes vegetation debris that is inside the defined outline of the building itself, not anything in the surrounds of the building. For example, a tree branch on a roof will be included in this category but fallen trees in the yard of a property will not be. | Numeric (0-100%) |
Damage by Tree | The percent of the identified building that was classified as damaged by tree. This is defined as any building that a tree has fallen on and penetrated one or more external protective layers. Note that this includes only standing buildings with fallen/broken trees on top of them, punctures or holes in building materials caused by trees and roofs with significant branch or tree debris on it. | Numeric (0-100%) |
