Nearmap AI customers can subscribe to any of the available AI Packs. This is allows you to view specific AI Layer attributes and export the AI Parcel data, both from within MapBrowser.

Available Packs

Currently available AI Packs are:

AI PackAI Layers IncludedAI Parcel Data Included*

Construction

Construction SiteConstruction presence in a parcel (area estimate and centroid refer to parcel).

Pool

Swimming PoolSwimming pool presence; area estimate and centroid of each pool.
BuildingBuilding Footprint presence; area estimate and polygon for each building footprint.
Residential Roof Characteristics 

Roof Material (Tile, Metal, Shingle)

Roof Shape (Hip, Turret, Flat, Gable)

Tree Overhang

Attributes of each Building Footprint: Dominant Roof Material, presence of each roof shape.

Tree Overhang presence; area estimate and polygon of each element of overhang.

Solar

Solar PanelSolar panel presence; area estimate and centroid of each solar array.

Trampolines

TrampolineTrampoline presence; area estimate and centroid of each trampoline.


*All data are based on WGS84 (EPSG:4326)

**If you subscribe to Residential Roof characteristics you must also subscribe to Residential Building Footprints.


Statistical Performance

The table below is a summary of the statistical performance for each attribute with a "Y"/"N" flag in the spreadsheet output of an AI Parcel export. These numbers refer to whether at least one object of this type is present in an AI Parcel. The AI Packs also define what data will be delivered if you order a bulk offline delivery of data.


To ensure that our performance scores are as objective as possible, our examples are drawn from a statistically determined sample across our coverage regions that is weighted towards populated areas. We have deliberately chosen a significant portion of our examples as challenging cases where our models are least certain. 


Our "source of truth" is a highly trained team of human expert labellers, who use a custom version of MapBrowser to check multiple dates, multiple angles, and even our 3D models to determine whether they believe an object is present. Our brief is "on the assessment date, mark what you judge to be present using all MapBrowser tools available to you". This means that a swimming pool missed on a leaf-on survey will be marked as incorrect, if the labeller can see the pool before or after that point in our capture history.

As a customer, you will notice three practical causes of error that stand out above all others:

  • Inconsistencies in third party parcel boundaries, causing an object to be misidentified as belonging to a neighbouring property.
  • Definitional differences, where your working definition is subtly different from ours (such as our current Building Footprint definition excluding rooftop carparks).
  • What we like to term "forgivable errors" where, on clicking the MapBrowser link provided with every AI Parcel output, you may think to yourself "I appreciate why that would have happened". This is most noticeable for the Construction Site class, where the Precision is decreased by picking up things such as landscaper's yards full of rubble and trucks, and the Recall is decreased mostly by examples of the first stage of construction, which is usually just an area of dirt with no obvious construction occurring.

Our models do of course make other kinds of errors; however this is one of the primary reasons we have provided you with the ability to view AI Layers in Map Browser. Nearmap AI gives you a unique perspective of the truth on the ground based on visual data, with different strengths and weaknesses to other sources (such as paper records of construction or solar installations). The consistent behaviour makes it an excellent source of truth as a standalone data product. If you have an existing data set representing a different perspective, we encourage you to combine it with ours to achieve a much more accurate picture than either perspective could alone.

Precision (Correctness)

We are correct approximately <Precision %> of the time, in cases where we said "Yes". For example, we are correct 98.5% of the time in cases where we said "Yes, this is a swimming pool".

Precision is about whether the model accidentally flags parcels as "Yes". e.g. if we incorrectly flag a landscaper's yard as construction, it reduces the Precision.

Recall (Completeness)

We find approximately <Recall %> percent of the parcels which should actually say "Yes". For example we find approximately 92% of the parcels containing a swimming pool which actually do contain a swimming pool.

Recall is about whether the model accidentally misses parcels which should be picked up as "Yes". e.g. if we miss flagging a swimming pool because it is hidden completely under trees on the assessed imagery date, it reduces the Recall.


Precision and recall summary by attribute

Class (object presence in a parcel, or on a building)

Precision

Recall
Building99.9%99.6%
Dominant Roof MaterialTile Roof96%95.7%

Shingle Roof95%96.6%

Metal Roof86%90%

Other92%84%
Roof shapeHip96.9%96%

Gable95.5%93%

Flat88%96.1%

Turret100%47%*
Construction Site**83%60%
Swimming Pool98.5%92%***
Solar Panel95.3%****98.5%
Trampoline95.9%88%


* 2/3 of the examples of missed turrets in the test set were partial round turrets (see AI Pack: Residential Roof Characteristics).

**The majority of missed construction is bare earth and slab down, before obvious signs of construction have commenced. The majority of false positive construction is "construction like" such as landscaper yards, or parcels with a lot of rubble and exposed dirt.

***The majority of missed swimming pools are very small above ground pools in a poor state of repair, or with a winter cover on.

****The majority of false positive solar panels are solar hot water systems, and easily excluded by cutting out lower confidence examples.


Confidence

We help you make sense of the data and how you can use it by giving each attribute a Confidence score. This score is a representation of how much we believe the classification to be true.

Our confidence at detecting the different attributes varies, as some are more challenging than others.

US "regional" confidence values

The confidence results for Australia and each key US region are included in the discussion of each attribute for each AI Pack. The US regions are shown in the map below.

These results are presented graphically, like the sample below, with the highest confidence bands being the darkest colour.



Jump directly to the confidence discussion for each AI Attribute using the links below:

Building Confidence

Dominant Roof Material - Tile Roof Confidence

Dominant Roof Material - Shingle Roof Confidence

Dominant Roof Material - Metal Roof Confidence

Dominant Roof Material - Other Roof Confidence

Roof Shape - Hip Confidence

Roof Shape - Gable Confidence

Roof Shape - Flat Confidence

Roof Shape - Turret Confidence

Construction Site Confidence

Swimming Pool Confidence

Solar Panel Confidence

Trampoline Confidence

Minimum Object Sizes

The table below defines the minimum attribute area. Any object smaller than this mimimum area is excluded form the AI data set. 


m2
ft2
Solar Panel332
Swimming Pool443
Building Footprint997
Construction Site997
Trampoline332
Tree Overhang00

AI Parcel Data Specifications

Spreadsheet Data

This represents a summary of information, where each row is a property parcel, and columns are summarised facts about that parcel. It often contains less information than the geospatial data, but is very convenient to use if you do not have a GIS background. We often refer to it as a "parcel rollup", because it rolls up information about all objects detected in that AI Parcel to a single row in a database, a little like a geospatial version of a "GROUP BY" aggregation over parcels.

Most of the .csv files (comma separated value files) have common elements:

.csv file

Common elements of .csv files

This applies to Trampoline.csv, Swimming_Pool.csv, Solar_Panel.csv, Construction_Site.csv

ColumnDescriptionFormat
property_idUnique parcel identifier from third party provider that best matches the parcel

GNAF (AU) / Parcel APN (US)

survey_dateCapture date of imagery used for the object detectionDD/MM/YYYY 
address

Address data as supplied by third party that best matches the parcel
NB: We still process parcels that have a blank address field from third party providers, as they often represent a legitimate property parcel.


longitudeLongitude coordinate of parcel centroid (EPSG:4326 WGS84)
latitudeLatitude coordinate of parcel centroid (EPSG:4326 WGS84)
attributeName of the attribute represented by the file, e.g. "Trampoline"
presentYes/No value representing whether at least one example of the object has been detected "Y" or there has been insufficient evidence that any examples exist in the parcel "N".Y/N
confidence

A percentage measure (represented as e.g. "100%" in the file) of the likelihood we believe the "present" decision is correct.

"Y" cases are typically well calibrated, such that the decision should be correct in 9/10 cases among all examples with a confidence of 90%.

Note that "N" cases are typically set to 100% confidence for technical reasons (when there is no evidence at all of object presence, it is not possible to separate out different confidence levels meaningfully. 100% is approximately well calibrated, given the true negative rates are typically in excess of 99%).

%

area_estimate_sqm

OR

area_estimate_sqft

An estimate of the total summed area of all instances of this type within the parcel, e.g. aggregate all sections of solar panel array. Units are selected automatically based on region, and reflected in the column name. Given the variation in areas due to occlusion from tree overhang etc., no statistical guarantees are made about the accuracy of the areas. Observing the AI Layers give a good visual indication of how well the area of each object is likely to be captured.

Estimated area is in the horizontal plane and does not take slope and 3D structure into account.

For Construction_Site.csv, the area represents the area of the parcel, not the area of the objects.


area_estimate_sqm - m2 (AU)

area_estimate_sqft - ft2 (US) 

map_browserDirect link to the parcel centroid at the specified survey date in MapBrowser. This can be used for examining why a particular decision may have been made.
wktWell Known Text representation of parcel centroid for easy use within GIS software.


Additional elements of .csv files

Some files have the above columns, plus additional ones representing further information. These include:

Building_And_Roof_Characteristic.csv

Additional ColumnDescription
building_confidenceRepresents the likelihood that the "present" field is correct for "Roof", indicating the likelihood that there is at least one building present in the parcel.
dom_roof_materialText field set to: "Tile", "Shingle", "Metal", "Other" or "NA"

The Dominant Roof Material of the primary (largest) 'Roof/Building' within the parcel. "NA" is indicated when no buildings at all are detected in the parcel.
dom_roof_material_confidenceThe percentage likelihood that the dominant roof material has been chosen correctly.
roof_hipAs per "present" field, applied to hip elements on the largest roof in the parcel.
roof_hip_confidenceAs per "confidence" field, applied to roof_hip.
roof_gableAs per "present" field, applied to gable elements on the largest building in the parcel.
roof_gable_confidenceAs per "confidence" field, applied to roof_gable.
roof_flatAs per "present" field, applied to flat elements on the largest roof in the parcel.
roof_flat_confidenceAs per "confidence" field, applied to roof_flat.
roof_turretAs per "present" field, applied to turret elements on the largest roof in the parcel.
roof_turret_confidenceAs per "confidence" field, applied to roof_turret.
tree_overhangAs per "present" field, applied to presence of non-zero area of tree overhang on the largest building in the parcel.
tree_overhang_confidenceAs per "confidence" field, applied to tree_overhang.

tree_overhang_area_sqm

OR

tree_overhang_area_sqft

As per "area_estimate", except referring to the summed area of tree overhangs on the largest building in the parcel.

Rich Geospatial Data

The GeoPackage files provided contain all the information in the spreadsheet files, but have some key differences, and represent more fine grained information about geospatial positions, areas and shapes of individual objects. It has been tested to open in QGIS, Esri's suite of ArcGIS products, and using the GeoPandas python package.

The geopackage data are all based on WGS84 (EPSG:4326).

Point Objects

  • The point represents the centroid of the object rather than the centroid of the parcel.
  • The area estimate represents the area estimate of that object (not the aggregated area of the object type within the parcel).

If multiple objects are present in a parcel, multiple points per parcel may be returned, each with their own area estimates. For Solar Panels, each group of panels on a roof is typically represented as a separate object. This applies to (Trampoline.gpkg, Swimming_Pool.gpkg, Solar_Panel.gpkg). Construction_Site.gpkg is the exception, where the point always represents the parcel centroid.

Polygon Objects

If only the "Residential Building Footprint" AI Pack is enabled, the file Building.gpkg will be present. The polygons represent every Building Footprint detected in each parcel.


If the "Residential Building Characteristics" AI Pack is also enabled, this file is replaced by Building_Footprint_With_Roof_Characteristic.gpkg. It contains the same Building Footprint polygons, with additional metadata for dominant roof material and roof shapes of each building. In that case, the file "Tree_Overhang.gpkg" will also be present, which contains polygons of all overhanging sections of tree detected.