Overview
Nearmap AI contains a rich and continually growing library of content. AI Layers are the most basic unit of content; they feed into all of our AI data products, can be ordered as an offline data delivery, and in some cases can be visualized within MapBrowser. The AI Layer Glossary provides a list of all AI Layers produced by our models, along with definitions, examples, and links to any AI Packs that make them available.
What are AI Layers?
An AI Layer is a a single data layer that is processed on whole surveys of our imagery coverage. It represents a fairly direct output of our machine learning models, which is used in various ways in our post-processing pipelines. At present, they are available in two ways:
AI Packs: Some layers are included in an "AI Pack", and are enabled for visualization in MapBrowser, and included as an input into a vectorised product that can be exported from MapBrowser. When visualized, these AI Layers form an overlay over our imagery to assist visual search.
Offline Delivery : AI Layers can be ordered for offline delivery (downloadable files). AI Layers will often appear in the glossary before they have been made available through an AI Pack.
Note that where an AI Layer lists AI Packs as "Not yet available", it can still be ordered as an offline delivery. See AI Offline Raster - Ordering and Delivery for details.
AI Layer lifecycle
At Nearmap, we're constantly innovating and improving our AI capabilities. To ensure that our users have access to the most cutting-edge tools, we categorize our AI layers into different lifecycle stages:
- Alpha
- Beta
- Production
- Deprecated
Alpha
- What is it? Alpha AI layers are in their early stages of development. They may have limitations or bugs, and their functionality is not yet fully guaranteed.
- Why do we have it? Alpha layers provide a platform for experimentation and feedback. By releasing them early, we can gather valuable insights from our users and make necessary improvements before the layer is fully mature.
- What to expect: Alpha layers may be subject to frequent changes or updates. Their accuracy and performance may not be as consistent as Beta or Production layers. It is recommended that you use them with caution and be aware of potential limitations.
Beta
- What is it? Beta AI layers are those that have undergone initial testing and are considered more stable than Alpha layers. However, they may still have minor bugs or limitations.
- Why do we have it? Beta layers offer a more solid experience than Alpha layers, while still providing opportunities for user feedback and further refinement.
- What to expect: Beta layers are generally reliable, but there may be occasional issues or unexpected behavior. We encourage users to report any problems they encounter so we can address them promptly.
Production
- What is it? Production AI layers have been thoroughly tested and are considered mature and reliable. They have undergone rigorous quality assurance processes and are expected to perform consistently in production environments.
- Why do we have it? Production layers are ideal for critical applications and projects that require a high level of accuracy and dependability.
- What to expect: Production layers are the most robust and feature-complete AI layers in our portfolio. They are designed to provide consistent performance and minimal downtime.
Deprecated
- What is it? Deprecated AI layers are no longer actively supported or maintained. They may have been replaced by newer, improved versions, or they may have become outdated due to changes in technology or user needs.
- Why do we have it? Deprecated layers are kept available for reference or compatibility purposes.
- What to expect: Deprecated layers have minimal support. Deprecated layers should not be used for new projects and existing projects should be migrated to use alternative layers.
Choosing the right AI layer
The choice of AI layer depends on your specific needs and risk tolerance. If you are looking for the latest features and are willing to accept potential risks, an Alpha or Beta layer may be suitable. If you prioritize stability and reliability, a Production layer is recommended.
AI Layer relationships
An AI Layer may be related to a layer in a different AI Pack by virtue of sharing a common attribute. A relationship is indicated by the presence of the ParentID attribute, if no value is present then no relationships exist.
For example, a Roof Condition layer identifies the condition of a roof as stained or damaged. This layer also needs information about the type of roof (tile, shingle, etc), which it obtains using the ParentID attribute that corresponds to the layer ID attribute in the Roof Characteristics pack.
IDs are not persistent between surveys and therefore relationships are only valid when layers have been created from the same survey date.