In general, Geospatial Artificial Intelligence (GeoAI) or Spatial AI refers to geospatial machine learning and deep learning capabilities that gather usable information and intelligence, which enable users to detect, track, discover, classify, predict, and analyze location related business events, geospatial objects, and ground features on the Earth.

Geospatial data is everywhere, and most events and business data are associated with location. Location plays a critical role in affecting environment, events, and businesses. Therefore, analyzing and applying location and related information to gather useful intelligence for various applications is important.

The following lists a few use cases where Spatial AI helps organizations to understand better the business opportunities, environmental impacts, or operational risks and gain valuable insights to make informed decisions:

• Analyzing patterns of cancer and epidemic disease such as cholera, SARS, and Covid-19.
• Finding hot spots of crime to help police to make staffing and patrolling decisions.
• Identifying patterns of car accidents or pedestrian deaths to help optimize arrangements of red lights and road networks.
• Predicting house prices based on census data and location information and helping to choose a home considering the home’s proximity to economic opportunities, schools, health care, and roadways for commutes.

The current release of Oracle Spatial AI provides geospatial machine learning algorithms for analyzing and modeling geospatial vector data and location related events. It provides geospatial machine learning techniques, end-to-end workflow, and related APIs.

Spatial AI is integrated with Oracle Machine Learning (OML) and is deployed with OML4Py on Oracle Autonomous Database Serverless cloud service. This implies that you can access Spatial AI through OML interfaces and services on you Autonomous Database Serverless instance.

You can leverage this product to prepare and analyze data stored in Oracle Spatial and Oracle Cloud Infrastructure (OCI) Object Storage, train spatial machine learning models, and apply the models in a variety of applications. For example, you can apply clustering techniques to identify spatial patterns of events, detect hot spots, cold spots, anomalies and outliers. You can also apply spatial regression and classification techniques to analyze spatial data, predict house prices, and classify poverty levels.