GeoAI

Satellite image with AI-detected building outlines showing intact and destroyed structures following a hurricane.

Mapping populations to keep people safe

Through advances in artificial intelligence, Oak Ridge National Laboratory is transforming geospatial analytic methods in support of information exploitation and dissemination into geospatial intelligence (GEOINT) foundational data layers. 

With core strengths in machine learning for high-performance computing, geoassurance, probabilistic reasoning, and spatio-temporal analytics, we are developing geospatial artificial intelligence (GeoAI) methods focused on several key research areas.

Trillion Pixel Challenge

In June 2023, we hosted our 3rd Trillion Pixel Challenge, an interdisciplinary gathering of experts from image science, computer vision, high-performance computing, architecture, machine learning, advanced workflows, and end-user communities to discuss the way forward in scaling multimodal GeoAI.

Learn More
Read the workshop report

We're a multidisciplinary team

To deliver our mission, we need dedicated, mission-driven researchers with expertise in electrical engineering, applied mathematics, computer engineering, statistics, computer science, data science, and more!

In addition to these academic backgrounds, our team has expertise in Artificial Intelligence, Probabilistic Reasoning, Computer Vision, Risk Analysis, Visual Analytics, High-Performance Computing, Geographic Information Science, Ontology Reasoning, and Remote Sensing.

Exploring complex geospatial analytic workflows

Aerial view of hurricane damage, with computer-generated utility pole detection.

Spatio-temporal Analytics for Global Data

Integrating global datasets and applying advanced analytics to identify trends, patterns, anomalies, and changes in national landscapes.
A color-coded map of socioeconomic neighborhood types

Settlement Characterization

Exploiting overhead imagery to develop scalable ways to characterize socioeconomic neighborhoods for economic stimulus, unstructured settlement mapping, population distribution studies, and more.
city map showing automated feature identification and extraction

Automated Feature Extraction

Employing machine learning, computer vision, and high-performance computing to automate the creation of foundational data layers for building footprints, road networks, solar panels, and more at scale.
World map showing color-coded population density

Population Dynamics

Applying Bayesian learning approaches to estimate building occupancy at varying times of day and night across a variety of sociocultural environments, improving urban planning, emergency management, and disaster response.
gravity map

Gravity Mapping

Adapting AI techniques to produce high-resolution gravity maps on a global scale to support navigation systems, early detection of potential earthquakes, and measurement of changes in water patterns

Keeping people safe

Disaster Response

Our deep-learning methods underlie a critical geographic dataset used during hurricane response efforts

Critical Infrastructure Resilience

ORNL tools help ensure energy supply

AI on the Edge

ORNL researchers developed a mobile system to quickly detect objects and analyze images following disasters

Portrait of a man in an orange shirt

Contact

Dalton Lunga, GeoAI Group Leader and Sr. Research Scientist
View profile