Wherobots, the Spatial Intelligence Cloud founded by the original creators of Apache Sedona, announced the general availability of Raster Inference for WherobotsAI. Raster Inference makes satellite or drone imagery analytically accessible for data developers who use SQL or Python. With flexible pay-as-you-go pricing and support for Wherobots hosted or custom computer vision models, solutions can be built from aerial imagery in hours versus weeks or months, at a fraction of the cost of starting from scratch.
Planetary imagery is transforming industries
Satellite and drone imagery are fueling advancements across agriculture, energy, transportation, climate science, clean-tech, and insurance. But these massive, unstructured datasets are complex and multidimensional, and the go-to computer vision tools used to extract insights from this imagery are not designed for the scale and variety of this data. Expertise is also needed to set up and manage specialized infrastructure, tune it to improve model performance, and shuttle inference results—the boundary polygons and coordinates that identify features of interest like buildings, flood damage, or crops—into a secondary solution capable of working with this data. It can take weeks or months for teams to stitch together what are often fragile solutions. These high costs make solutions from this data hard to attain, or simply “off limits.”
Also Read: Stellar Solutions Appoints Don Rynkowski as VP of Intelligence Sector
Aerial intelligence is now accessible
WherobotsAI Raster Inference makes the creation of solutions based on satellite and drone imagery significantly easier, lower cost, and accessible to existing data teams. Key features include:
- On-demand inference: Production ready inference pipelines can be created in seconds, on-demand, with no infrastructure to manage.
- Model Integration: Start quickly with Wherobots’ hosted machine learning models or easily import existing models.
- Unified environment: Easily join inference results with other datasets using Spatial SQL and Python with a spatial engine that’s up to 20x more performant than popular alternatives.
- Workload automation: Job Runs and an integration with Apache Airflow make it easy to automate insights.
- Improved model portability: Support for the MLM STAC (Machine Learning Model Spatial Temporal Asset Catalog) extension, a new standard co-developed by Wherobots to enhance model portability across platforms.
- Example notebooks: Wherobots provides example notebooks for Wherobots hosted models to help customers get started.
“Every day, petabytes of satellite data are produced. But without specialized talent, deep pockets, or significant time investments, this data often remains untapped, putting solutions out of reach,” said Mo Sarwat, co-founder and CEO of Wherobots. “Raster Inference changes the game by enabling teams to easily derive actionable insights from aerial imagery, on-demand. This solution puts unprecedented power into the hands of developers and data scientists, driving impactful innovations for businesses and the planet alike.”
Improving portability of geospatial AI
Wherobots co-developed the MLM STAC extension alongside experts from Université de Sherbrooke, CRIM, Terradue, Natural Resources Canada, and other collaborators. This standard addresses the challenge of model portability by requiring comprehensive metadata—including model properties, data, and processing requirements—to make geospatial AI models more sharable and deployable across platforms.
SOURCE: Businesswire