IBM and open-source AI platform Hugging Face has announced that IBM’s watsonx.ai geospatial foundation model – built from NASA’s satellite data – will be available on Hugging Face. It will be the largest geospatial foundation model and the first-ever open-source AI foundation model built in collaboration with NASA.
As part of a Space Act Agreement with NASA, IBM set out earlier this year to build an AI foundation model for geospatial data. And now, by making a geospatial foundation model available, efforts can advance to democratize access and application of AI to generate new innovations in climate and Earth science.
The model – trained jointly by IBM and NASA on Harmonized Landsat Sentinel-2 satellite data (HLS) over one year across the continental United States and finetuned on labeled data for flood and burn scar mapping — has demonstrated to date a 15 percent improvement over state-of-the-art techniques using half as much labeled data. With additional fine tuning, the base model can be redeployed for tasks like tracking deforestation, predicting crop yields, or detecting and monitoring greenhouse gasses. https://newsroom.ibm.com
The Overture Maps Foundation (OMF), a collaborative effort to enable current and next-generation interoperable open map products, announced the release of its first open map dataset.
It includes four unique data layers: Places of Interest (POIs), Buildings, Transportation Network, and Administrative Boundaries. These layers, which combine various sources of open map data, have been validated and conflated through a series of quality checks, and are released in the Overture Maps data schema which was released publicly in June 2023.
The Places dataset includes data on over 59 million places worldwide and will be a foundational element of navigation, local search and many other location-based applications. https://overturemaps.org
>Mapbox 3D mapping designed to enhance location awareness
Mapbox has released new platform updates to enhance user’s 3D mapping experience by adding powerful dynamic lighting capabilities and landmark 3D buildings. The new ready-to-use platform aims to enhance wayfinding and spatial orientation for users and provides a polished canvas for custom location data. www.mapbox.com
Ras Al Khaimah (RAK) has become the first city in the Middle East to implement “Parcel Fabric” technology for managing spatial land data, based on a certificate granted by the Esri.
In partnership with the GIS Centre, Ras Al Khaimah Municipality is using the Parcel Fabric technology to manage the spatial information of land plots through the rules and definitions it defines. This spatial data forms the basis of the systems that register land ownership and other real estate interests and is, therefore, key to the effective management of any city. Adopting the technology, which is linked to the land registry, will help preserve the rights of owners and property investors in the Emirate. The system improves records’ accuracy, increasing operations efficiency and reducing the time required for tasks such as modifying and updating land records.
Parcel Fabric allows cadastral data to be fit for purpose by storing the required metrics and metadata, such as the method of capture, date, spatial accuracy and historical lineage, for use and publishing as needed. In addition, the built-in data quality management mechanisms ensure the accuracy of other key elements, such as topology and plot attribution. www.zawya.com