Friday, April 19, 2024
ad
HomeNewsIBM and NASA Unveil AI Geospatial Model to Track Earth's Climate and...

IBM and NASA Unveil AI Geospatial Model to Track Earth’s Climate and Landscape Change

By turning satellite data into high-resolution maps, this model aims to follow changes to Earth's terrain, like floods and wildfires, with the intention of revealing the planet's past and hinting at its future.

IBM and NASA announced their partnership on a new initiative at the beginning of the year, with the goal of developing AI foundation models to examine petabytes of text and remote-sensing data to make it simpler to develop AI applications suited to various geospatial tasks. Recently, the pair unveiled the first foundation model produced from the collaboration which is a part of IBM’s watsonx.ai geospatial offering.

By turning satellite data into high-resolution maps, this new geospatial foundation model aims to follow changes to Earth’s terrain, like floods and wildfires, with the intention of revealing the planet’s past and hinting at its future. At some time in the second part of this year, IBM clients should be able to preview the model through the IBM Environmental Intelligence Suite. 

IBM lists a few potential applications for the model in their news release, including estimating climate-related risks to crops, buildings, and other infrastructure, valuing and monitoring forests for carbon-offset programmes, and developing predictive models to assist businesses in developing climate change mitigation and adaptation strategies.

Read More: Microsoft Announces AI Personal Assistant Windows Copilot for Windows 11

This is the first foundation model created specifically for the analysis of geographical data, according to IBM. In order to pre-train the model, the IBM Research team used NASA’s Harmonised Landsat Sentinel-2 data, a collection of measurements that allows observations of land at a 30-meter spatial resolution around the world every two or three days. 

They then used hand-labeled instances of floods, fires, and other comparable occurrences that had an impact on the landscape, to train the model, resulting in a model that allows users to quickly select a region, task, and date period to obtain the visualized data. 

Subscribe to our newsletter

Subscribe and never miss out on such trending AI-related articles.

We will never sell your data

Join our WhatsApp Channel and Discord Server to be a part of an engaging community.

Sahil Pawar
Sahil Pawar
I am a graduate with a bachelor's degree in statistics, mathematics, and physics. I have been working as a content writer for almost 3 years and have written for a plethora of domains. Besides, I have a vested interest in fashion and music.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular