The UN Satellite Center collaborates with NVIDIA to advance its Sustainable Development Goals

Published June 28, 2022, 4:07 PM

by Enzo Luna

NVIDIA is collaborating with the United Nations Satellite Center (UNOSAT) to use deep learning and AI to promote climate action for a healthy global environment.

The initiative supports the United Nations’ 2030 Agenda for Sustainable Development, which includes 17 interconnected Sustainable Development Goals. These SDGs, which include “climate action” and “sustainable cities and communities,” serve as a rallying cry for all UN member states to work together to improve global well-being.

This was the dominant topic discussed by NVIDIA and UNOSAT during their recent media presentation on improving climate-related disaster management through the use of AI for Earth Observation. AI4EO.

The collaboration between UNOSAT, a branch of the United Nations Institute for Training and Research, and NVIDIA is initially aimed at improving climate-related disaster management through the use of artificial intelligence for Earth Observation. AI4EO is a term that refers to initiatives that use artificial intelligence to monitor and assess global changes.


UNOSAT will integrate its satellite imagery technology infrastructure with NVIDIA’s accelerated computing platform to accelerate research and development for its AI4EO efforts. The artificial intelligence-powered satellite imagery system will collect and analyze geospatial data to provide near-real-time insights into floods, wildfires, and other climate-related disasters.

Furthermore, UNOSAT has launched an educational module based on an NVIDIA Deep Learning Institute (DLI) course on using deep learning methods to generate accurate flood detection models.

“Working with NVIDIA will enable us to close the loop from AI research to implementation of climate solutions in the shortest time possible, ensuring that vulnerable populations can benefit from the technology,” said Einar Bjørgo, director of UNOSAT.

AI-Powered Satellite Imagery Analysis

AI Dashboard

UNOSAT’s emergency mapping service uses computer vision and satellite imagery analysis to gain accurate information about complex disasters, such as assessing the impact of a tropical cyclone in the Philippines or a volcanic eruption in Tonga.

Climate-disaster management requires near-real-time analysis. Humanitarian teams can use AI’s data-driven insights to respond quickly and effectively to disasters. The data is also used to inform sustainable development policies, build user capacity, and improve overall climate resilience.

UNOSAT will upgrade its satellite imagery technology infrastructure with NVIDIA DGX systems, which enable AI development at scale, and the NVIDIA EGX platform, which brings the power of accelerated computing from the data center to the edge.

According to UNOSAT, NVIDIA technology accelerates AI-based flood detection by 7x, allowing it to cover larger areas with greater accuracy.

NVIDIA DLI Course on Disaster Risk Monitoring

A skilled workforce, in addition to powerful technology, is required to use AI and data science to analyze and prevent climate events from becoming humanitarian disasters.

“NVIDIA and UNOSAT have a unique opportunity to combat the impact of climate change and advance the UN’s SDGs, with a launching point of training data scientists to develop and deploy GPU-accelerated models that improve flood prediction,” said Keith Strier, vice president of global AI Initiatives at NVIDIA.

UNOSAT has created a module for the Deep Learning Institute’s free online course on how to build a deep learning model to automate flood detection.

Disaster Risk Monitoring Using Satellite Imagery is NVIDIA’s first of many planned climate action courses for the global public sector community.

Based on a real UN case study, UNOSAT’s module highlights an example of a flood in Nepal.

In collaboration with NVIDIA, UNOSAT is providing the module for free in order to train data scientists around the world to use accelerated computing to predict and respond to climate-related disasters.

“We aim to democratize access to accelerated computing to help nations train more accurate deep learning models that better predict and respond to a full spectrum of humanitarian and natural disasters,” Strier said.

Get started with the course, which is now available.

Learn more about how NVIDIA technology is used to improve the planet and its people.