Every day, NASA satellites orbit the Earthcapturing a wealth of information that helps us understand our planet. From monitoring wildfires to tracking climate change, this vast trove of Earth science data has the potential to lead to scientific discoveries, inform policy decisions and support sectors such as agriculture, urban planning and disaster response.

But navigating the more than 100 petabytes of collected data can be difficult. That’s why NASA collaborated with Microsoft to explore the use of a custom copilot using Azure OpenAI Service to develop NASA’s Earth Copilot, which could transform the way people interact with Earth data.

Geospatial data is complex and often requires a certain level of technical expertise to access. As a result, these data tend to be accessible only to a limited number of researchers and scientists. As NASA collects more data from new satellites, these complexities only increase and could further limit the potential pool of people who can learn from them and develop applications that could benefit society.

Recognizing this challenge, NASA embarked on a mission to make its data more accessible and user-friendly. As part of its Transform to Open Science initiative, the agency seeks to democratize access to data, removing technical barriers to empower a wide range of audiences, from scientists and educators to policymakers and the general public.

The challenge: navigating the complexity of data

NASA’s Earth Science Data Systems program is responsible for collecting an incredible variety of data from space sensors and instruments. This data covers everything from atmospheric conditions to land cover changes to ocean temperatures and much more. However, the scale and complexity of this information can be overwhelming. For many, finding and extracting information requires navigating technical interfaces, understanding data formats, and mastering the intricacies of geospatial analysis – specialized skills that very few non-technical users possess. AI could streamline this process, reducing the time it takes to obtain insights from Earth data to seconds.

This problem is not just a matter of convenience; this has real-world implications. For example, scientists who need to analyze historical hurricane data to improve predictive models, or policymakers who want to study deforestation patterns to implement environmental regulations, may find themselves unable to do so. easily access the data they need. This inaccessibility affects a wide range of sectors, including agriculture, urban planning and disaster response, where timely insights from spatial data could make a significant difference.

Additionally, as new satellites with new instruments continue to launch and collect more data, NASA continually faces the challenge of creating new tools to manage and make sense of this growing repository. The agency explored emerging technologies that could not only streamline data discovery, but also expand accessibility, allowing more people to interact with data and discover new insights.

The solution: AI-powered data access through Microsoft Azure

To address these challenges, NASA IMPACT worked with Microsoft to develop an AI-powered client copilot, called Earth Copilot, that could simplify data access and encourage a wider range of users to interact with its science data. of the Earth. Together, they built the proof-of-concept AI model that leverages Microsoft’s Azure cloud platform and advanced AI capabilities to transform how users can search, discover and analyze NASA geospatial data.

The key to NASA’s Earth Copilot is the integration of cloud-based technologies like Azure OpenAI Service, which provides access to powerful AI models and natural language processing capabilities that allow developers to integrate intelligent conversational AI in their applications. This approach allows NASA to integrate AI into its existing data analysis platform – VEDA. Together, these technologies make it easier for users to search, discover and analyze Earth science data.

By combining these technologies, Earth Copilot allows users to interact with NASA’s data repository through plain language queries. Instead, they can simply ask questions like “How much impact did Hurricane Ian have on Sanibel Island?” or “How has the COVID-19 pandemic affected air quality in the United States?” » The AI ​​will then retrieve the relevant data sets, making the process transparent and intuitive.

“Azure’s robust suite of services, including machine learning, data analytics and scalable cloud infrastructure, powers this AI prototype,” said Juan Carlos López, former NASA engineer and current specialist. Azure at Microsoft. “We designed the system to efficiently handle complex queries and large data sets, ensuring that users can quickly find the information they need without getting bogged down in technical complexities. Our goal was to create a transparent, scalable solution that could evolve as NASA’s data, tools, and applications grow.

Democratizing data for open science

The collaboration between NASA IMPACT and Microsoft has resulted in a solution that democratizes access to space data, allowing a wider range of users to interact with NASA science data. This has significant benefits for the scientific community, as researchers can now spend less time on data retrieval and more on analysis and discovery. For example, climatologists can quickly access historical data to study trends, while agricultural experts can gain insights into soil moisture levels to improve crop management.

Educators and teachers can use real-world examples to engage students in Earth science, sparking curiosity and encouraging the next generation of scientists and engineers. Policymakers can leverage data to make informed decisions on critical issues such as climate change, urban development and disaster preparedness, ensuring they have the most accurate information at their fingertips.

“The vision behind this collaboration was to leverage AI and cloud technologies to bring Earth’s knowledge to underserved communities, where access to data can lead to tangible improvements,” said Minh Nguyen, architect of cloud solutions at Microsoft. “By allowing users to interact with data via simple and clear queries, we are helping to democratize access to spatial information. »

The development of this AI prototype is part of NASA’s Open Science initiative, which aims to make scientific research more transparent, inclusive and collaborative. By removing barriers to data discovery, NASA and Microsoft are paving the way for a new era of discovery, where knowledge is not reserved for a privileged few but can be explored and developed by any curious person in the world.

Looking Ahead: Bridging the Gap Between Data and Insights

Currently, the NASA Earth Copilot is available to NASA scientists and researchers to explore and test its capabilities. Any responsible deployment of AI technologies requires rigorous assessments to ensure that data and results cannot be misused. After a period of internal evaluations and testing, the NASA IMPACT team will explore the integration of this capability into the VEDA Platform.

This collaboration illustrates how technology can empower people, drive innovation and create positive change. Solutions like this will be key to ensuring the benefits of data are widely shared, enabling more people to interact, analyze and act on the information that shapes our world.

Tags: AI, Azure OpenAI Service, Co-pilot, Microsoft Azure