Combining satellite imagery and next-generation AI

AI For Business


Author: Kevin Weil, Andrew Zori

In 2018, Planet co-founder and CEO Will Marshall asked the audience during a TED talk:

It wasn’t science fiction. Use artificial intelligence (AI) and machine learning (ML) to index objects on Earth over time. This will allow you to search for ships, trees, buildings, and other objects on Earth the same way you search with your Internet browser. Planet and its partners have made rapid progress in this area since Will’s TED talk: tracking high-altitude balloons, classifying building damage to aid in disaster response, and building utility-scale applications around the world. Such as mapping wind and solar power.

Some of these projects were done in collaboration with Microsoft’s AI for Good Lab. In those rooms, we were manipulating each other’s data and tools, processing the code we asked ourselves. other than that Can the combination of high-resolution satellite imagery and AI technology help solve some of humanity’s greatest challenges?

Fundamentally, access to data and insights made available through digital analytics can be transformative for businesses, academics, researchers, policy makers, and others. As the world seeks an explanation for physical changes on Earth, data can inform tracking supply chains, actions to mitigate the effects of climate change, disaster preparedness and response, and food insecurity. .

So at Explore23, Planet’s annual user conference, we presented the results of one of Microsoft’s and Planet’s brainstorming sessions. How to make satellite data more accessible to all by using next-generation AI to make it searchable, conversational, and context-aware.

Together with the Microsoft AI for Good Lab, we built this proof-of-concept project, affectionately known as “Queryable California.” This won’t show up in your internet browser tomorrow, but it shows the best possible technology. And that’s what’s incredibly exciting for us.

The idea of ​​Queryable California is that Microsoft’s next-generation AI will index the physical properties of life on Earth and make them searchable, making high-resolution satellite imagery and planetary variable data products more accessible. Evaluate ways to make it easier. Understand language in a real-world context of place and time. All hope to give people the data and insights that can guide them in making better decisions with just a few keyboard presses.

In this demo video below, you can see me asking a customized next generation AI interface about the temperature in Sacramento. We combined this with our query engine and datasets from Planetary Variables (such as surface temperature) to enable AI to calculate key insights such as the average surface temperature and the hottest year in the last 20 years. In the case of wildfires, we can learn not only how many trees were destroyed in the 2018 California Campfires, but also how much forest carbon was lost. This is an example of what we often talk about. It’s the future of abstracting satellite imagery and giving users the specific information from the imagery they need to make decisions.

Speaking to Planeteer, visualizing change is about agile aerospace and Planet’s ability to rapidly build massive satellite constellations that can generate new datasets the world has never seen before. I know there is. Making change accessible means connecting that data so it can be analyzed quickly and easily, helping customers and partners derive insights from it. Making change actionable is delivering these building blocks to our customers wherever they are and providing an Earth Data Platform that allows them to incorporate our solutions into their workflows.

So this proof of concept shows what we mean and what we’re aiming for. This is just one of his examples of what Planet’s satellite data and Microsoft’s AI technology can unlock, and we look forward to sharing more in the future.

Forward-Looking Statements

Except for the historical information contained herein, the matters contained in this blog are forward-looking statements within the meaning of the “safe harbor” provisions of the Private Securities Litigation Reform Act of 1995, which include, but are not limited to, the Company’s Including but not limited to abilities. To capture market opportunities and realize potential benefits from current or future product enhancements, new products, or strategic partnerships and customer collaborations. Forward-looking statements are based on our management’s beliefs, assumptions and currently available information. Such statements are based on expectations of future events or results and are not statements of fact, and actual results may differ materially from those projected. The factors that could cause actual results to differ materially from current expectations include the risk factors relating to the Company and its business contained in the Company’s periodic reports, proxy statements and other disclosure materials filed from time to time. and other disclosures, including but not limited to. Securities and Exchange Commission (SEC) information is available online at www.sec.gov and our website at www.planet.com. All forward-looking statements reflect our beliefs and assumptions only as of the date such statements are made. We undertake no obligation to update any forward-looking statements to reflect future events or circumstances.

# # #



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *