Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock () or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Over 50 years ago, the first Landsat archive satellite imagery arrived at the U.S. Geological Survey (USGS) Earth Resources Observation and Science (EROS) Center on rolls of film flown in from the East Coast, marking a significant milestone in the new era of Earth observation.
Since then, technology has significantly advanced, transforming the data and science at EROS.
Now an artificial intelligence revolution is enabling the USGS to accomplish a lot more—and at a much faster pace.
For decades after artificial intelligence (AI)—which refers to machines or computers designed to think, learn and make decisions like humans—was introduced in the 1950s, it was mainly used to follow a set of rules to solve specific problems. Later, a new type of AI called machine learning emerged. This approach relies on algorithms that detect patterns and uses them to make predictions, enabling systems to not only address specific issues but also to learn from their experiences and apply that knowledge in solving new problems.
USGS EROS Center Director Pete Doucette is enthusiastic about the potential AI now offers to meet complex science and data needs at the USGS and EROS. Doucette has served on high-profile AI panel discussions, and in a recent two-episode Eyes on Earth podcast series about AI, he compared earlier and modern AI to different ways to learn to ride a bike.
“You can learn to ride a bike from a manual, a user’s guide, on how to ride a bike. That's kind of a knowledge-based way of thinking about the early days of AI,” Doucette said.
“A more effective way to learn to ride a bike is to actually get on it and go through trial and error. Balancing and falling down over and over until you figure out how to balance, which is more in line with how machine learning works by processing information and learning from it in real time.”
Of course, machine learning can tackle far more complex topics than riding a bicycle, with outcomes that have far-reaching benefits.
The Annual National Land Cover Database (NLCD) was released in late 2024 as a reinvention of the prior NLCD, a longstanding and definitive national U.S. land cover resource valued by private industry, government agencies and university researchers.
New AI innovations made the Annual NLCD improvements possible, including providing a look at yearly land changes dating back to 1985. The previous NLCD was only able to offer new land cover data every two to three years and dated back only to 2001.
The primary source for Annual NLCD’s 16 land cover labels—for fields, forests, city development and more—is Landsat satellite imagery. Every satellite pixel, or 30-meter-by-30-meter plot, needed to be processed from 1985 to 2023 across the lower 48 states, which added up to 295 trillion pixels. With a goal of completing the entire release in two years, the development of more advanced methods was essential.
AI was used for both the classification, or labeling, of land cover types and also the detection of changes in land cover from year to year. That involved a lot of training data—helping the algorithms learn from labeled satellite data and from mistakes to predict labels and changes.
Rylie Fleckenstein, the Research and Development technical lead for Annual NLCD, discussed the deeper levels of machine learning used for Annual NLCD in the podcast episodes. Annual NLCD aimed for a faster, more automated approach that would not compromise on quality or consistency, versus slower methods in the past that relied more on human interpretation of imagery.
Deep learning is a type of machine learning that performs complex tasks and learns from the results, essentially training itself. Flecksenstein compared it to LEGOS. Rather than using the instructions to build a certain object in a certain way, he said deep learning is like “a box of LEGOS that you can construct in any way that you can think of that actually can better fit to your problem.”
Terry Sohl, Chief of the Integrated Science and Applications Branch at EROS, summarized how AI benefited not only Annual NLCD production and data users but also taxpayers. “A completely new methodology was stood up, all AI-based, linking three different AI models,” Sohl said. “We’re faster, we’re more efficient. We’ve saved the government and the taxpayers money, and we’re creating a superior product. It’s a win all the way around.”
Annual NLCD is not the only science work at EROS based on Landsat and reliant on AI. Another example is the Rangeland Condition Monitoring Assessment and Projection (RCMAP), which provides land cover detail specifically for rangeland in the western United States. AI helps make predictions about the amount of different types of land cover, including shrubs and grasses, across the landscape.
Other science efforts are showing interest in Annual NLCD’s AI methods, too, Sohl said. But there’s an even more advanced AI approach that EROS is exploring called a foundation model, which once set up could be adapted more easily to other projects. Foundation models are large-scale models trained on vast amounts of data that can be applied to a wide variety of tasks.
USGS EROS Research Physical Scientist Neal Pastick, who also participated in the podcast episodes, has been working to develop a suite of foundation models pretrained on large amounts of geospatial information such as imagery from Landsat and other satellites.
“The idea is akin to how large-language models operate on text,” Pastick said. ChatGPT, for example, reviews content on the internet and other places to learn from context and get better at predicting appropriate words in order to create new content. “But instead, we’re working with remote sensing data. So we’re trawling the entire archive, trying to exploit patterns therein and using that information to better understand the landscape around us.”
The results, which can range from mapping fire scars and monitoring snow depth to forecasting invasive plant species, could be applied to a wide variety of uses for land and water resource managers.
“Once we stand these models up, researchers and users don't have to start from scratch,” Pastick said. “They can leverage the weights within these models to kind of speed up deployment of solutions. In short, we're basically making a cost-effective tool for gaining insights from geospatial information.”
Beyond science, AI offers the potential to improve the operation of Landsat satellites overseen by USGS EROS. There is a constant need to monitor the health and safety of the satellites because of high-energy radiation, thermal fluctuations, repeated movement from sun to shadow and back, and space debris, Doucette said.
Radiation leads to natural degradation over time, Doucette explained. “To the extent that we can better understand that across thousands of vital signs, we populate databases of this information over time. That’s the kind of thing that you can use to train an AI algorithm to better understand these subtle patterns that may be indicating certain trends.”
With space getting more crowded as new satellites launch and old debris lingers, Doucette sees an AI opportunity for helping avoid collisions, too.
“We can train algorithms on all the debris out there on orbital rates, and maybe we’re more effective at being able to maneuver around this debris or other vehicles. You don't necessarily turn over the joystick to the algorithm like a self-driving car, but you inform the human to be more efficient and effective as to how humans command the satellite to avoid debris,” Doucette said.
AI could also offer advancements in data integration, Doucette said. Combining remote sensing data from different sensor types can provide even more information than either sensor alone could. For example, Landsat data has been harmonized with similar data provided by the European Sentinel-2 satellites. This ultimately provides more frequent imagery of the Earth, which is helpful for monitoring rapidly changing land conditions.
To take this idea a step further, AI techniques might be able to help integrate data from dissimilar sensors, such as the light energy of Landsat with the radio waves of radar. Doucette compares the potential to how the human brain can blend information from two senses, seeing and hearing, “in an almost seamless way” and put it to use.
Doucette sees the big challenge to this “next frontier” as being the large amount of data and computing power required to train an algorithm.
And the data just keeps coming. The trio of satellites in Landsat Next, for example, planned for launch in late 2030/early 2031, will capture far more detail about features of the Earth’s surface more frequently than current Landsat satellites. Landsat Next would be expected to produce about 20 times more data than its predecessor, Landsat 9.
“As we start moving in that direction of having more data that we have to comb through, I think it's even more important to try to develop these types of models to exploit the data for better managing our world,” Pastick said.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, we talked about AI’s current and upcoming impact on our work at EROS and clarified some of the AI jargon.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, we talked about AI’s current and upcoming impact on our work at EROS and clarified some of the AI jargon.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, EROS Director Pete Doucette discusses AI and its current and upcoming impact on our work at EROS.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, EROS Director Pete Doucette discusses AI and its current and upcoming impact on our work at EROS.
Every pixel has a story. At least that’s how land remote sensing scientist Jo Horton sees it. The new Annual National Land Cover Database (NLCD) was just released in October 2024. NLCD is widely used for land cover and change research in the U.S.
Every pixel has a story. At least that’s how land remote sensing scientist Jo Horton sees it. The new Annual National Land Cover Database (NLCD) was just released in October 2024. NLCD is widely used for land cover and change research in the U.S.
In this episode of Eyes on Earth, we talk about the latest release of the National Land Cover Database (NLCD). More than just a map, NLCD is a stack of maps—a database. It has long been the foundational land cover source for scientists, resource managers, and decision-makers across the United States, and now the next generation of USGS land cover mapping is here.
In this episode of Eyes on Earth, we talk about the latest release of the National Land Cover Database (NLCD). More than just a map, NLCD is a stack of maps—a database. It has long been the foundational land cover source for scientists, resource managers, and decision-makers across the United States, and now the next generation of USGS land cover mapping is here.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, we talked about AI’s current and upcoming impact on our work at EROS and clarified some of the AI jargon.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, we talked about AI’s current and upcoming impact on our work at EROS and clarified some of the AI jargon.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, EROS Director Pete Doucette discusses AI and its current and upcoming impact on our work at EROS.
Eyes on Earth tackles artificial intelligence (AI) in a 2-part episode. AI is quickly becoming a necessary part of geospatial work at EROS, helping us efficiently do science to better manage our world. In Part 1, EROS Director Pete Doucette discusses AI and its current and upcoming impact on our work at EROS.
Every pixel has a story. At least that’s how land remote sensing scientist Jo Horton sees it. The new Annual National Land Cover Database (NLCD) was just released in October 2024. NLCD is widely used for land cover and change research in the U.S.
Every pixel has a story. At least that’s how land remote sensing scientist Jo Horton sees it. The new Annual National Land Cover Database (NLCD) was just released in October 2024. NLCD is widely used for land cover and change research in the U.S.
In this episode of Eyes on Earth, we talk about the latest release of the National Land Cover Database (NLCD). More than just a map, NLCD is a stack of maps—a database. It has long been the foundational land cover source for scientists, resource managers, and decision-makers across the United States, and now the next generation of USGS land cover mapping is here.
In this episode of Eyes on Earth, we talk about the latest release of the National Land Cover Database (NLCD). More than just a map, NLCD is a stack of maps—a database. It has long been the foundational land cover source for scientists, resource managers, and decision-makers across the United States, and now the next generation of USGS land cover mapping is here.
