From University of California-Berkeley (US) : “A machine learning breakthrough uses satellite images to improve lives”

From University of California-Berkeley (US)

July 20, 2021
Edward Lempinen

Deep streams of data from Earth-imaging satellites arrive in databases every day but advanced technology and expertise are required to access and analyze the data. Now a new system, developed in research based at the University of California-Berkeley, uses machine learning to drive low-cost, easy-to-use technology that one person could run on a laptop, without advanced training, to address their local problems. (Photo by NASA via Pxfuel.)

More than 700 imaging satellites are orbiting the earth. Every day they beam vast oceans of information-including data that reflects climate change; health; and poverty — to databases on the ground. There’s just one problem: While the geospatial data could help researchers and policymakers address critical challenges only those with considerable wealth and expertise can access it.

Now a team based at University of California-Berkeley (US) has devised a machine learning system to tap the problem-solving potential of satellite imaging using low-cost easy-to-use technology that could bring access and analytical power to researchers and governments worldwide. The study was published July 20, 2021 in the journal Nature Communications.

“Satellite images contain an incredible amount of data about the world, but the trick is how to translate the data into usable insights without having a human comb through every single image,” said co-author Esther Rolf, a final-year Ph.D. student in computer science. “We designed our system for accessibility, so that one person should be able to run it on a laptop, without specialized training, to address their local problems.”

“We’re entering a regime in which our actions are having truly global impact,” said co-author Solomon Hsiang, director of the Global Policy Lab at the Goldman School of Public Policy. “Things are moving faster than they’ve ever moved in the past. We’re changing resource allocations faster than ever. We’re transforming the planet. That requires a more responsive management system that is able to see these things happen, so that we can respond in a timely, effective way.”

The project was a collaboration between the Global Policy Lab, which Hsiang directs, and Benjamin Recht’s research team in the department of Electrical Engineering and Computer Sciences. Other co-authors are Berkeley Ph.D. graduates Tamma Carleton, now at University of California-Santa Barbara (US); Jonathan Proctor, now at Harvard University (US)’s Center for the Environment and Data Science Initiative; Ian Bolliger, now at the Rhodium Group; and Vaishaal Shankar, now at Amazon; and Berkeley Ph.D. student Miyabi Ishihara.

All of them were at University of California-Berkeley (US) when the project began. Their collaboration has been remarkable for bringing together disciplines that often look at the world in different ways and speak different languages: computer science, environmental and climate science, statistics, economics and public policy.

But they have been guided by a common interest in creating an open access tool that democratizes the power of technology, making it usable even by communities and countries that lack resources and advanced technical skill. “It’s like Ford’s Model T, but with machine learning and satellites,” Hsiang said. “It’s cheap enough that everyone can now access this new technology.”

“MOSAIKS”: Improving lives, protecting the planet

The system that emerged from the Berkeley-based research is called “MOSAIKS”, short for Multi-Task Observation using Satellite Imagery & Kitchen Sinks. It ultimately could have the power to analyze hundreds of variables drawn from satellite data — from soil and water conditions to housing, health and poverty — at a global scale.

In the Indian state of Andhra Pradesh, a satellite image shows hundreds of green aquaculture ponds where local farmers grow fish and shrimp. Geospatial imaging holds enormous potential for developing nations to address challenges related to agriculture, poverty, health and human migration, scholars at University of California-Berkeley (US) say. But until now, the technology and expertise needed to efficiently access and analyze satellite data usually has been limited to developed countries. (NASA Earth Observatory (US) images by Joshua Stevens, using Landsat data from the U.S. Geological Survey.)

The research paper details how MOSAIKS was able to replicate with reasonable accuracy reports prepared at great cost by the U.S. Census Bureau. It also has enormous potential in addressing development challenges in low-income countries and to help scientists and policymakers understand big-picture environmental change.

“Climate change is diffuse and difficult to see at any one location, but when you step back and look at the broad scale, you really see what is going on around the planet,” said Hsiang, who also serves as co-director of the multi-institution Climate Impact Lab.

For example, he said, the satellite data could give researchers deep new insights into expansive rangeland areas such as the Great Plains in the U.S. and the Sahel in Africa, or into areas such as Greenland or Antarctica that may be shedding icebergs as temperatures rise.

“These areas are so large, and to have people sitting there and looking at pictures and counting icebergs is really inefficient,” Hsiang explained. But with MOSAIKS, he said, “you could automate that and track whether these glaciers are actually disintegrating faster, or whether this has been happening all along.”

For a government in the developing world, the technology could help guide even routine decisions, such as where to build roads.

“A government wants to build roads where the most people are and the most economic activity is,” Hsiang said. “You might want to know which community is underserved, or the condition of existing infrastructure in a community. But often it’s very difficult to get that information.”

The challenge: Organizing trillions of bytes of raw satellite data

The growing fleet of imaging satellites beam data back to Earth 24/7 — some 80 terabytes every day according to the research-a number certain to grow in coming years.

But often, imaging satellites are built to capture information on narrow topics — supplies of fresh water, for example, or the condition of agricultural soils. And the data doesn’t arrive as neat, orderly images, like snapshots from a photo shop. It’s raw data, a mass of binary information. Researchers who access the data have to know what they’re looking for.

Merely storing so many terabytes of data requires a huge investment. Distilling the layers of data embedded in the images requires additional computing power and advanced human expertise to tease out strands of information that are coherent and useful to other researchers, policymakers or funding agencies.

Inevitably, exploiting satellite images is largely limited to scholars or agencies in wealthy nations, Rolf and Hsiang said.

“If you’re an elite professor, you can get someone to build your satellite for you,” said Hsiang. “But there’s no way that a conservation agency in Kenya is going to be able to access the technology and the experts to do this work.

“We wanted to find a way to empower them. We decided to come up with a Swiss Army Knife — a practical tool that everyone can access.”

Like Google for satellite imagery, sort of

Especially in low-income countries, one dimension of poverty is a poverty of data. But even communities in the U.S. and other developed countries usually don’t have ready access to geospatial data in a convenient, usable format for addressing local challenges.

Machine learning opens the door to solutions.

The illustrations show how the MOSAIKS machine learning system developed at University of California-Berkeley (US) predicts, in fine detail, forest cover (above, in green) and population (below). (Image courtesy of Esther Rolf, Jonathan Proctor, Tamma Carleton, Ian Bolliger, Miyabi Ishihara, Vaishaal Shankar, Benjamin Recht and Solomon Hsiang)

In a general sense, machine learning refers to computer systems that use algorithms and statistical modeling to learn on their own, without step-by-step human intervention. What the new research describes is a system that can assemble data delivered by many satellites and organize it in ways that are accessible and useful.

There are precedents for such systems: Google Earth Engine and Microsoft’s Planetary Computer are both platforms for accessing and analyzing global geospatial data, with a focus on conservation. But, Rolf said, even with these technologies, considerable expertise is often required to convert the data into new insights.

The goal of MOSAIKS is not to develop more complex machine learning systems, Rolf said. Rather, its innovation is in making satellite data widely useable for addressing global challenges. The team did this by making the algorithms radically simpler and more efficient.

MOSAIKS starts with learning to recognize minuscule patterns in the images — Hsiang compares it to a game of Scrabble, in which the algorithm learns to recognize each letter. In this case, however, the tiles are minuscule pieces of satellite image, 3 pixels by 3 pixels.

But MOSAIKS doesn’t conclude “this is a tree” or “this is pavement.” Instead, it recognizes patterns and groups them together, said Proctor. It learns to recognize similar patterns in different parts of the world.

When thousands of terabytes from hundreds of sources are analyzed and organized, researchers can choose a village or a country or a region and draw out organized data that can touch on themes as varied as soil moisture, health conditions, human migration and home values.

In a sense Hsiang said “MOSAIKS” could do for satellite databases what Google in the early days did for the Internet: map the data; make it accessible and user-friendly at low cost; and perhaps make it searchable. But Rolf, a machine learning scholar based in the Berkeley Electrical Engineering and Computer Sciences department, said the Google comparison goes only so far.

MOSAIKS “is about translating an unwieldy amount of data into usable information,” she explained. “Maybe a better analogy would be that the system takes very dense information — say, a very large article — and produces a summary.”

Creating a living atlas of global data

Both Hsiang and Rolf see the potential for MOSAIKS to evolve in powerful and elegant directions.

Hsiang imagines the data being collected into computer-based, continually evolving atlases. Turn to any given “page,” and a user could access broad, deep data about conditions in a country or a region.

Rolf envisions a system that can take the stream of data from humanity’s fleet of imaging satellites and remote sensors and transform it into a flowing, real-time portrait of Earth and its inhabitants, continually in a state of change. We could see the past and the present, and so discern emerging challenges and address them.

“We’ve sent so much stuff to space,” Hsiang says. “It’s an amazing achievement. But we can get a lot more bang for our buck for all of this data that we’re already pulling down. Let’s let the world use it in a useful way. Let’s use it for good.”

See the full article here .


Please help promote STEM in your local schools.

Stem Education Coalition

The University of California-Berkeley US) is a public land-grant research university in Berkeley, California. Established in 1868 as the state’s first land-grant university, it was the first campus of the University of California (US) system and a founding member of the Association of American Universities (US). Its 14 colleges and schools offer over 350 degree programs and enroll some 31,000 undergraduate and 12,000 graduate students. Berkeley is ranked among the world’s top universities by major educational publications.

Berkeley hosts many leading research institutes, including the Mathematical Sciences Research Institute and the Space Sciences Laboratory. It founded and maintains close relationships with three national laboratories at DOE’s Lawrence Berkeley National Laboratory(US), DOE’s Lawrence Livermore National Laboratory(US) and DOE’s Los Alamos National Lab(US), and has played a prominent role in many scientific advances, from the Manhattan Project and the discovery of 16 chemical elements to breakthroughs in computer science and genomics. Berkeley is also known for student activism and the Free Speech Movement of the 1960s.

Berkeley alumni and faculty count among their ranks 110 Nobel laureates (34 alumni), 25 Turing Award winners (11 alumni), 14 Fields Medalists, 28 Wolf Prize winners, 103 MacArthur “Genius Grant” recipients, 30 Pulitzer Prize winners, and 19 Academy Award winners. The university has produced seven heads of state or government; five chief justices, including Chief Justice of the United States Earl Warren; 21 cabinet-level officials; 11 governors; and 25 living billionaires. It is also a leading producer of Fulbright Scholars, MacArthur Fellows, and Marshall Scholars. Berkeley alumni, widely recognized for their entrepreneurship, have founded many notable companies.

Berkeley’s athletic teams compete in Division I of the NCAA, primarily in the Pac-12 Conference, and are collectively known as the California Golden Bears. The university’s teams have won 107 national championships, and its students and alumni have won 207 Olympic medals.

Made possible by President Lincoln’s signing of the Morrill Act in 1862, the University of California was founded in 1868 as the state’s first land-grant university by inheriting certain assets and objectives of the private College of California and the public Agricultural, Mining, and Mechanical Arts College. Although this process is often incorrectly mistaken for a merger, the Organic Act created a “completely new institution” and did not actually merge the two precursor entities into the new university. The Organic Act states that the “University shall have for its design, to provide instruction and thorough and complete education in all departments of science, literature and art, industrial and professional pursuits, and general education, and also special courses of instruction in preparation for the professions”.

Ten faculty members and 40 students made up the fledgling university when it opened in Oakland in 1869. Frederick H. Billings, a trustee of the College of California, suggested that a new campus site north of Oakland be named in honor of Anglo-Irish philosopher George Berkeley. The university began admitting women the following year. In 1870, Henry Durant, founder of the College of California, became its first president. With the completion of North and South Halls in 1873, the university relocated to its Berkeley location with 167 male and 22 female students.

Beginning in 1891, Phoebe Apperson Hearst made several large gifts to Berkeley, funding a number of programs and new buildings and sponsoring, in 1898, an international competition in Antwerp, Belgium, where French architect Émile Bénard submitted the winning design for a campus master plan.

20th century

In 1905, the University Farm was established near Sacramento, ultimately becoming the University of California, Davis. In 1919, Los Angeles State Normal School became the southern branch of the University, which ultimately became the University of California, Los Angeles. By 1920s, the number of campus buildings had grown substantially and included twenty structures designed by architect John Galen Howard.

In 1917, one of the nation’s first ROTC programs was established at Berkeley and its School of Military Aeronautics began training pilots, including Gen. Jimmy Doolittle. Berkeley ROTC alumni include former Secretary of Defense Robert McNamara and Army Chief of Staff Frederick C. Weyand as well as 16 other generals. In 1926, future fleet admiral Chester W. Nimitz established the first Naval ROTC unit at Berkeley.

In the 1930s, Ernest Lawrence helped establish the Radiation Laboratory (now DOE’s Lawrence Berkeley National Laboratory (US)) and invented the cyclotron, which won him the Nobel physics prize in 1939. Using the cyclotron, Berkeley professors and Berkeley Lab researchers went on to discover 16 chemical elements—more than any other university in the world. In particular, during World War II and following Glenn Seaborg’s then-secret discovery of plutonium, Ernest Orlando Lawrence’s Radiation Laboratory began to contract with the U.S. Army to develop the atomic bomb. Physics professor J. Robert Oppenheimer was named scientific head of the Manhattan Project in 1942. Along with the Lawrence Berkeley National Laboratory, Berkeley founded and was then a partner in managing two other labs, Los Alamos National Laboratory (1943) and Lawrence Livermore National Laboratory (1952).

By 1942, the American Council on Education ranked Berkeley second only to Harvard University (US) in the number of distinguished departments.

In 1952, the University of California reorganized itself into a system of semi-autonomous campuses, with each campus given its own chancellor, and Clark Kerr became Berkeley’s first Chancellor, while Sproul remained in place as the President of the University of California.

Berkeley gained a worldwide reputation for political activism in the 1960s. In 1964, the Free Speech Movement organized student resistance to the university’s restrictions on political activities on campus—most conspicuously, student activities related to the Civil Rights Movement. The arrest in Sproul Plaza of Jack Weinberg, a recent Berkeley alumnus and chair of Campus CORE, in October 1964, prompted a series of student-led acts of formal remonstrance and civil disobedience that ultimately gave rise to the Free Speech Movement, which movement would prevail and serve as precedent for student opposition to America’s involvement in the Vietnam War.

In 1982, the Mathematical Sciences Research Institute (MSRI) was established on campus with support from the National Science Foundation and at the request of three Berkeley mathematicians — Shiing-Shen Chern, Calvin Moore and Isadore M. Singer. The institute is now widely regarded as a leading center for collaborative mathematical research, drawing thousands of visiting researchers from around the world each year.

21st century

In the current century, Berkeley has become less politically active and more focused on entrepreneurship and fundraising, especially for STEM disciplines.

Modern Berkeley students are less politically radical, with a greater percentage of moderates and conservatives than in the 1960s and 70s. Democrats outnumber Republicans on the faculty by a ratio of 9:1. On the whole, Democrats outnumber Republicans on American university campuses by a ratio of 10:1.

In 2007, the Energy Biosciences Institute was established with funding from BP and Stanley Hall, a research facility and headquarters for the California Institute for Quantitative Biosciences, opened. The next few years saw the dedication of the Center for Biomedical and Health Sciences, funded by a lead gift from billionaire Li Ka-shing; the opening of Sutardja Dai Hall, home of the Center for Information Technology Research in the Interest of Society; and the unveiling of Blum Hall, housing the Blum Center for Developing Economies. Supported by a grant from alumnus James Simons, the Simons Institute for the Theory of Computing was established in 2012. In 2014, Berkeley and its sister campus, Univerity of California-San Fransisco (US), established the Innovative Genomics Institute, and, in 2020, an anonymous donor pledged $252 million to help fund a new center for computing and data science.

Since 2000, Berkeley alumni and faculty have received 40 Nobel Prizes, behind only Harvard and Massachusetts Institute of Technology (US) among US universities; five Turing Awards, behind only MIT and Stanford; and five Fields Medals, second only to Princeton University (US). According to PitchBook, Berkeley ranks second, just behind Stanford University, in producing VC-backed entrepreneurs.

UC Berkeley Seal