Cookies help us run our site more efficiently.

By clicking “Accept”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information or to customize your cookie preferences.

The Best Way to Find Out if We Can Cool the Planet

News Feed
Sunday, March 17, 2024

A few years ago, the idea of deliberately blocking the sun to combat climate change was so taboo for scientists. But a lot can change in a short time.As the disastrous effects of climate change mount, Congress has asked federal scientists for a research plan, private money is flowing and rogue start-ups are attempting experiments — all signs that momentum around solar geoengineering is building fast. The most discussed approach involves spraying tiny particles into the stratosphere to reflect sunlight and cool the planet. Other proposals include injecting sea salt into clouds to increase their reflectivity or using giant space parasols to block the sun.It might all sound like dystopian science fiction, but some techno-futurists, like OpenAI’s chief executive, Sam Altman, are already normalizing it: “We’re going to have to do something dramatic with climate like geoengineering as a Band-Aid, as a stop gap,” he said in January at the World Economic Forum in Davos.No one fully understands the risks of these technologies — which could include calamitous disruptions in weather — or how significant the benefits could be. I’m increasingly convinced that we should do more research on solar geoengineering. But such high-stakes science requires extraordinary levels of transparency and accountability to the global public. The alternative is clandestine research controlled by corporations or autocratic regimes, lurching toward deployment without knowing — or knowing and not sharing — the true risks.The potential risks of solar geoengineering are serious. Spraying reflective particles in one place, for example, could significantly change rainfall patterns elsewhere. What’s more, once anyone starts solar geoengineering at a larger scale, suddenly stopping it could lead to “termination shock” — global temperatures rapidly readjusting to where they would have been without geoengineering. With such terrifying points of no return, every accelerating step of research requires global public participation and deliberation.Most research so far has been tentative and contained to computer simulations. But to know what will happen in the real world, we also need outdoor experiments. By launching an instrument-laden balloon into the stratosphere, for example, researchers could release a tiny amount of particles and measure how they interact with the atmosphere, with minimal environmental risk.Subscribe to The Times to read as many articles as you like.

High-stakes geoengineering science requires transparency and accountability to the public.

A few years ago, the idea of deliberately blocking the sun to combat climate change was so taboo for scientists. But a lot can change in a short time.

As the disastrous effects of climate change mount, Congress has asked federal scientists for a research plan, private money is flowing and rogue start-ups are attempting experiments — all signs that momentum around solar geoengineering is building fast. The most discussed approach involves spraying tiny particles into the stratosphere to reflect sunlight and cool the planet. Other proposals include injecting sea salt into clouds to increase their reflectivity or using giant space parasols to block the sun.

It might all sound like dystopian science fiction, but some techno-futurists, like OpenAI’s chief executive, Sam Altman, are already normalizing it: “We’re going to have to do something dramatic with climate like geoengineering as a Band-Aid, as a stop gap,” he said in January at the World Economic Forum in Davos.

No one fully understands the risks of these technologies — which could include calamitous disruptions in weather — or how significant the benefits could be. I’m increasingly convinced that we should do more research on solar geoengineering. But such high-stakes science requires extraordinary levels of transparency and accountability to the global public. The alternative is clandestine research controlled by corporations or autocratic regimes, lurching toward deployment without knowing — or knowing and not sharing — the true risks.

The potential risks of solar geoengineering are serious. Spraying reflective particles in one place, for example, could significantly change rainfall patterns elsewhere. What’s more, once anyone starts solar geoengineering at a larger scale, suddenly stopping it could lead to “termination shock” — global temperatures rapidly readjusting to where they would have been without geoengineering. With such terrifying points of no return, every accelerating step of research requires global public participation and deliberation.

Most research so far has been tentative and contained to computer simulations. But to know what will happen in the real world, we also need outdoor experiments. By launching an instrument-laden balloon into the stratosphere, for example, researchers could release a tiny amount of particles and measure how they interact with the atmosphere, with minimal environmental risk.

Subscribe to The Times to read as many articles as you like.

Read the full story here.
Photos courtesy of

Fostering research, careers, and community in materials science

MICRO internship program expands, brings undergraduate interns from other schools to campus.

Gabrielle Wood, a junior at Howard University majoring in chemical engineering, is on a mission to improve the sustainability and life cycles of natural resources and materials. Her work in the Materials Initiative for Comprehensive Research Opportunity (MICRO) program has given her hands-on experience with many different aspects of research, including MATLAB programming, experimental design, data analysis, figure-making, and scientific writing.Wood is also one of 10 undergraduates from 10 universities around the United States to participate in the first MICRO Summit earlier this year. The internship program, developed by the MIT Department of Materials Science and Engineering (DMSE), first launched in fall 2021. Now in its third year, the program continues to grow, providing even more opportunities for non-MIT undergraduate students — including the MICRO Summit and the program’s expansion to include Northwestern University.“I think one of the most valuable aspects of the MICRO program is the ability to do research long term with an experienced professor in materials science and engineering,” says Wood. “My school has limited opportunities for undergraduate research in sustainable polymers, so the MICRO program allowed me to gain valuable experience in this field, which I would not otherwise have.”Like Wood, Griheydi Garcia, a senior chemistry major at Manhattan College, values the exposure to materials science, especially since she is not able to learn as much about it at her home institution.“I learned a lot about crystallography and defects in materials through the MICRO curriculum, especially through videos,” says Garcia. “The research itself is very valuable, as well, because we get to apply what we’ve learned through the videos in the research we do remotely.”Expanding research opportunitiesFrom the beginning, the MICRO program was designed as a fully remote, rigorous education and mentoring program targeted toward students from underserved backgrounds interested in pursuing graduate school in materials science or related fields. Interns are matched with faculty to work on their specific research interests.Jessica Sandland ’99, PhD ’05, principal lecturer in DMSE and co-founder of MICRO, says that research projects for the interns are designed to be work that they can do remotely, such as developing a machine-learning algorithm or a data analysis approach.“It’s important to note that it’s not just about what the program and faculty are bringing to the student interns,” says Sandland, a member of the MIT Digital Learning Lab, a joint program between MIT Open Learning and the Institute’s academic departments. “The students are doing real research and work, and creating things of real value. It’s very much an exchange.”Cécile Chazot PhD ’22, now an assistant professor of materials science and engineering at Northwestern University, had helped to establish MICRO at MIT from the very beginning. Once at Northwestern, she quickly realized that expanding MICRO to Northwestern would offer even more research opportunities to interns than by relying on MIT alone — leveraging the university’s strong materials science and engineering department, as well as offering resources for biomaterials research through Northwestern’s medical school. The program received funding from 3M and officially launched at Northwestern in fall 2023. Approximately half of the MICRO interns are now in the program with MIT and half are with Northwestern. Wood and Garcia both participate in the program via Northwestern.“By expanding to another school, we’ve been able to have interns work with a much broader range of research projects,” says Chazot. “It has become easier for us to place students with faculty and research that match their interests.”Building communityThe MICRO program received a Higher Education Innovation grant from the Abdul Latif Jameel World Education Lab, part of MIT Open Learning, to develop an in-person summit. In January 2024, interns visited MIT for three days of presentations, workshops, and campus tours — including a tour of the MIT.nano building — as well as various community-building activities.“A big part of MICRO is the community,” says Chazot. “A highlight of the summit was just seeing the students come together.”The summit also included panel discussions that allowed interns to gain insights and advice from graduate students and professionals. The graduate panel discussion included MIT graduate students Sam Figueroa (mechanical engineering), Isabella Caruso (DMSE), and Eliana Feygin (DMSE). The career panel was led by Chazot and included Jatin Patil PhD ’23, head of product at SiTration; Maureen Reitman ’90, ScD ’93, group vice president and principal engineer at Exponent; Lucas Caretta PhD ’19, assistant professor of engineering at Brown University; Raquel D’Oyen ’90, who holds a PhD from Northwestern University and is a senior engineer at Raytheon; and Ashley Kaiser MS ’19, PhD ’21, senior process engineer at 6K.Students also had an opportunity to share their work with each other through research presentations. Their presentations covered a wide range of topics, including: developing a computer program to calculate solubility parameters for polymers used in textile manufacturing; performing a life-cycle analysis of a photonic chip and evaluating its environmental impact in comparison to a standard silicon microchip; and applying machine learning algorithms to scanning transmission electron microscopy images of CrSBr, a two-dimensional magnetic material. “The summit was wonderful and the best academic experience I have had as a first-year college student,” says MICRO intern Gabriella La Cour, who is pursuing a major in chemistry and dual degree biomedical engineering at Spelman College and participates in MICRO through MIT. “I got to meet so many students who were all in grades above me … and I learned a little about how to navigate college as an upperclassman.” “I actually have an extremely close friendship with one of the students, and we keep in touch regularly,” adds La Cour. “Professor Chazot gave valuable advice about applications and recommendation letters that will be useful when I apply to REUs [Research Experiences for Undergraduates] and graduate schools.”Looking to the future, MICRO organizers hope to continue to grow the program’s reach.“We would love to see other schools taking on this model,” says Sandland. “There are a lot of opportunities out there. The more departments, research groups, and mentors that get involved with this program, the more impact it can have.”

‘Simply mind-boggling’: world record temperature jump in Antarctic raises fears of catastrophe

An unprecedented leap of 38.5C in the coldest place on Earth is a harbinger of a disaster for humans and the local ecosystemOn 18 March, 2022, scientists at the Concordia research station on the east Antarctic plateau documented a remarkable event. They recorded the largest jump in temperature ever measured at a meteorological centre on Earth. According to their instruments, the region that day experienced a rise of 38.5C above its seasonal average: a world record.This startling leap – in the coldest place on the planet – left polar researchers struggling for words to describe it. “It is simply mind-boggling,” said Prof Michael Meredith, science leader at the British Antarctic Survey. “In sub-zero temperatures such a massive leap is tolerable but if we had a 40C rise in the UK now that would take temperatures for a spring day to over 50C – and that would be deadly for the population.” Continue reading...

On 18 March, 2022, scientists at the Concordia research station on the east Antarctic plateau documented a remarkable event. They recorded the largest jump in temperature ever measured at a meteorological centre on Earth. According to their instruments, the region that day experienced a rise of 38.5C above its seasonal average: a world record.This startling leap – in the coldest place on the planet – left polar researchers struggling for words to describe it. “It is simply mind-boggling,” said Prof Michael Meredith, science leader at the British Antarctic Survey. “In sub-zero temperatures such a massive leap is tolerable but if we had a 40C rise in the UK now that would take temperatures for a spring day to over 50C – and that would be deadly for the population.”This amazement was shared by glaciologist Prof Martin Siegert, of the University of Exeter. “No one in our community thought that anything like this could ever happen. It is extraordinary and a real concern,” he told the Observer. “We are now having to wrestle with something that is completely unprecedented.”Poleward winds, which previously made few inroads into the atmosphere above Antarctica, are now carrying more and more warm, moist air from lower latitudes – including Australia – deep into the continent, say scientists, and these have been blamed for the dramatic polar “heatwave” that hit Concordia. Exactly why these currents are now able to plunge so deep into the continent’s air space is not yet clear, however.Nor has this huge temperature hike turned out to be an isolated event, scientists have discovered. For the past two years they have been inundated with rising numbers of reports of disturbing meteorological anomalies on the continent. Glaciers bordering the west Antarctic ice-sheet are losing mass to the ocean at an increasing rate, while levels of sea ice, which float on the oceans around the continent, have plunged dramatically, having remained stable for more than a century.These events have raised fears that the Antarctic, once thought to be too cold to experience the early impacts of global warming, is now succumbing dramatically and rapidly to the swelling levels of greenhouse gases that humans continue to pump into the atmosphere.These dangers were highlighted by a team of scientists, led by Will Hobbs of the University of Tasmania, in a paper that was published last week in the Journal of Climate. After examining recent changes in sea ice coverage in Antarctica, the group concluded there had been an “abrupt critical transition” in the continent’s climate that could have repercussions for both local Antarctic ecosystems and the global climate system.“The extreme lows in Antarctic sea ice have led researchers to suggest that a regime shift is under way in the Southern Ocean, and we found multiple lines of evidence that support such a shift to a new sea ice state,” said Hobbs.The dramatic nature of this transformation was emphasised by Meredith. “Antarctic sea ice coverage actually increased slightly in the late 20th and early 21st century. However, in the middle of the last decade it fell off a cliff. It is a harbinger of the new ground with the Antarctic climate system, and that could be very troubling for the region and for the rest of the planet.”The continent is now catching up with the Arctic, where the impacts of global warming have, until now, been the most intense experienced across the planet, added Siegert. “The Arctic is currently warming at four times the rate experienced by the rest of the planet. But the Antarctic has started to catch up, so that it is already warming twice as quickly as the planet overall.”A key reason for the Arctic and Antarctic to be taking disproportionate hits from global warming is because the Earth’s oceans – warmed by fossil-fuel burning – are losing their sea ice at their polar extremities. The dark waters that used to lie below the ice are being exposed and solar radiation is no longer reflected back into space. Instead, it is being absorbed by the sea, further heating the oceans there.“Essentially, it is a vicious circle of warming oceans and melting of sea ice, though the root cause is humanity and its continuing burning of fossil fuels and its production of greenhouse gases,” said Meredith. “This whole business has to be laid at our door.”Ice cover in Antarctica has been eroding at an alarming rate due to global warming caused by burning fossil fuels. Photograph: Anadolu/Getty ImagesAs to the consequences of this meteorological metamorphosis, these could be devastating, researchers warn. If all the ice on Antarctica were to melt, this would raise sea levels around the globe by more than 60 metres. Islands and coastal zones where much of the world’s population now have homes would be inundated.Such an apocalypse is unlikely to occur for some time, however. Antarctica’s ice sheet covers 14m square kilometres (about 5.4m square miles), roughly the area of the United States and Mexico combined, and contains about 30m cubic kilometres (7.2m cubic miles) of ice – about 60% of the world’s fresh water. This vast covering hides a mountain range that is nearly as high as the Alps, so it will take a very long time for that to melt completely, say scientists.Nevertheless, there is now a real danger that some significant sea level rises will occur in the next few decades as the ice sheets and glaciers of west Antarctica continue to shrink. These are being eroded at their bases by warming ocean water and could disintegrate in a few decades. If they disappear entirely, that would raise sea levels by 5m – sufficient to cause damage to coastal populations around the world. How quickly that will happen is difficult to assess. The Intergovernmental Panel on Climate Change has said that sea levels are likely to rise between 0.3m to 1.1m by the end of the century. Many experts now fear this is a dangerous underestimate. In the past, climate change deniers accused scientists of exaggerating the threat of global warming. However, the evidence that is now emerging from Antarctica and other parts of the world makes it very clear that scientists did not exaggerate. Indeed, they very probably underrated by a considerable degree the threat that now faces humanity.“The picture is further confused in Antarctica because, historically, we have had problems getting data,” added Meredith. “We have never had the information about weather and ecosystem, compared with the data we get from the rest of the world, because the continent is so remote and so hostile. Our records are comparatively short and that means that the climate models we have created, although very capable, are based on sparse data. They cannot capture all of the physics, chemistry and biology. They can make predictions that are coherent but they cannot capture the sort of extremes that we’re now beginning to observe.”The woes facing Antarctica are not merely of human concern, however. “We are already seeing serious ecological impacts that threaten to spread through the food chain,” said Prof Kate Hendry, a chemical oceanographer based at the British Antarctic Survey.A critical example is provided by the algae which grow under and around sea ice in west Antarctica. This is starting to disappear, with very serious implications, added Hendry. Algae is eaten by krill, the tiny marine crustaceans that are one of the most abundant animals on Earth and which provide food for predators that include fish, penguins, seals and whales. “If krill starts to disappear in the wake of algae, then all sorts of disruption to the food chain will occur,” said Hendry.The threat posed by the disappearance of krill goes deeper, however. They play a key role in limiting global warming. Algae absorb carbon dioxide. Krill then eat them and excrete it, the faeces sinking to the seabed and staying there. Decreased levels of algae and krill would then mean less carbon from the atmosphere would be deposited on the ocean floor and would instead remain near the sea surface, where it would return to the atmosphere.“They act like a conveyor belt that takes carbon out of the atmosphere and carries it down to the deep ocean floor where it can be locked away. So if we start messing with that system, there could be all sorts of other knock-on effects for our attempts to cope with the impact of global warming,” added Hendry. “It is a scary scenario. Nevertheless that, unfortunately, is what we are now facing.”Another victim of the sudden, catastrophic warming that has gripped the continent is its most famous resident: the emperor penguin. Last year the species, which is found only in Antarctica, suffered a catastrophic breeding failure because the platforms of sea ice on which they are born started to break up long before the young penguins could grow waterproof feathers.“We have never seen emperor penguins fail to breed, at this scale, in a single season,” said Peter Fretwell, of the British Antarctic Survey. “The loss of sea ice in this region during the Antarctic summer made it very unlikely that displaced chicks would survive.”Researchers say that the discovery of the loss of emperor penguins suggests that more than 90% of colonies will be wiped out by the end of the century, if global warming trends continue at their current disastrous rate. “The chicks cannot live on sea ice until they have fledged,” said Meredith. “After that, they can look after themselves. But the sea ice is breaking up before they reach that stage and mass drowning events are now happening. Colonies of penguins are being wiped out. And that’s a tragedy. This is an iconic species, one that is emblematic of Antarctica and the new vulnerability of its ecosystems.”The crisis facing the continent has widespread implications. More than 40 nations are signatories of the Antarctic Treaty’s environmental protocol, which is supposed to shield it from a host of different threats, with habitat degradation being one of the most important. The fact that the continent is now undergoing alarming shifts in its ice covering, eco-systems and climate is a clear sign that this protection is no longer being provided.“The cause of this ecological and meteorological change lies outside the continent,” added Siegert. “It is being caused because the rest of the world is continuing to emit vast amounts carbon dioxide.“Nevertheless, there is a good case for arguing that if countries are knowingly polluting the atmosphere with greenhouse gases, and Antarctica is being affected as a consequence, then the treaty protocol is being breached by its signatories and their behaviour could be challenged on legal and political grounds. It should certainly make for some challenging meetings at the UN in the coming years.”

SpaceX Dragon Spacecraft Docks to Space Station With New Science and Supplies

While the International Space Station (ISS) was traveling more than 262 miles over the South Atlantic Ocean, a SpaceX Dragon cargo spacecraft autonomously docked to station’s...

The SpaceX Dragon cargo spacecraft docks to the International Space Station’s Harmony module at 7:19 a.m. EDT on Saturday, March 23. Credit: NASA TVWhile the International Space Station (ISS) was traveling more than 262 miles over the South Atlantic Ocean, a SpaceX Dragon cargo spacecraft autonomously docked to station’s Harmony module at 7:19 a.m. EDT on March 23, with NASA astronauts Loral O’Hara and Michael Barratt monitoring operations from the station.The Dragon launched on SpaceX’s 30th contracted commercial resupply mission for NASA at 4:55 p.m. EDT, March 21, from Space Launch Complex 40 at Cape Canaveral Space Force Station in Florida. After Dragon spends about one month attached to the space station, the spacecraft will return to Earth with cargo and research.Among the science experiments Dragon is delivering to the space station are: Fully assembled Nanoracks-Killick-1 CubeSat with its Global Navigation Satellite System Reflectometry (GNSS-R) antenna deployed. Nanoracks-Killick-1 measures sea ice using GNSS-R. Potential applications of GNSS-R include providing data for weather and climate models and improving understanding of ocean phenomena such as surface winds and storm surge. Credit: C-CORE and Memorial University.Monitoring Sea Ice Thickness and Wave Height(Nanoracks-Killick-1) is a CubeSat that measures sea ice parameters using Global Navigation Satellite System (GNSS) reflectometry or reflected signals. This monitoring system could contribute to a better understanding of important ocean phenomena and improved weather and climate models.CSIRO Project Lead Marc Elmouttie with the MRS hardware and Astrobee robot ready for final pre-flight testing. Credit: NASANew Sensors for ASTROBEEThe Multi-resolution Scanner (MRS) Payload for the Astrobee (Multi-Resolution Scanning) tests a new set of sensors to support automated 3D sensing, mapping, and situational awareness functions. These systems could support future Gateway and Lunar surface missions by providing automated defect detection, automated and remote maintenance, and autonomous vehicle operations.A capstone student assembles the microscope and fluid breadboard for the Nano Particle Haloing Suspension payload. This payload tests the controlled assembly of nanoparticles in a solution of zirconia and titanium-dioxide-coated silica. Effective demonstration could lead to applications in an enhanced solar cell generation technology known as quantum-dot solar synthesis. Credit: University of LouisvilleImproving Efficiency of Quantum-Dot Solar CellsThe Nano Particle Haloing Suspension payload tests the controlled assembly of nanoparticles in a liquid solution. A process called nanoparticle haloing uses charged nanoparticles to enable precise particle arrangements that improve the efficiency of quantum-dot synthesized solar cells. Conducting these processes in microgravity provides insight into the relationship between shape, charge, concentration, and interaction of particles.Brachypodium and Setaria were grown in the Plant Growth Systems (PGS) and tested under International Space Station environmental conditions using the Veggie units at NASA’s Kennedy Space Center during the APEX-09 Experiment Verification Test. Credit: Pubudu HandakumburaObserving Photosynthesis in SpaceAdvanced Plant Experiment-09 (APEX-09), also known as C4 Photosynthesis in Space, observes carbon dioxide capture and mechanisms in two types of grasses. Researchers hope to learn more about photosynthesis and plant metabolism changes overall in space. Knowledge gained could support development of bioregenerative life support systems on future missions.These are just a few of the hundreds of investigations currently being conducted aboard the orbiting laboratory in the areas of biology and biotechnology, physical sciences, and Earth and space science. Advances in these areas will help keep astronauts healthy during long-duration space travel and demonstrate technologies for future human and robotic exploration beyond low-Earth orbit to the Moon through NASA’s Artemis missions and eventually Mars.

Science Simplified: What Is Artificial Intelligence?

What Is Artificial Intelligence? Artificial intelligence (AI) is the collective term for computer technologies and techniques that help solve complex problems by imitating the brain’s...

Artificial intelligence, particularly through machine learning, is revolutionizing how we solve complex problems in various fields including science, medicine, and technology. Facilities like Argonne National Laboratory are leading these advancements, using AI to predict complex system behaviors, improve material selection, and assist in global challenges like disease and climate change.What Is Artificial Intelligence?Artificial intelligence (AI) is the collective term for computer technologies and techniques that help solve complex problems by imitating the brain’s ability to learn.AI helps computers recognize patterns hidden within a lot of information, solve problems, and adjust to changes in processes as they happen, much faster than humans can.VIDEOIn this Science 101: What is Artificial Intelligence video, Argonne National Laboratory scientists Taylor Childers and Bethany Lusch discuss AI — the computer technologies and techniques that help solve complex problems by imitating the brain’s ability to learn. Researchers use AI to be better and faster at tackling the most difficult problems in science, medicine, and technology, and help drive discovery in those areas. This could range from helping us understand how COVID-19 attacks the human body to finding ways to manage traffic jams. Researchers use AI to be better and faster at tackling the most difficult problems in science, medicine, and technology, and help drive discovery in those areas. This could range from helping us understand how COVID-19 attacks the human body to finding ways to manage traffic jams.Many Department of Energy (DOE) facilities, like Argonne National Laboratory, assist in developing some the most advanced AI technologies available. Today, they are used in areas of study ranging from chemistry to environmental and manufacturing sciences to medicine and the universe.AI is used to help make models of complex systems, like engines or weather, and predict what might happen if certain parts of those systems changed — for example, if a different fuel was used or temperatures increased steadily.But there are many more uses for AI.A key tool in Argonne’s AI toolbox is a type of technique called machine learning that gets smarter or more accurate as it gets more data to learn from. Machine learning is really helpful in identifying specific objects hidden within a bigger, more crowded picture.In a popular example, a machine learning model was trained to recognize the main features of cats and dogs by showing it many images. Later, the model was able to identify cats and dogs from pictures of mixed animals.Similar machine learning models can help scientists identify, for example, one type of galaxy from another when they receive object-packed images from space telescopes.Machine learning is just one of many AI techniques that help us learn more quickly and accurately. They can help choose the right molecule or chemical for a new material and may one day guide new experiments on their own.Argonne has worked with many organizations around the world to become a leader in artificial intelligence use and development, this includes applying AI to:Improve battery life for cars and energy.Build better climate models that can predict wildfires, hurricanes, and other disasters, and help our communities and power companies protect against them.Find those parts of viruses that attack our cells and develop drugs to fight them.Credit: Argonne National LaboratoryWhat is Artificial Intelligence?Analyzing large complex data to perform human tasks at computer speeds.Artificial intelligence (AI) is now a part of our daily lives, helping to simplify basic tasks, such as voice recognition, content recommendations or photo searches based on people or objects they contain. Scientists are using AI in similar ways to advance our understanding of the world around us. It can help them analyze mountains of data faster, and has provided better solutions. Different AI techniques are used in many research areas, from materials science and medicine to climate change and the cosmos.For example, we can train AI to recognize complex patterns by viewing many different examples. Researchers can use this capability to find new and improved materials for things like solar cells or medicine by training AI on all the known materials for that application. Then AI can help researchers zero in on other promising materials that can be fabricated and tested in a laboratory.

When Algorithms Deliver: The AI Revolution in Logistics

A new, data-driven approach could lead to better solutions for tricky optimization problems like global package routing or power grid operation. While Santa Claus may...

A new technique combining machine learning with traditional optimization has been shown to accelerate the solution-finding process of mixed-integer linear programming solvers by up to 70%, enhancing efficiency in logistics and other sectors. Credit: SciTechDaily.comA new, data-driven approach could lead to better solutions for tricky optimization problems like global package routing or power grid operation.While Santa Claus may have a magical sleigh and nine plucky reindeer to help him deliver presents, for companies like FedEx, the optimization problem of efficiently routing holiday packages is so complicated that they often employ specialized software to find a solution.This software, called a mixed-integer linear programming (MILP) solver, splits a massive optimization problem into smaller pieces and uses generic algorithms to try and find the best solution. However, the solver could take hours — or even days — to arrive at a solution. The process is so onerous that a company often must stop the software partway through, accepting a solution that is not ideal but the best that could be generated in a set amount of time.Accelerating Solutions With Machine LearningResearchers from MIT and ETH Zurich used machine learning to speed things up.They identified a key intermediate step in MILP solvers that has so many potential solutions it takes an enormous amount of time to unravel, which slows the entire process. The researchers employed a filtering technique to simplify this step, and then used machine learning to find the optimal solution for a specific type of problem.Their data-driven approach enables a company to use its own data to tailor a general-purpose MILP solver to the problem at hand.This new technique sped up MILP solvers between 30 and 70 percent, without any drop in accuracy. One could use this method to obtain an optimal solution more quickly or, for especially complex problems, a better solution in a tractable amount of time.This approach could be used wherever MILP solvers are employed, such as by ride-hailing services, electric grid operators, vaccination distributors, or any entity faced with a thorny resource-allocation problem.“Sometimes, in a field like optimization, it is very common for folks to think of solutions as either purely machine learning or purely classical. I am a firm believer that we want to get the best of both worlds, and this is a really strong instantiation of that hybrid approach,” says senior author Cathy Wu, the Gilbert W. Winslow Career Development Assistant Professor in Civil and Environmental Engineering (CEE), and a member of a member of the Laboratory for Information and Decision Systems (LIDS) and the Institute for Data, Systems, and Society (IDSS).Wu wrote the paper with co-lead authors Sirui Li, an IDSS graduate student, and Wenbin Ouyang, a CEE graduate student; as well as Max Paulus, a graduate student at ETH Zurich. The research will be presented at the Conference on Neural Information Processing Systems.Tough to SolveMILP problems have an exponential number of potential solutions. For instance, say a traveling salesperson wants to find the shortest path to visit several cities and then return to their city of origin. If there are many cities that could be visited in any order, the number of potential solutions might be greater than the number of atoms in the universe.“These problems are called NP-hard, which means it is very unlikely there is an efficient algorithm to solve them. When the problem is big enough, we can only hope to achieve some suboptimal performance,” Wu explains.An MILP solver employs an array of techniques and practical tricks that can achieve reasonable solutions in a tractable amount of time.A typical solver uses a divide-and-conquer approach, first splitting the space of potential solutions into smaller pieces with a technique called branching. Then, the solver employs a technique called cutting to tighten up these smaller pieces so they can be searched faster.Cutting uses a set of rules that tighten the search space without removing any feasible solutions. These rules are generated by a few dozen algorithms, known as separators, that have been created for different kinds of MILP problems.Wu and her team found that the process of identifying the ideal combination of separator algorithms to use is, in itself, a problem with an exponential number of solutions.“Separator management is a core part of every solver, but this is an underappreciated aspect of the problem space. One of the contributions of this work is identifying the problem of separator management as a machine learning task to begin with,” she says.Shrinking the Solution SpaceShe and her collaborators devised a filtering mechanism that reduces this separator search space from more than 130,000 potential combinations to around 20 options. This filtering mechanism draws on the principle of diminishing marginal returns, which says that the most benefit would come from a small set of algorithms, and adding additional algorithms won’t bring much extra improvement.Then they use a machine-learning model to pick the best combination of algorithms from among the 20 remaining options.This model is trained with a dataset specific to the user’s optimization problem, so it learns to choose algorithms that best suit the user’s particular task. Since a company like FedEx has solved routing problems many times before, using real data gleaned from past experience should lead to better solutions than starting from scratch each time.The model’s iterative learning process, known as contextual bandits, a form of reinforcement learning, involves picking a potential solution, getting feedback on how good it was, and then trying again to find a better solution.This data-driven approach accelerated MILP solvers between 30 and 70 percent without any drop in accuracy. Moreover, the speedup was similar when they applied it to a simpler, open-source solver and a more powerful, commercial solver.In the future, Wu and her collaborators want to apply this approach to even more complex MILP problems, where gathering labeled data to train the model could be especially challenging. Perhaps they can train the model on a smaller dataset and then tweak it to tackle a much larger optimization problem, she says. The researchers are also interested in interpreting the learned model to better understand the effectiveness of different separator algorithms.Reference: “Learning to Configure Separators in Branch-and-Cut” by Sirui Li, Wenbin Ouyang, Max B. Paulus, Cathy Wu, 8 November 2023, Mathematics > Optimization and Control.arXiv:2311.05650This research is supported, in part, by Mathworks, the National Science Foundation (NSF), the MIT Amazon Science Hub, and MIT’s Research Support Committee.

Suggested Viewing

Join us to forge
a sustainable future

Our team is always growing.
Become a partner, volunteer, sponsor, or intern today.
Let us know how you would like to get involved!

CONTACT US

sign up for our mailing list to stay informed on the latest films and environmental headlines.

Subscribers receive a free day pass for streaming Cinema Verde.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.