Researchers harness 2D magnetic materials for energy-efficient computing

Experimental computer memories and processors built from magnetic materials use far less energy than traditional silicon-based devices. Two-dimensional magnetic materials, composed of layers that are only a few atoms thick, have incredible properties that could allow magnetic-based devices to achieve unprecedented speed, efficiency, and scalability.

While many hurdles must be overcome until these so-called van der Waals magnetic materials can be integrated into functioning computers, MIT researchers took an important step in this direction by demonstrating precise control of a van der Waals magnet at room temperature.

This is key, since magnets composed of atomically thin van der Waals materials can typically only be controlled at extremely cold temperatures, making them difficult to deploy outside a laboratory.

The researchers used pulses of electrical current to switch the direction of the device’s magnetization at room temperature. Magnetic switching can be used in computation, the same way a transistor switches between open and closed to represent 0s and 1s in binary code, or in computer memory, where switching enables data storage.

The team fired bursts of electrons at a magnet made of a new material that can sustain its magnetism at higher temperatures. The experiment leveraged a fundamental property of electrons known as spin, which makes the electrons behave like tiny magnets. By manipulating the spin of electrons that strike the device, the researchers can switch its magnetization.

“The heterostructure device we have developed requires an order of magnitude lower electrical current to switch the van der Waals magnet, compared to that required for bulk magnetic devices,” says Deblina Sarkar, the AT&T Career Development Assistant Professor in the MIT Media Lab and Center for Neurobiological Engineering, head of the Nano-Cybernetic Biotrek Lab, and the senior author of a paper on this technique. “Our device is also more energy efficient than other van der Waals magnets that are unable to switch at room temperature.”

In the future, such a magnet could be used to build faster computers that consume less electricity. It could also enable magnetic computer memories that are nonvolatile, which means they don’t leak information when powered off, or processors that make complex AI algorithms more energy-efficient.

“There is a lot of inertia around trying to improve materials that worked well in the past. But we have shown that if you make radical changes, starting by rethinking the materials you are using, you can potentially get much better solutions,” says Shivam Kajale, a graduate student in Sarkar’s lab and co-lead author of the paper.

Kajale and Sarkar are joined on the paper by co-lead author Thanh Nguyen, a graduate student in the Department of Nuclear Science and Engineering (NSE); Corson Chao, a graduate student in the Department of Materials Science and Engineering (DSME); David Bono, a DSME research scientist; Artittaya Boonkird, an NSE graduate student; and Mingda Li, associate professor of nuclear science and engineering. The research appears this week in Nature Communications.

An atomically thin advantage

Methods to fabricate tiny computer chips in a clean room from bulk materials like silicon can hamper devices. For instance, the layers of material may be barely 1 nanometer thick, so minuscule rough spots on the surface can be severe enough to degrade performance.

By contrast, van der Waals magnetic materials are intrinsically layered and structured in such a way that the surface remains perfectly smooth, even as researchers peel off layers to make thinner devices. In addition, atoms in one layer won’t leak into other layers, enabling the materials to retain their unique properties when stacked in devices.

“In terms of scaling and making these magnetic devices competitive for commercial applications, van der Waals materials are the way to go,” Kajale says.

But there’s a catch. This new class of magnetic materials have typically only been operated at temperatures below 60 kelvins (-351 degrees Fahrenheit). To build a magnetic computer processor or memory, researchers need to use electrical current to operate the magnet at room temperature.

To achieve this, the team focused on an emerging material called iron gallium telluride. This atomically thin material has all the properties needed for effective room temperature magnetism and doesn’t contain rare earth elements, which are undesirable because extracting them is especially destructive to the environment.

Nguyen carefully grew bulk crystals of this 2D material using a special technique. Then, Kajale fabricated a two-layer magnetic device using nanoscale flakes of iron gallium telluride underneath a six-nanometer layer of platinum.

Tiny device in hand, they used an intrinsic property of electrons known as spin to switch its magnetization at room temperature.

Electron ping-pong

While electrons don’t technically “spin” like a top, they do possess the same kind of angular momentum. That spin has a direction, either up or down. The researchers can leverage a property known as spin-orbit coupling to control the spins of electrons they fire at the magnet.

The same way momentum is transferred when one ball hits another, electrons will transfer their “spin momentum” to the 2D magnetic material when they strike it. Depending on the direction of their spins, that momentum transfer can reverse the magnetization.

In a sense, this transfer rotates the magnetization from up to down (or vice-versa), so it is called a “torque,” as in spin-orbit torque switching. Applying a negative electric pulse causes the magnetization to go downward, while a positive pulse causes it to go upward.

The researchers can do this switching at room temperature for two reasons: the special properties of iron gallium telluride and the fact that their technique uses small amounts of electrical current. Pumping too much current into the device would cause it to overheat and demagnetize.

The team faced many challenges over the two years it took to achieve this milestone, Kajale says. Finding the right magnetic material was only half the battle. Since iron gallium telluride oxidizes quickly, fabrication must be done inside a glovebox filled with nitrogen.

“The device is only exposed to air for 10 or 15 seconds, but even after that I have to do a step where I polish it to remove any oxide,” he says.

Now that they have demonstrated room-temperature switching and greater energy efficiency, the researchers plan to keep pushing the performance of magnetic van der Waals materials.

“Our next milestone is to achieve switching without the need for any external magnetic fields. Our aim is to enhance our technology and scale up to bring the versatility of van der Waals magnet to commercial applications,” Sarkar says.

This work was carried out, in part, using the facilities at MIT.Nano and the Harvard University Center for Nanoscale Systems.

MLK Celebration Gala pays tribute to Martin Luther King Jr. and his writings on “the goal of true education”

MLK Celebration Gala pays tribute to Martin Luther King Jr. and his writings on “the goal of true education”

After a week of festivities around campus, members of the MIT community gathered Saturday evening in the Boston Marriott Kendall Square ballroom to celebrate the life and legacy of Martin Luther King Jr. Marking 50 years of this annual celebration at MIT, the gala event’s program was loosely organized around a line in King’s essay, “The Purpose of Education,” which he penned as an undergraduate at Morehouse College:

“We must remember that intelligence is not enough,” King wrote. “Intelligence plus character — that is the goal of true education.”

Senior Myles Noel was the master of ceremonies for the evening and welcomed one and all. Minister DiOnetta Jones Crayton, former director of the Office of Minority Education and associate dean of minority education, delivered the invocation, exhorting the audience to embrace “the fiery urgency of now.” Next, MIT President Sally Kornbluth shared her remarks.

She acknowledged that at many institutions, diversity and inclusion efforts are eroding. Kornbluth reiterated her commitment to these efforts, saying, “I want to be clear about how important I believe it is to keep such efforts strong — and to make them the best they can be. The truth is, by any measure, MIT has never been more diverse, and it has never been more excellent. And we intend to keep it that way.”

Kornbluth also recognized the late Paul Parravano, co-director of MIT’s Office of Government and Community Relations, who was a staff member at MIT for 33 years as well as the longest-serving member on the MLK Celebration Committee. Parravano’s “long and distinguished devotion to the values and goals of Dr. Martin Luther King, Jr. inspires us all,” Kornbluth said, presenting his family with the 50th Anniversary Lifetime Achievement Award. 

Next, students and staff shared personal reflections. Zina Queen, office manager in the Department of Political Science, noted that her family has been a part of the MIT community for generations. Her grandmother, Rita, her mother, Wanda, and her daughter have all worked or are currently working at the Institute. Queen pointed out that her family epitomizes another of King’s oft-repeated quotes, “Every man is an heir to a legacy of dignity and worth.”

Senior Tamea Cobb noted that MIT graduates have a particular power in the world that they must use strategically and with intention. “Education and service go hand and hand,” she said, adding that she intends “every one of my technical abilities will be used to pursue a career that is fulfilling, expansive, impactful, and good.”

Graduate student Austin K. Cole ’24 addressed the Israel-Hamas conflict and the MIT administration. As he spoke, some attendees left their seats to stand with Cole at the podium. Cole closed his remarks with a plea to resist state and structural violence, and instead focus on relationship and mutuality.

After dinner, incoming vice president for equity and inclusion Karl Reid ’84, SM ’85 honored Adjunct Professor Emeritus Clarence Williams for his distinguished service to the Institute. Williams was an assistant to three MIT presidents, served as director of the Office of Minority Education, taught in the Department of Urban Planning, initiated the MIT Black History Project, and mentored hundreds of students. Reid was one of those students, and he shared a few of his mentor’s oft repeated phrases:

“Do the work and let the talking take care of itself.”

“Bad ideas kill themselves; great ideas flourish.”

In closing, Reid exhorted the audience to create more leaders who, like Williams, embody excellence and mutual respect for others.

The keynote address was given by civil rights activist Janet Moses, a member of the Student Nonviolent Coordinating Committee (SNCC) in the 1960s; a physician who worked for a time as a pediatrician at MIT Health; a longtime resident of Cambridge, Massachusetts; and a co-founder, with her husband, Robert Moses, of the Algebra Project, a pioneering program grounded in the belief “that in the 21st century every child has a civil right to secure math literacy — the ability to read, write, and reason with the symbol systems of mathematics.”

A striking image of a huge new building planned for New York City appeared on the screen behind Moses during her address. It was a rendering of a new jail being built at an estimated cost of $3 billion. Against this background, she described the trajectory of the “carceral state,” which began in 1771 with the Mansfield Judgement in England. At the time, “not even South Africa had a set of race laws as detailed as those in the U.S.,” Moses observed.

Today, the carceral state uses all levels of government to maintain a racial caste system that is deeply entrenched, Moses argued, drawing a connection between the purported need for a new prison complex and a statistic that Black people in New York state are three times more likely than whites to be convicted for a crime.

She referenced a McKinsey study that it will take Black people over three centuries to achieve a quality of life on parity with whites. Despite the enormity of this challenge, Moses encouraged the audience to “rock the boat and churn the waters of the status quo.” She also pointed out that “there is joy in the struggle.”

Symbols of joy were also on display at the Gala in the forms of original visual art and poetry, and a quilt whose squares were contributed by MIT staff, students, and alumni, hailing from across the Institute.

Quilts are a physical manifestation of the legacy of the enslaved in America and their descendants — the ability to take scraps and leftovers to create something both practical and beautiful. The 50th anniversary quilt also incorporated a line from King’s highly influential “I Have a Dream Speech”:

“One day, all God’s children will have the riches of freedom and the security of justice.”

Nourishing the mind, hand, and stomach

Nourishing the mind, hand, and stomach

As early as middle school, Branden Spitzer loved to watch cooking shows and experiment with recipes in his family’s kitchen. It was a clear harbinger of his interest in materials science, he says now. Once he discovered that he could delight others with a perfectly executed pie, he began to see the many ways that his passion for baking might branch into other areas requiring technical acuity.

“We have this deep connection to food, the things that we wear, the products around us that we experience or work with every day,” says the MIT senior. “I hope we can make those things even better using science and engineering.”

Spitzer is a materials science and engineering major and has rounded out his education by cross registering for food science classes at Harvard University. He has pursued a variety of research opportunities related to food and sustainability, from extending the shelf-life of produce to developing lab-grown meat.

Spitzer also sees food as a means of social nourishment. He enjoys exploring restaurants and having dinners with friends, and takes special pleasure in planning and putting together meals. “I love making pies and cooking because you can share something with people that they think is really tasty,” he says. “And by eating the food they can understand all the thought and everything that went into it. I want the work or research I go on to do to have that same sort of tangible impact.”

Sampling a huge menu

Upon beginning his first year at MIT, Spitzer was overwhelmed by the seemingly endless amount of activities the Institute had to offer. He says the busy student culture was one of the things that attracted him to MIT, yet once he was face-to-face with it all, he didn’t know where to begin. He recalls one of his first-year advisors instructing him to “ride the wave,” and he took this to heart. Open to trying anything, Spitzer set forth on several academic and extracurricular journeys that would lead him in completely different directions through his four years.

He pursued research projects centered on food and sustainability. In one of his first research positions, Spitzer worked for Mori, a Cambridge-based startup that makes a silk-based coating that slows the spoiling of fruits and vegetables. His longest-running research project, in Professor Markus Buehler’s Laboratory for Atomistic and Molecular Mechanics, involves working with mycelium, the root systems of mushrooms, to improve and alter the growth of the material for use in 3D printing. He spent a summer interning for a company in South Africa that is working on a lab-grown meat product, and currently he is interning for Faerm, a plant-based cheese company in Copenhagen, Denmark. He hopes to continue this in this direction after graduation, either at a startup or in graduate school studying materials science or biological engineering.

Spitzer also strives to make a positive impact on his local community at MIT through his work. He participated in activities ranging from physical education to the arts, and everything in between. He joined the student organization MCG, the MIT Consulting Group, solving real-world business problems for clients. Spitzer is also a member of the Phi Delta Theta fraternity, where he served as vice president for three semesters and introduced an initiative to prioritize inclusivity and mental health awareness. And, he joined MIT’s lighting design group, which he says exposed him to new entirely new communities of artists and engineers.  

Spitzer has been fond of traveling since he was a child. He recalls taking trips with his family often, visiting historical and global landmarks. In the past four years he has embarked on multiple study abroad and work experiences through MISTI and is enthusiastic about the unexpected places his internships have taken him. He has spent time in the U.K., Brazil, and South Africa, and will be studying in Denmark this semester.

In Brazil, Spitzer helped to develop and teach a materials science program and class. He says it was exciting to share the subjects of polymers, recycling, and sustainability with students in a different part of the world. In South Africa, Spitzer interned for the Mzansi Meat Co. (now Newform Foods), which he came across by surprise after searching for companies that were making cultured meat products.

Pirates at MIT

Spurred by MIT’s physical education requirements, Spitzer has found a passion for several sports activities. Sailing, for example, has become one of his favorite hobbies. “It’s super cool that we have a chance to do these crazy things,” he says when referring to his time spent taking out sailboats to practice for his sailing class on the Charles River.

Sailing is one of four physical education classes needed to obtain the MIT Pirate Certificate, an incentive that encourages participation in MIT’s P.E. offerings. Spitzer pursued this achievement, enrolling in archery, rifle, and fencing classes over several semesters. The diverse course selection allowed for unexpected discoveries. “I was surprised and blown away by how much the rifle practice was an exercise in thought, focus, and meditation,” he says. “It was very different than I expected, in a very pleasant way.”

Ice skating is another discovery Spitzer made through his four required gym classes. He has taken many more classes by now though since they are “super fun.” Beginning as a nervous newcomer with no experience, Spitzer now takes an intermediate skating class where he develops his skills in turns and speed skating.

Spitzer also enjoys recreational cycling and indoor rock climbing in his spare time, as well as yoga and dancing. He has taken multiple dance classes in his time at MIT and has been a member of the organization MIT DanceTroupe for four years.

Whether in the kitchen, lab, or gym, Spitzer has found a robust community in all corners of the MIT campus and beyond. Rather than choosing one area of focus, Spitzer states the most integral aspect of his student experience at MIT was getting a taste for everything: “You just try things out here. You learn the things you love or the things you hate, and get to do something really cool along the way.”

MIT engineers 3D print the electromagnets at the heart of many electronics

MIT engineers 3D print the electromagnets at the heart of many electronics

Imagine being able to build an entire dialysis machine using nothing more than a 3D printer.

This could not only reduce costs and eliminate manufacturing waste, but since this machine could be produced outside a factory, people with limited resources or those who live in remote areas may be able to access this medical device more easily.

While multiple hurdles must be overcome to develop electronic devices that are entirely 3D printed, a team at MIT has taken an important step in this direction by demonstrating fully 3D-printed, three-dimensional solenoids.

Solenoids, electromagnets formed by a coil of wire wrapped around a magnetic core, are a fundamental building block of many electronics, from dialysis machines and respirators to washing machines and dishwashers.

The researchers modified a multimaterial 3D printer so it could print compact, magnetic-cored solenoids in one step. This eliminates defects that might be introduced during post-assembly processes.

This customized printer, which could utilize higher-performing materials than typical commercial printers, enabled the researchers to produce solenoids that could withstand twice as much electric current and generate a magnetic field that was three times larger than other 3D-printed devices.

In addition to making electronics cheaper on Earth, this printing hardware could be particularly useful in space exploration. For example, instead of shipping replacement electronic parts to a base on Mars, which could take years and cost millions of dollars, one could send a signal containing files for the 3D printer, says Luis Fernando Velásquez-García, a principal research scientist in MIT’s Microsystems Technology Laboratories (MTL).

“There is no reason to make capable hardware in only a few centers of manufacturing when the need is global. Instead of trying to ship hardware all over the world, can we empower people in distant places to make it themselves? Additive manufacturing can play a tremendous role in terms of democratizing these technologies,” adds Velásquez-García, the senior author of a new paper on the 3D printed solenoids that appears in the journal Virtual and Physical Prototyping.

He is joined on the paper by lead author Jorge Cañada, an electrical engineering and computer science graduate student; and Hyeonseok Kim, a mechanical engineering graduate student.

Additive advantages

A solenoid generates a magnetic field when an electrical current is passed through it. When someone rings a doorbell, for instance, electric current flows through a solenoid, which generates a magnetic field that moves an iron rod so it strikes a chime.

Integrating solenoids onto electrical circuits manufactured in a clean room poses significant challenges, as they have very different form factors and are made using incompatible processes that require post assembly. Consequently, researchers have investigated making solenoids utilizing many of the same processes that make semiconductor chips. But these techniques limit the size and shape of solenoids, which hampers performance.

With additive manufacturing, one can produce devices that are practically any size and shape. However, this presents its own challenges, since making a solenoid involves coiling thin layers made from multiple materials that may not all be compatible with one machine.

To overcome these challenges, the researchers needed to modify a commercial extrusion 3D printer.

Extrusion printing fabricates objects one layer at a time by squirting material through a nozzle. Typically, a printer uses one type of material feedstock, often spools of filament.

“Some people in the field look down on them because they are simple and don’t have a lot of bells and whistles, but extrusion is one of very few methods that allows you to do multimaterial, monolithic printing,” says Velásquez-García.

This is key, since the solenoids are produced by precisely layering three different materials — a dielectric material that serves as an insulator, a conductive material that forms the electric coil, and a soft magnetic material that makes up the core.

The team selected a printer with four nozzles — one dedicated to each material to prevent cross-contamination. They needed four extruders because they tried two soft magnetic materials, one based on a biodegradable thermoplastic and the other based on nylon.

Printing with pellets

They retrofitted the printer so one nozzle could extrude pellets, rather than filament. The soft magnetic nylon, which is made from a pliable polymer studded with metallic microparticles, is virtually impossible to produce as a filament. Yet this nylon material offers far better performance than filament-based alternatives.

Using the conductive material also posed challenges, since it would start melting and jam the nozzle. The researchers found that adding ventilation to cool the material prevented this. They also built a new spool holder for the conductive filament that was closer to the nozzle, reducing friction that could damage the thin strands.

Even with the team’s modifications, the customized hardware cost about $4,000, so this technique could be employed by others at a lower cost than other approaches, adds Velásquez-García.

The modified hardware prints a U.S. quarter-sized solenoid as a spiral by layering material around the soft magnetic core, with thicker conductive layers separated by thin insulating layers.

Precisely controlling the process is of paramount importance because each material prints at a different temperature. Depositing one on top of another at the wrong time might cause the materials to smear.

Because their machine could print with a more effective soft magnetic material, the solenoids achieved higher performance than other 3D-printed devices.

The printing method enabled them to build a three-dimensional device comprising eight layers, with coils of conductive and insulating material stacked around the core like a spiral staircase. Multiple layers increase the number of coils in the solenoid, which improves the amplification of the magnetic field.

Due to the added precision of the modified printer, they could make solenoids that were about 33 percent smaller than other 3D-printed versions. More coils in a smaller area also boosts amplification.

In the end, their solenoids could produce a magnetic field that was about three times larger than what other 3D-printed devices can achieve.

“We were not the first people to be able to make inductors that are 3D-printed, but we were the first ones to make them three-dimensional, and that greatly amplifies the kinds of values you can generate. And that translates into being able to satisfy a wider range of applications,” he says.

For instance, while these solenoids can’t generate as much magnetic field as those made with traditional fabrication techniques, they could be used as power convertors in small sensors or actuators in soft robots.

Moving forward, the researchers are looking to continue enhancing their performance.

For one, they could try using alternate materials that might have better properties. They are also exploring additional modifications that could more precisely control the temperature at which each material is deposited, reducing defects.

This work is funded by Empiriko Corporation.

Putting AI into the hands of people with problems to solve

Putting AI into the hands of people with problems to solve

As Media Lab students in 2010, Karthik Dinakar SM ’12, PhD ’17 and Birago Jones SM ’12 teamed up for a class project to build a tool that would help content moderation teams at companies like Twitter (now X) and YouTube. The project generated a huge amount of excitement, and the researchers were invited to give a demonstration at a cyberbullying summit at the White House — they just had to get the thing working.

The day before the White House event, Dinakar spent hours trying to put together a working demo that could identify concerning posts on Twitter. Around 11 p.m., he called Jones to say he was giving up.

Then Jones decided to look at the data. It turned out Dinakar’s model was flagging the right types of posts, but the posters were using teenage slang terms and other indirect language that Dinakar didn’t pick up on. The problem wasn’t the model; it was the disconnect between Dinakar and the teens he was trying to help.

“We realized then, right before we got to the White House, that the people building these models should not be folks who are just machine-learning engineers,” Dinakar says. “They should be people who best understand their data.”

The insight led the researchers to develop point-and-click tools that allow nonexperts to build machine-learning models. Those tools became the basis for Pienso, which today is helping people build large language models for detecting misinformation, human trafficking, weapons sales, and more, without writing any code.

“These kinds of applications are important to us because our roots are in cyberbullying and understanding how to use AI for things that really help humanity,” says Jones.

As for the early version of the system shown at the White House, the founders ended up collaborating with students at nearby schools in Cambridge, Massachusetts, to let them train the models.

“The models those kids trained were so much better and nuanced than anything I could’ve ever come up with,” Dinakar says. “Birago and I had this big ‘Aha!’ moment where we realized empowering domain experts — which is different from democratizing AI — was the best path forward.”

A project with purpose

Jones and Dinakar met as graduate students in the Software Agents research group of the MIT Media Lab. Their work on what became Pienso started in Course 6.864 (Natural Language Processing) and continued until they earned their master’s degrees in 2012.

It turned out 2010 wasn’t the last time the founders were invited to the White House to demo their project. The work generated a lot of enthusiasm, but the founders worked on Pienso part time until 2016, when Dinakar finished his PhD at MIT and deep learning began to explode in popularity.

“We’re still connected to many people around campus,” Dinakar says. “The exposure we had at MIT, the melding of human and computer interfaces, widened our understanding. Our philosophy at Pienso couldn’t be possible without the vibrancy of MIT’s campus.”

The founders also credit MIT’s Industrial Liaison Program (ILP) and Startup Accelerator (STEX) for connecting them to early partners.

One early partner was SkyUK. The company’s customer success team used Pienso to build models to understand their customer’s most common problems. Today those models are helping to process half a million customer calls a day, and the founders say they have saved the company over £7 million pounds to date by shortening the length of calls into the company’s call center.

The difference between democratizing AI and empowering people with AI comes down to who understands the data best — you or a doctor or a journalist or someone who works with customers every day?” Jones says. “Those are the people who should be creating the models. That’s how you get insights out of your data.”

In 2020, just as Covid-19 outbreaks began in the U.S., government officials contacted the founders to use their tool to better understand the emerging disease. Pienso helped experts in virology and infectious disease set up machine-learning models to mine thousands of research articles about coronaviruses. Dinakar says they later learned the work helped the government identify and strengthen critical supply chains for drugs, including the popular antiviral remdesivir.

“Those compounds were surfaced by a team that did not know deep learning but was able to use our platform,” Dinakar says.

Building a better AI future

Because Pienso can run on internal servers and cloud infrastructure, the founders say it offers an alternative for businesses being forced to donate their data by using services offered by other AI companies.

“The Pienso interface is a series of web apps stitched together,” Dinakar explains. “You can think of it like an Adobe Photoshop for large language models, but in the web. You can point and import data without writing a line of code. You can refine the data, prepare it for deep learning, analyze it, give it structure if it’s not labeled or annotated, and you can walk away with fine-tuned, large language model in a matter of 25 minutes.”

Earlier this year, Pienso announced a partnership with GraphCore, which provides a faster, more efficient computing platform for machine learning. The founders say the partnership will further lower barriers to leveraging AI by dramatically reducing latency.

“If you’re building an interactive AI platform, users aren’t going to have a cup of coffee every time they click a button,” Dinakar says. “It needs to be fast and responsive.”

The founders believe their solution is enabling a future where more effective AI models are developed for specific use cases by the people who are most familiar with the problems they are trying to solve.

“No one model can do everything,” Dinakar says. “Everyone’s application is different, their needs are different, their data is different. It’s highly unlikely that one model will do everything for you. It’s about bringing a garden of models together and allowing them to collaborate with each other and orchestrating them in a way that makes sense — and the people doing that orchestration should be the people who understand the data best.”

Generative AI for smart grid modeling

Generative AI for smart grid modeling

MIT’s Laboratory for Information and Decision Systems (LIDS) has been awarded $1,365,000 in funding from the Appalachian Regional Commission (ARC) to support its involvement with an innovative project, “Forming the Smart Grid Deployment Consortium (SGDC) and Expanding the HILLTOP+ Platform.”

The grant was made available through ARC’s Appalachian Regional Initiative for Stronger Economies, which fosters regional economic transformation through multi-state collaboration.

Led by Kalyan Veeramachaneni, principal research scientist and principal investigator at LIDS’ Data to AI Group, the project will focus on creating AI-driven generative models for customer load data. Veeramachaneni and colleagues will work alongside a team of universities and organizations led by Tennessee Tech University, including collaborators across Ohio, Pennsylvania, West Virginia, and Tennessee, to develop and deploy smart grid modeling services through the SGDC project.

These generative models have far-reaching applications, including grid modeling and training algorithms for energy tech startups. When the models are trained on existing data, they create additional, realistic data that can augment limited datasets or stand in for sensitive ones. Stakeholders can then use these models to understand and plan for specific what-if scenarios far beyond what could be achieved with existing data alone. For example, generated data can predict the potential load on the grid if an additional 1,000 households were to adopt solar technologies, how that load might change throughout the day, and similar contingencies vital to future planning.

The generative AI models developed by Veeramachaneni and his team will provide inputs to modeling services based on the HILLTOP+ microgrid simulation platform, originally prototyped by MIT Lincoln Laboratory. HILLTOP+ will be used to model and test new smart grid technologies in a virtual “safe space,” providing rural electric utilities with increased confidence in deploying smart grid technologies, including utility-scale battery storage. Energy tech startups will also benefit from HILLTOP+ grid modeling services, enabling them to develop and virtually test their smart grid hardware and software products for scalability and interoperability.

The project aims to assist rural electric utilities and energy tech startups in mitigating the risks associated with deploying these new technologies. “This project is a powerful example of how generative AI can transform a sector — in this case, the energy sector,” says Veeramachaneni. “In order to be useful, generative AI technologies and their development have to be closely integrated with domain expertise. I am thrilled to be collaborating with experts in grid modeling, and working alongside them to integrate the latest and greatest from my research group and push the boundaries of these technologies.”

“This project is testament to the power of collaboration and innovation, and we look forward to working with our collaborators to drive positive change in the energy sector,” says Satish Mahajan, principal investigator for the project at Tennessee Tech and a professor of electrical and computer engineering. Tennessee Tech’s Center for Rural Innovation director, Michael Aikens, adds, “Together, we are taking significant steps towards a more sustainable and resilient future for the Appalachian region.”

Cybersecurity software wins a 2024 Federal Laboratory Consortium Excellence in Technology Transfer Award

Cybersecurity software wins a 2024 Federal Laboratory Consortium Excellence in Technology Transfer Award

The Federal Laboratory Consortium (FLC) has selected MIT Lincoln Laboratory’s Timely Address Space Randomization (TASR) as one of the recipients of their 2024 Excellence in Technology Transfer Award. This cybersecurity technology was transferred in 2019 and 2021 to two companies that develop cloud-based services.

TASR has the potential to help harden many cloud-based servers and user applications against rampant information-leakage attacks. These attacks have been involved in several recent high-profile breaches in which cyber criminals used sensitive information to commit fraud or identity theft, steal financial assets, or gain unauthorized access to other restricted or mission-critical systems. TASR is the first technology that mitigates the impact of such attacks regardless of the attack mechanism or underlying system vulnerability.

A nationwide network of more than 300 government laboratories, agencies, and research centers, FLC helps facilitate the transfer of technologies out of research labs and into the marketplace to benefit the U.S. economy, society, and national security. On an annual basis, FLC confers awards to commend outstanding technology transfer achievements of employees of FLC member labs and their partners from industry, academia, nonprofits, and state and local governments. The Excellence in Technology Transfer Award recognizes exemplary transfer of federally developed technology.

“We are honored to receive this FLC award recognizing our excellence in such technology transfer — in this case, of a cutting-edge cybersecurity technology for protecting everyday users of cloud infrastructure,” says Lincoln Laboratory Chief Technology Ventures Officer Asha Rajagopal.

The Lincoln Laboratory team behind TASR initially developed the technology under sponsorship by the National Security Agency (NSA), following a survey of existing cyber defenses and their vulnerabilities. The three-year development of TASR led to a research prototype in 2015 and a U.S. patent in 2019. In 2020, the U.S. Department of Homeland Security (DHS) selected TASR for its Commercialization Accelerator Program, through which the team matured the technology and connected with commercial companies. Given the growing need for hardening cloud-based services, TASR offers an attractive solution, as it protects Linux-based applications and servers from cyberattacks. Originally developed for personal computers based on Intel’s x86 architecture, the Linux operating system now runs more than 80 percent of all internet servers, 90 percent of public cloud workloads, all 500 of the world’s fastest supercomputers, and the majority of smartphones using Android.

TASR works by automatically and transparently shuffling (rerandomizing) the location of code in memory every time an application processes an input-and-output pair. Information may leak to an attacker whenever the application sends an output, such as a file write or data packet transmitted over a network. But with TASR, the information that may be leaked during system output will have changed at the next point the attacker is able to act on such information (i.e., at system input). Through this moving-target approach, TASR addresses a significant problem contributing to information-leakage attacks: target homogeneity. Once attackers devise an attack against an application, they can easily compromise millions of computers at once because all installations of that application look alike internally. By continuously rerandomizing memory throughout the application’s execution, TASR prevents such action.

“From the first day we started working on TASR, our focus was on making the technology as practical as possible to facilitate its transition to real users. We are honored to be recognized by the FLC for the decade-long journey leading to the transfer of TASR,” says principal investigator Hamed Okhravi, senior staff in the laboratory’s Secure Resilient Systems and Technology Group. Okhravi led the nearly decade-long process of conception, NSA and DHS sponsorship, development, maturation, and transfer phases for TASR, with support from the laboratory’s Technology Ventures Office and MIT’s Technology Licensing Office. The other team members are David Bigelow, Jason Martin, and William Streilein, and former staff members Thomas Hobson and Robert Rudd. TASR was previously recognized with a 2022 R&D 100 Award, acknowledged as one of the year’s 100 most innovative technologies available for sale or license.

The TASR team and awardees in the other categories will be honored at an award ceremony on April 10 during the 2024 FLC National Meeting in Dallas, Texas.

New AI model could streamline operations in a robotic warehouse

New AI model could streamline operations in a robotic warehouse

Hundreds of robots zip back and forth across the floor of a colossal robotic warehouse, grabbing items and delivering them to human workers for packing and shipping. Such warehouses are increasingly becoming part of the supply chain in many industries, from e-commerce to automotive production.

However, getting 800 robots to and from their destinations efficiently while keeping them from crashing into each other is no easy task. It is such a complex problem that even the best path-finding algorithms struggle to keep up with the breakneck pace of e-commerce or manufacturing. 

In a sense, these robots are like cars trying to navigate a crowded city center. So, a group of MIT researchers who use AI to mitigate traffic congestion applied ideas from that domain to tackle this problem.

They built a deep-learning model that encodes important information about the warehouse, including the robots, planned paths, tasks, and obstacles, and uses it to predict the best areas of the warehouse to decongest to improve overall efficiency.

Their technique divides the warehouse robots into groups, so these smaller groups of robots can be decongested faster with traditional algorithms used to coordinate robots. In the end, their method decongests the robots nearly four times faster than a strong random search method.

In addition to streamlining warehouse operations, this deep learning approach could be used in other complex planning tasks, like computer chip design or pipe routing in large buildings.

“We devised a new neural network architecture that is actually suitable for real-time operations at the scale and complexity of these warehouses. It can encode hundreds of robots in terms of their trajectories, origins, destinations, and relationships with other robots, and it can do this in an efficient manner that reuses computation across groups of robots,” says 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, senior author of a paper on this technique, is joined by lead author Zhongxia Yan, a graduate student in electrical engineering and computer science. The work will be presented at the International Conference on Learning Representations.

Robotic Tetris

From a bird’s eye view, the floor of a robotic e-commerce warehouse looks a bit like a fast-paced game of “Tetris.”

When a customer order comes in, a robot travels to an area of the warehouse, grabs the shelf that holds the requested item, and delivers it to a human operator who picks and packs the item. Hundreds of robots do this simultaneously, and if two robots’ paths conflict as they cross the massive warehouse, they might crash.

Traditional search-based algorithms avoid potential crashes by keeping one robot on its course and replanning a trajectory for the other. But with so many robots and potential collisions, the problem quickly grows exponentially.

“Because the warehouse is operating online, the robots are replanned about every 100 milliseconds. That means that every second, a robot is replanned 10 times. So, these operations need to be very fast,” Wu says.

Because time is so critical during replanning, the MIT researchers use machine learning to focus the replanning on the most actionable areas of congestion — where there exists the most potential to reduce the total travel time of robots.

Wu and Yan built a neural network architecture that considers smaller groups of robots at the same time. For instance, in a warehouse with 800 robots, the network might cut the warehouse floor into smaller groups that contain 40 robots each.

Then, it predicts which group has the most potential to improve the overall solution if a search-based solver were used to coordinate trajectories of robots in that group.

An iterative process, the overall algorithm picks the most promising robot group with the neural network, decongests the group with the search-based solver, then picks the next most promising group with the neural network, and so on.

Considering relationships

The neural network can reason about groups of robots efficiently because it captures complicated relationships that exist between individual robots. For example, even though one robot may be far away from another initially, their paths could still cross during their trips.

The technique also streamlines computation by encoding constraints only once, rather than repeating the process for each subproblem. For instance, in a warehouse with 800 robots, decongesting a group of 40 robots requires holding the other 760 robots as constraints. Other approaches require reasoning about all 800 robots once per group in each iteration.

Instead, the researchers’ approach only requires reasoning about the 800 robots once across all groups in each iteration.

“The warehouse is one big setting, so a lot of these robot groups will have some shared aspects of the larger problem. We designed our architecture to make use of this common information,” she adds.

They tested their technique in several simulated environments, including some set up like warehouses, some with random obstacles, and even maze-like settings that emulate building interiors.

By identifying more effective groups to decongest, their learning-based approach decongests the warehouse up to four times faster than strong, non-learning-based approaches. Even when they factored in the additional computational overhead of running the neural network, their approach still solved the problem 3.5 times faster.

In the future, the researchers want to derive simple, rule-based insights from their neural model, since the decisions of the neural network can be opaque and difficult to interpret. Simpler, rule-based methods could also be easier to implement and maintain in actual robotic warehouse settings.

“This approach is based on a novel architecture where convolution and attention mechanisms interact effectively and efficiently. Impressively, this leads to being able to take into account the spatiotemporal component of the constructed paths without the need of problem-specific feature engineering. The results are outstanding: Not only is it possible to improve on state-of-the-art large neighborhood search methods in terms of quality of the solution and speed, but the model generalizes to unseen cases wonderfully,” says Andrea Lodi, the Andrew H. and Ann R. Tisch Professor at Cornell Tech, and who was not involved with this research.

This work was supported by Amazon and the MIT Amazon Science Hub.

Sadhana Lolla named 2024 Gates Cambridge Scholar

Sadhana Lolla named 2024 Gates Cambridge Scholar

MIT senior Sadhana Lolla has won the prestigious Gates Cambridge Scholarship, which offers students an opportunity to pursue graduate study in the field of their choice at Cambridge University in the U.K.

Established in 2000, the Gates Cambridge Scholarship offers full-cost post-graduate scholarships to outstanding applicants from countries outside of the U.K. The mission of the scholarship is to build a global network of future leaders committed to improving the lives of others.

Lolla, a senior from Clarksburg, Maryland, is majoring in computer science and minoring in mathematics and literature. At Cambridge, she will pursue an MPhil in technology policy.

In the future, Lolla aims to lead conversations on deploying and developing technology for marginalized communities, such as the rural Indian village that her family calls home, while also conducting research in embodied intelligence.

At MIT, Lolla conducts research on safe and trustworthy robotics and deep learning at the Distributed Robotics Laboratory with Professor Daniela Rus. Her research has spanned debiasing strategies for autonomous vehicles and accelerating robotic design processes. At Microsoft Research and Themis AI, she works on creating uncertainty-aware frameworks for deep learning, which has impacts across computational biology, language modeling, and robotics. She has presented her work at the Neural Information Processing Systems (NeurIPS) conference and the International Conference on Machine Learning (ICML). 

Outside of research, Lolla leads initiatives to make computer science education more accessible globally. She is an instructor for class 6.s191 (MIT Introduction to Deep Learning), one of the largest AI courses in the world, which reaches millions of students annually. She serves as the curriculum lead for Momentum AI, the only U.S. program that teaches AI to underserved students for free, and she has taught hundreds of students in Northern Scotland as part of the MIT Global Teaching Labs program.

Lolla was also the director for xFair, MIT’s largest student-run career fair, and is an executive board member for Next Sing, where she works to make a cappella more accessible for students across musical backgrounds. In her free time, she enjoys singing, solving crossword puzzles, and baking. 

“Between Sadhana’s impressive research in the Distributed Robotics Group, her volunteer teaching with Momentum AI, and her internship and extracurricular experiences, she has developed the skills to be a leader,” says Kim Benard, associate dean of distinguished fellowships in Career Advising and Professional Development. “Her work at Cambridge will allow her the time to think about reducing bias in systems and the ethical implications of her work. I am proud that she will be representing MIT in the Gates Cambridge community.”

Moving past the Iron Age

Moving past the Iron Age

MIT graduate student Sydney Rose Johnson has never seen the steel mills in central India. She’s never toured the American Midwest’s hulking steel plants or the mini mills dotting the Mississippi River. But in the past year, she’s become more familiar with steel production than she ever imagined.

A fourth-year dual degree MBA and PhD candidate in chemical engineering and a graduate research assistant with the MIT Energy Initiative (MITEI) as well as a 2022-23 Shell Energy Fellow, Johnson looks at ways to reduce carbon dioxide (CO2) emissions generated by industrial processes in hard-to-abate industries. Those include steel.

Almost every aspect of infrastructure and transportation — buildings, bridges, cars, trains, mass transit — contains steel. The manufacture of steel hasn’t changed much since the Iron Age, with some steel plants in the United States and India operating almost continually for more than a century, their massive blast furnaces re-lined periodically with carbon and graphite to keep them going.

According to the World Economic Forum, steel demand is projected to increase 30 percent by 2050, spurred in part by population growth and economic development in China, India, Africa, and Southeast Asia.

The steel industry is among the three biggest producers of CO2 worldwide. Every ton of steel produced in 2020 emitted, on average, 1.89 tons of CO2 into the atmosphere — around 8 percent of global CO2 emissions, according to the World Steel Association.

A combination of technical strategies and financial investments, Johnson notes, will be needed to wrestle that 8 percent figure down to something more planet-friendly.

Johnson’s thesis focuses on modeling and analyzing ways to decarbonize steel. Using data mined from academic and industry sources, she builds models to calculate emissions, costs, and energy consumption for plant-level production.

“I optimize steel production pathways using emission goals, industry commitments, and cost,” she says. Based on the projected growth of India’s steel industry, she applies this approach to case studies that predict outcomes for some of the country’s thousand-plus factories, which together have a production capacity of 154 million metric tons of steel. For the United States, she looks at the effect of Inflation Reduction Act (IRA) credits. The 2022 IRA provides incentives that could accelerate the steel industry’s efforts to minimize its carbon emissions.

Johnson compares emissions and costs across different production pathways, asking questions such as: “If we start today, what would a cost-optimal production scenario look like years from now? How would it change if we added in credits? What would have to happen to cut 2005 levels of emissions in half by 2030?”

“My goal is to gain an understanding of how current and emerging decarbonization strategies will be integrated into the industry,” Johnson says.

Grappling with industrial problems

Growing up in Marietta, Georgia, outside Atlanta, the closest she ever came to a plant of any kind was through her father, a chemical engineer working in logistics and procuring steel for an aerospace company, and during high school, when she spent a semester working alongside chemical engineers tweaking the pH of an anti-foaming agent.

At Kennesaw Mountain High School, a STEM magnet program in Cobb County, students devote an entire semester of their senior year to an internship and research project.

Johnson chose to work at Kemira Chemicals, which develops chemical solutions for water-intensive industries with a focus on pulp and paper, water treatment, and energy systems.

“My goal was to understand why a polymer product was falling out of suspension — essentially, why it was less stable,” she recalls. She learned how to formulate a lab-scale version of the product and conduct tests to measure its viscosity and acidity. Comparing the lab-scale and regular product results revealed that acidity was an important factor. “Through conversations with my mentor, I learned this was connected with the holding conditions, which led to the product being oxidized,” she says. With the anti-foaming agent’s problem identified, steps could be taken to fix it.

“I learned how to apply problem-solving. I got to learn more about working in an industrial environment by connecting with the team in quality control as well as with R&D and chemical engineers at the plant site,” Johnson says. “This experience confirmed I wanted to pursue engineering in college.”

As an undergraduate at Stanford University, she learned about the different fields — biotechnology, environmental science, electrochemistry, and energy, among others — open to chemical engineers. “It seemed like a very diverse field and application range,” she says. “I was just so intrigued by the different things I saw people doing and all these different sets of issues.”

Turning up the heat

At MIT, she turned her attention to how certain industries can offset their detrimental effects on climate.

“I’m interested in the impact of technology on global communities, the environment, and policy. Energy applications affect every field. My goal as a chemical engineer is to have a broad perspective on problem-solving and to find solutions that benefit as many people, especially those under-resourced, as possible,” says Johnson, who has served on the MIT Chemical Engineering Graduate Student Advisory Board, the MIT Energy and Climate Club, and is involved with diversity and inclusion initiatives.

The steel industry, Johnson acknowledges, is not what she first imagined when she saw herself working toward mitigating climate change.

“But now, understanding the role the material has in infrastructure development, combined with its heavy use of coal, has illuminated how the sector, along with other hard-to-abate industries, is important in the climate change conversation,” Johnson says.

Despite the advanced age of many steel mills, some are quite energy-efficient, she notes. Yet these operations, which produce heat upwards of 3,000 degrees Fahrenheit, are still emission-intensive.

Steel is made from iron ore, a mixture of iron, oxygen, and other minerals found on virtually every continent, with Brazil and Australia alone exporting millions of metric tons per year. Commonly based on a process dating back to the 19th century, iron is extracted from the ore through smelting — heating the ore with blast furnaces until the metal becomes spongy and its chemical components begin to break down.

A reducing agent is needed to release the oxygen trapped in the ore, transforming it from its raw form to pure iron. That’s where most emissions come from, Johnson notes.

“We want to reduce emissions, and we want to make a cleaner and safer environment for everyone,” she says. “It’s not just the CO2 emissions. It’s also sometimes NOx and SOx [nitrogen oxides and sulfur oxides] and air pollution particulate matter at some of these production facilities that can affect people as well.”

In 2020, the International Energy Agency released a roadmap exploring potential technologies and strategies that would make the iron and steel sector more compatible with the agency’s vision of increased sustainability. Emission reductions can be accomplished with more modern technology, the agency suggests, or by substituting the fuels producing the immense heat needed to process ore. Traditionally, the fuels used for iron reduction have been coal and natural gas. Alternative fuels include clean hydrogen, electricity, and biomass.

Using the MITEI Sustainable Energy System Analysis Modeling Environment (SESAME), Johnson analyzes various decarbonization strategies. She considers options such as switching fuel for furnaces to hydrogen with a little bit of natural gas or adding carbon-capture devices. The models demonstrate how effective these tactics are likely to be. The answers aren’t always encouraging.

“Upstream emissions can determine how effective the strategies are,” Johnson says. Charcoal derived from forestry biomass seemed to be a promising alternative fuel, but her models showed that processing the charcoal for use in the blast furnace limited its effectiveness in negating emissions.

Despite the challenges, “there are definitely ways of moving forward,” Johnson says. “It’s been an intriguing journey in terms of understanding where the industry is at. There’s still a long way to go, but it’s doable.”

Johnson is heartened by the steel industry’s efforts to recycle scrap into new steel products and incorporate more emission-friendly technologies and practices, some of which result in significantly lower CO2 emissions than conventional production.

A major issue is that low-carbon steel can be more than 50 percent more costly than conventionally produced steel. “There are costs associated with making the transition, but in the context of the environmental implications, I think it’s well worth it to adopt these technologies,” she says.

After graduation, Johnson plans to continue to work in the energy field. “I definitely want to use a combination of engineering knowledge and business knowledge to work toward mitigating climate change, potentially in the startup space with clean technology or even in a policy context,” she says. “I’m interested in connecting the private and public sectors to implement measures for improving our environment and benefiting as many people as possible.”