Tags Posts tagged with "Ali Khosronejad"

Ali Khosronejad

Ali Khosronejad in front of the Santa Maria Cathedral, which is considered the first modern cathedral in Madrid.

By Daniel Dunaief

An approaching weather front brings heavy rains and a storm surge, threatening to inundate homes and businesses with dangerous water and potentially undermining critical infrastructure like bridges.

Once officials figure out the amount of water that will affect an area, they can either send out inspectors to survey the exact damage or they can use models that take time to process and analyze the likely damage.

Ali Khosronejad

Ali Khosronejad, Associate Professor in the Department of Civil Engineering at Stony Brook University, hopes to use artificial intelligence to change that.

Khosronejad recently received $550,000 from the National Science Foundation (NSF) for four years to create a high-fidelity model using artificial intelligence that will predict the flood impact on infrastructure.

The funds, which will be available starting on June 20, will support two PhD students who will work to provide an artificial intelligence-based program that can work on a single laptop at a “fraction of the cost of more advanced modeling approaches,” Khosronejad said during an interview in Madrid, Spain, where he is on sabbatical leave under a Fulbright U.S Senior Scholar Award. He is doing his Fulbright research at Universidad Carlos III de Madrid.

Stony Brook University will also provide some funding for these students, which will help defray the cost of expenses related to traveling and attending conferences and publishing papers.

In the past, Stony Brook has been “quite generous when it comes to supporting graduate students working on federally funded projects,” Khosronejad explained and he hopes that continues with this research.

Khosronejad and his students will work with about 50 different flooding and terrain scenarios, which will cover about 95 percent of extreme flooding. These 50 possibilities will cover a range of waterways, infrastructure, topography, and coastal areas. The researchers will feed data into their high fidelity supercomputing cluster simulations to train artificial intelligence to assess the likely damage from a flood.

As they build the model, Khosronejad explained that they will collect data from floods, feed them into the computer and test how well the computer predicts the kind of flooding that has can cause damage or threaten the stability of structures like bridges. Over the next four years, the team will collect data from the Departments of Transportation in California, Minnesota and New York.

Nearly six years ago, his team attempted to use algorithms available in ChatGPT for some of his AI development. Those algorithms, however, didn’t predict flood flow prediction. He tried to develop new algorithms based on convolutional neural networks. Working with CNN, he attempted to improve its capabilities by including some physics-based constraints.

“We are very enthusiastic about this,” Khosronejad said. “We do think that this opportunity can help us to open up the use of AI for other applications in fluid mechanics” in fields such as renewable energy, contaminant transport predictions in urban areas and biological flow predictions, among others.

Planners working with groups such as the California Department of Transportation could use such a program to emphasize which infrastructure might be endangered.

This analysis could highlight effective mitigation strategies. Artificial intelligence can “provide [planners and strategists] with a tool that is not that expensive, can run on a single laptop, can reproduce lots of scenarios with flooding, to figure out which infrastructure is really in danger,” Khosronejad said.

Specifically, this tool could evaluate the impact of extreme floods on bridge foundations. Floods can remove soil from around the foundation of a bridge, which can cause it to collapse. Civil engineers can strengthen bridge foundations and mitigate the effect of future floods by using riprap, which is a layer of large stones.

This kind of program can reduce the reliance on surveying after a flood, which is expensive and sometimes “logistically impossible and unsafe” to monitor areas like the foundations of bridges, Khosronejad said. He plans to build into the AI program an awareness of the changing climate, so that predictions using it in three or five years can provide an accurate reflection of future conditions.

“Floods are getting more and more extreme” he said. “We realize that floods we feed into the program during training will be different” from the ones that will cause damage in subsequent years.

Floods that had a return period of every 100 years are now happening much more frequently. In one or two decades, such a flood might occur every 10 years.

Adding updated data can allow practitioners to make adjustments to the AI program a decade down the road, he suggested. He and his team will add data every year, which will create a more versatile model.

What it can’t do

While the AI programs will predict the damage to infrastructure from floods, they will not address storm or flood predictions.

“Those are different models, based on the movement of clouds” and other variables, Khosronejad said. “This doesn’t do that: if you give the program a range of flood magnitudes, it will tell you what will happen.”

High fidelity models currently exist that can do what Khosronejad is proposing, although those models require hundreds of CPUs to run for five months. Khosronejad has developed his own in house high fidelity model that is capable of making similar predictions. He has tested it to examine various infrastructures and used it to study various flooding events. These models are expensive, which is why he’s trying to replace them with AI to reduce the cost while maintaining fidelity.

AI, on the other hand, can run on a single CPU and may be able to provide the same result, which will allow people to plan ahead before it happens. The NSF approved the single principal investigator concept two months ago.

Khosronejad has worked with Fotis Sotiropoulos, former Dean of the College of Engineering and Applied Sciences at Stony Brook and current Provost at Virginia Commonwealth University, on this and other projects.

The two have bi-weekly discussions over the weekend to discuss various projects.

Sotiropoulos was “very happy” when Khosronejad told him he received the funds. Although he’s not a part of the project, Sotiropoulos will “provide inputs.”

Sotiropoulos has “deep insights” into fluid mechanics. “When you have him on your side, it always pays off,” Khosronejad said.

Pixabay photo

By Daniel Dunaief

While wind is nice and effective, moving water is even more promising, especially in the future of alternative energies.

Ali Khosronejad. Photo from SBU

That’s because water is almost 1,000 times more dense than air, which means that the movement of the wet stuff due to tides or storms could produce a considerable amount of energy.

Indeed, “if we can effectively harness the energy from moving waters in our national waterways alone, it could provide enough energy to power the whole country,” said Ali Khosronejad, Assistant Professor in the Department of Civil Engineering at Stony Brook University.

Khosronejad recently received $2 million as part of a $9.7 million four-year Department of Energy grant to study and develop ways to turn the movement of water into usable energy.

“I’m very optimistic about the future of this” approach, he said.

The DOE funds, which will involve a collaboration with East Carolina University, the University of New Hampshire, and Lehigh University, is a part of the new Atlantic Marine Energy Center, for which Khosronejad is a co-director.

The funds at Stony Brook will support hiring researchers at numerous levels, from post doctoral scientists, to graduate students and undergraduates. The money will also support adding new computer modules and expanding storage at the supercomputer. 

Stony Brook will also tap into these funds to enable travel for these new hires, to help them interact in person with their collaborators from other universities.

The combined effort at these academic centers will be dedicated to researching ocean energy technology, education and outreach. 

Researchers will work in the field, the laboratory and with computers on these ocean energy projects. They will seek to use wave energy and tidal energy conversion through such efforts as wave energy converters and tidal turbine farms.

This image depicts simulated turbulence in a waterway where a virtual tidal farm can be installed. The Stony Brook research team will use such simulations to investigate potential renewable ocean energy options. Image from Ali Khosronejad

The wave-energy converter floats on the seawater surface and uses the energy from the up and down motion of the water surface to produce electrical energy.

Researchers around the world are working to improve the efficiency of tidal turbine farms. Khosronejad described the effort as being in its infancy.

A good portion of the current project involves finding ways to optimize the positioning and layout of turbines in tidal farms. In his team, Khosronejad will work on the development of new artificial intelligence approaches to optimize the positioning and layout of turbines in tidal farms.

Stony Brook’s role in this project will involve working with computers.

In his research group, Khosronejad will work with supercomputers. His effort involves working to develop high-fidelity mathematical models that can address sediment transport and sediment-laden flows in tidal farms. 

Scientists at the University of New Hampshire and ECU are involved in addressing environmental concerns.

In the Department of Electrical Engineering at Stony Brook, co-principal investigators Fang Luo, Associate Professor and Peng Zhang, Professor in the Department of Electrical Engineering will work with computers and laboratories for micro-grid software and hardware research, respectively.

Ali Khosronejad, right, with former graduate student Kevin Flora, who earned his PhD in 2021

Working with Lehigh University, Khosronejad is doing high fidelity simulations, to replicate what researchers in the field at the University of New Hampshire and the Coastal Studies Institute at ECU are studying.

“We validate and develop artificial intelligence for design optimization of these tidal farms,” Khosronejad explained. The goal is to optimize the design of hydrokinetic turbines in estuaries and coastal areas that can create tidal farms.

The collaboration will coordinate with the National Renewable Energy Laboratory, Sandia National Laboratories, Pacific Northwest National Laboratory, European Marine Energy Centre and Old Dominion University.

The first year of the project involves hiring, training graduates and undergraduates, setting up the foundation, and beginning the infrastructure upgrade.

“The training part is important,” Khosronejad said. “This will be the next workforce. The infrastructure will stay there for the next 10 years” so the university can use it in a host of other projects.

Khosronejad is encouraged by the financial commitment from the Department of Energy. “They understand how important it is, which is why they are investing a lot in this,” he said. Some of these tidal farms are already working in the East River, between Manhattan and Roosevelt Island.

Wind turbines

At the same time, Khosronejad is continuing a wind turbine project he started with Fotis Sotiropoulos, the former dean of the College of Engineering and Applied Sciences at Stony Brook who is now Provost at Virginia Commonwealth University.

Khosronejad is now the principal investigator on that $1.1 million project and is continuing to work with Sotiropoulos, who officially left the project but is still volunteering to participate in its research activities. The scientists are working on how to use artificial intelligence to enhance the design of wind turbines.

Computer programs can alter the angle of the blades for the offshore wind farms where they attempt to use a control system to pitch the blades automatically to reduce the wind load during highly turbulent wind flows.

Changing the angle of attack of the blade can lower the loads and save money that would otherwise go to repairing blades that cracked or developed weaknesses amid strong winds, Khosronejad said.

The researchers presented their results at the American Physical Society meeting in Phoenix just before Thanksgiving. 

The researchers are trying to balance between using the turbine to generate energy and preventing the force of the winds from damaging the system.

When wind speeds are up to 25 miles per hour, the system uses the full power of the wind to maximize energy production. At speeds above that, the turbulent wind can damage the rotor and gearbox. The blades are pitched to reduce the angular velocity, which is known as self-preservation mode. At speeds over 55 miles per hour, the turbine stops working to produce no energy and avoid significant damage to the rotors and gearbox.

Generally, such federal research projects involve sharing results publicly and with the industry sector. The goal is to share science that enables the production of reliable energy.

 

 

Dean Sotiropoulos. Photo courtesy of SBU

By Daniel Dunaief

Too much of a good thing can be a problem. That’s true even for offshore wind farms.

Fotis Sotiropoulos

Using the flow of air to move blades, wind farms convert motion into electricity. The process of gathering energy has numerous costs, including the strain that builds up on the blades, which causes the kind of wear and tear that can reduce the efficiency of the process. The more often companies have to maintain the turbines, the higher the cost of the energy.

Fotis Sotiropoulos, the Dean of the College of Engineering and Applied Sciences and Ali Khosronejad, an assistant professor of Civil Engineering at Stony Brook University, are using computers to reduce the cost and increase the efficiency of these wind farms.

Experts in computer modeling and the flow of everything from water to air to blood through the body, Sotiropoulos and Khosronejad recently received a $1.1 million award from the National Offshore Wind Research and Development Consortium to use computational tools to create the best layout and operations for turbines for offshore wind farms.

By controlling the turbine through computer modeled yawing and/or pitching the blades, the scientists will try to optimize the annual energy production and minimize the structural loads, which reduces the need for maintenance.

“We don’t want too much pressure and turbulence, but at the same time, we want to generate maximum energy from the wind,” explained Khosronejad from Stony Brook University Hospital two days after his second daughter Amytis was born.

Ali Khosronejad

Khosronejad and Sotiropoulos, who worked together for seven years at the University of Minnesota before they came separately to Stony Brook, project that the insights that they gain through virtual modeling that uses enormous data streams over large areas of the ocean can reduce the so-called levelized cost of energy (LCOE) by as much as 15 percent.

The LCOE represents the net present cost of electricity generation for an energy plant over its lifetime. Any such reduction in these costs increases available resources for companies like Equinor, a Stavanger, Norway-based leader in offshore wind development that is a partner in this work, to increase the efficiency and effectiveness of generating energy.

Sotiropoulos suggested that virtual models that use high performance supercomputers can enable simulations that can lead to the construction of more efficient and effective wind farms.

“The more you keep cycling and fatiguing [the blades] with high bursts of wind, the more likely you are to develop micro cracks,” which require companies to shut down the facility to repair or replace the blade, Sotiropoulos said.

Companies have developed programs that allow the blades to sense the forces and that can orient or pitch the blades to minimize the loads. “What has never been done before, however, is to incorporate the effect of these control strategies into the design of an entire wind farm,” Sotiropoulos wrote in an email.

The addition of artificial intelligence tools is a new element to previous work. Training artificial intelligence models that use state-of-the-art algorithms will be computationally efficient for optimization studies, he explained.

Over the last 10 years, Sotiropoulos has received over $13 million of the $37 million in total research funding he received for wind and tidal energy. Indeed, when he was at the University of Minnesota, which will serve as a partner on the current project, Sotiropoulos received one of three Department of Energy grants across the nation to build a 2.5 megawatt turbine to conduct research that also provided power.

When he arrived at Stony Brook University as dean, he knew “Long Island had tremendous off shore wind potential,” Sotiropoulos said. Long Island has the only offshore wind farm in the United States, with a 30 megawatt facility off of Block Island.

Indeed, New York State has made considerable investments in wind energy in general and in Stony Brook’s efforts in particular. Early this year, Governor Andrew Cuomo (D) announced an investment of $20 million in a new offshore wind training institute hosted by Stony Brook and SUNY Farmingdale. The institute plans to train 2,500 workers over the next five years.

New York State is moving forward to develop 9,000 megawatts of offshore wind by 2035 and will lead the nation, Sotiropoulos said. “All of that is going to happen around here because of these activities” focused in the area. “The work done here will set the standard for how to develop offshore wind in the rest of the country.”

Specifically, Khosronejad, who joined Stony Brook in September of 2016, described the artificial intelligence that he and Sotiropoulos will use as being similar to the cognitive development of a child. As the scientists add data to their algorithms, the programs begin to learn how any given input can lead to a specific output.

Through parallel supercomputing, they can look at the flow of wind in an area that is 100 miles by 100 miles and that has a height up to one mile above the surface of the water.

“We want to solve for small pockets of air,” Khosronejad said. This can be done with a resolution of about a foot, depending on the availability of CPU on the supercomputing cluster.

On a laptop, that kind of data analysis would take at least 1,000 years to complete. By using supercomputers, they can model the wind flows, which inform their artificial intelligence models, in a week.

The scientists introduce new scenarios that the model didn’t experience during training, which has an error rate that is below one percent.

“It’s a very intelligent system that is affordable to use and that a practitioner can install on their cell phone,” Khosronejad said.

A native of Tehran, Iran, Khosronejad has been in the United States for 12 years. He didn’t speak much English when he arrived and said he took about five years to master it.

Khosronejad and his wife Sanam Ghandehari, who practices family and immigration law, have a 12-year old daughter, Aramis. The family lives in the village of Port Jefferson.

Ghandehari teaches at Touro Law School. Khosronejad described his wife as “incredibly strong” and so smart that he feels intellectually dwarfed when he sits next to her.

As for the next step in their work, Sotiropoulos suggested they would partner with scientists specializing in meso scale weather predictions from the School of Marine and Atmospheric Sciences to look at weather patterns over different parts of the year.

Photos courtesy of SBU