Uncategorized

From the mystery of neutrinos and gravitational waves to diagnosing cancer in fractions of a second | technology


Pablo Morales Alvarez, computer scientist awarded by SCIE and BBVA for his algorithms for determining the effects of gravitational waves.
Pablo Morales Alvarez, computer scientist awarded by SCIE and BBVA for his algorithms for determining the effects of gravitational waves.Miguel Angel Medina / BBVA Foundation

A simple and common criticism of investigations into the origin and behavior of the universe is their lack of practical application in everyday life. If the answer is that these studies allow us to know our world and the emergence of life is not enough, two of the ten prizes presented by the Spanish Society for Scientific Information (SCIE) – BBVA Foundation (granted 5,000 euros) this year provide a resounding answer: computer scientists got Saúl Alonso Monsalve, aged 28, from Madrid, and Pablo Morales Álvarez, aged 30, from Granada, won an award for their work with artificial intelligence to identify neutrinos and measure the effects of gravitational waves, two global singularities that affected them led to the development of tools that help in diagnosing cancer in fractions of a second.

Neutrinos are the second most abundant particle in the universe after photons (particles of light). Billions of matter first pass through our bodies – and any matter – every second, because it lacks electric charge and only interacts with the weak nuclear force (one of the known forces along with gravity, electromagnetism, and the strong nuclear). They also have mass, though it is not known how much or how it originated, and they travel in straight lines, so they are unique messengers of the origin of the universe. But these singularities make them so difficult to detect, that they are called “ghost particles”.

See also  Twitter Blue: The paid version of Twitter is now available in Spain | Technique

The types of neutrinos (electron, muon, and tau) are known in physics as “flavours” and they oscillate. “This means,” explains Alonso Monsalve, “that when you measure the flavor of a neutrino some time after its formation, it could have changed.” Matter particles (dominant, though why is not known) interact with antimatter, which is called a CP violation (symmetry of charge). Thus, neutrinos and antineutrinos oscillate differently. “The discovery of CP violation in the neutrino sector can finally explain the difference between matter and antimatter in the universe and give us a lot of information about their origin,” the computer researcher elaborates.

To detect neutrinos, Alonso Monsalve participated in the Deep Underground Neutrino Experiment (DUNE), an accelerator equipped with beam detectors for these ghostly particles that travel 1,300 kilometers through the Earth’s interior in the United States. The Spanish researcher has applied his computational knowledge to develop an algorithm that determines the flavor of neutrinos after their long journey. It would be like a facial recognition system that verifies that whoever arrived at the border is the same person who left another country based on their passport photo and how the trip affected them.

“My job,” Alonso Monsalve details, “was collecting images from detectors and applying AI algorithms to understand what’s going on. Even an expert can’t look at those images and conclude 100% that it’s an electron, a muon, or a tau neutrino. AI algorithms identify neutrinos and reconstruct the particles In three dimensions of the two-dimensional projections that the detectors see. In addition, they discriminate against noise, because what is collected is not exactly what happened.”

See also  The lack of transparency with permanent interruptions calls into question the reliability of the unemployment record
Computer scientist Saúl Alonso Monsalve, at CERN headquarters, where he developed his doctoral thesis.
Computer scientist Saúl Alonso Monsalve, at CERN headquarters, where he developed his doctoral thesis.BBVA Foundation

Pablo Morales Alvarez’s award-winning work also has to do with the universe, specifically with gravitational waves. These are ripples caused by extremely violent events, such as the merger of two black holes or a supernova, that travel at the speed of light and alter space-time, an effect described by Albert Einstein, but not proven until its discovery. GW150914 in September 2015, although it was announced six months later.

These ripples, like those in the skin of a percussion instrument, physically distort everything in its path, but the trail that reaches the floor is almost undetectable.

Morales-Alvarez collaborated with the US LIGO project to detect gravitational waves, an experiment that identifies changes to the millionth of a millimeter in a mineral structure caused by cosmic ripples. “It’s like gaining a new sense,” he explains. In this sense, the researcher specifies that gravitational waves are not like sound waves that do not propagate in a vacuum or electromagnetic waves. “They have another new nature, hence their interest,” he says.

“We now want to automate and speed up the process of detecting gravitational waves,” he adds. “They leave a mark and my job was to create an algorithm that automates the process of distinguishing between gravitational waves and what isn’t. An expert can do that, but the stream of data that’s being generated is so massive you can’t have a physicist read all that information to identify a wave.”

Since the algorithm does not learn on its own and feeds off information provided by a group of trained volunteers, Morales’ work on the computer made the computational, in addition to identifying waves, also learn to identify the source of the information, which is more reliable. Because of errors previously discovered in other notes.

The work of both is necessary to observe the universe. But it also ended up being the closest apps. Alonso Monsalve used his knowledge of neutrino identification to develop an algorithm capable of identifying liver cancer in fractions of a second from analyzing patients’ radiological images. The advantage of his system is that it converts 2D images into 3D reconstructions, which makes the analysis more accurate and complete.

Its pattern was developed from expert information from around the world on 300 images that allowed teaching AI to identify and locate a tumor. “The results don’t replace an expert’s diagnosis, but they help and guide you within milliseconds,” he notes.

Similarly, Morales-Alvarez spent two years applying his expertise in gravitational wave detection to identify tumors from microscopic images obtained from biopsies. “It’s also a diagnostic aid system that shows the pathologist if and where there are patterns consistent with cancer,” he explains.

You can write to [email protected]will follow country technology in Facebook s Twitter Sign up here to receive The weekly newsletter

Subscribe to continue reading

Read without limits



Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button