In the ongoing endeavor to understand the mysteries of outer space, scientists at the U.S. Department of Energy’s Princeton Plasma Physics Laboratory (PPPL) have developed an innovative computer program that utilizes machine learning and could potentially assist in identifying plasma blobs in outer space, commonly referred to as plasmoids. What sets this program apart is that it has been trained using simulated data.
This program is designed to analyze extensive spacecraft data collected in the magnetosphere, the area of outer space strongly influenced by Earth’s magnetic field, and highlight distinct indicators of these hard-to-detect blobs.
Using this technique, scientists hope to gain a deeper understanding of magnetic reconnection by employing this method, which has the potential to cause disruptions to communication satellites and the electrical grid in the magnetosphere and beyond.
Scientists believe that the use of machine learning could enhance the ability to locate plasmoids, advance comprehension of magnetic reconnection, and assist in preparing for disturbances caused by reconnection.
“As far as we know, this is the first time that anyone has used artificial intelligence trained on simulated data to look for plasmoids,” said Kendra Bergstedt(Link is external), a graduate student in the Princeton Program in Plasma Physics(Link is external), which is based at PPPL.
Researchers are seeking reliable and accurate techniques to detect plasmoids so that they can determine their impact on magnetic reconnection. Magnetic reconnection involves the violent separation, reattachment, and release of large amounts of energy in magnetic field lines. When this process happens near Earth, it can set off a series of charged particles entering the atmosphere, causing disruptions to satellites, cell phones, and the power grid.
“Some researchers believe that plasmoids aid fast reconnection in large plasmas,” said Hantao Ji, a professor of astrophysical sciences at Princeton University and a distinguished research fellow at PPPL. “But those hypotheses haven’t been proven yet.”
The researchers are investigating whether plasmoids can influence the rate of reconnection and the amount of energy transmitted to the plasma particles. They have used computer-generated training data to ensure that the program can identify various plasma signatures. Typically, computer-generated plasmoids are based on idealized mathematical formulas and often have shapes such as perfect circles, which are not commonly found in nature. To prevent the program from missing plasmoids with different shapes, the scientists deliberately used artificially imperfect data to provide an accurate baseline for future studies.
“Compared to mathematical models, the real world is messy,” Bergstedt said. “So we decided to let our program learn using data with fluctuations that you would get in actual observations. For instance, rather than beginning our simulations with a perfectly flat electrical current sheet, we give our sheet some wobbles. We’re hoping that the machine learning approach can allow for more nuance than a strict mathematical model can.”
Bergstedt and Ji aim to utilize the plasmoid-detecting software to analyze the data collected during NASA’s Magnetospheric Multiscale (MMS) mission. Launched in 2015 to investigate reconnection, MMS comprises four spacecraft operating in unison through plasma in the magnetotail, the region in space that is directed away from the sun and influenced by Earth’s magnetic field.
The magnetotail offers an ideal setting for reconnection studies due to its combination of accessibility and scale. “If we observe reconnection in a laboratory, we can put our instruments directly into the plasma, but the sizes of the plasmas would be smaller than those typically found in space.” Studying reconnection in the magnetotail is an ideal middle option. “It’s a large and naturally occurring plasma that we can measure directly using spacecraft that fly through it,” Bergstedt said.
Bergstedt and Ji are looking to make two key advancements as they enhance the plasmoid-detecting software. Their first goal is to implement domain adaptation to enable the program to analyze datasets that are unfamiliar. The second objective is to utilize the program for analyzing data captured by the MMS spacecraft.
“The methodology we demonstrated is mostly a proof of concept since we haven’t aggressively optimized it,” Bergstedt said. “We want to get the model working even better than it is now, start applying it to real data, and then we’ll just go from there!”
Journal reference:
- K. Bergstedt, H. Ji. A Novel Method to Train Classification Models for Structure Detection in In Situ Spacecraft Data. Earth and Space Science, 2024; DOI: 10.1029/2023EA002965