Debate
Large Language Models for Plasma Research - Curse or Blessing?
Large language models (LLM) such as ChatGPT and others may change the way we do research. These systems serve as a tool for literature searches, data analysis and performing programming tasks. But what are the potentials of LLMs and their shortcomings, especially regarding the very interdisciplinary plasma research?
The advent of large language models (LLM) such as ChatGPT and others will change the way we gather, process and present scientific findings. LLMs are based on collecting information from the internet and composing answers based on the likelihood of succession of words. Thereby, the most common statements and phrases are amplified, hoping these common information pieces are correct. This might, however, not necessarily be true, and the amplification of wrong statements may distort any thorough assessment and analysis of a topic. This is referred to as the hallucination of LLMs [1]. The ease of gathering information and creating answers in a very readable form is a blessing; amplifying wrong statements is a curse. Some publishers have already discussed this in the community and are addressing it [1-5]. But what are the potentials of LLMs and their shortcomings, especially regarding plasma research?
LLMs exhibit several advantages. (i) LLMs will change how we gather information because AI will condense information and filter out the most relevant information from the internet very efficiently, being judged by its popularity. This is very helpful for many well-defined tasks. These LLMs will presumably replace the current search engine approach for information gathering. Since plasma research is very interdisciplinary and the information is dispersed over many journals and conferences, using automated literature searches by LLMs can help. (ii) LLMs may accelerate data analysis by providing analysis concepts for filtering and fitting data with the most up-to-date algorithms. (iii) Simple programming tasks can be completed very quickly without the need to collect many different code snippets from the Internet. Usually, one or two attempts with an LLM are enough to have at least a starting version of a program if the task is not too elaborate. (iv) LLMs can generate at least a starting point for further research for most scientific topics. This is not too different from conventional research based on libraries, journal editions, or simply using a search engine. Using LLMs is much more comfortable. (v) LLMs help write scientific texts and produce highly readable output. This is their core expertise.
However, LLMs also exhibit challenges and shortcomings in doing plasma research. Doing a literature search and collecting information on a topic on the web by the LLM will not account for any accumulation or repetition of wrong statements and findings. In some cases, references given by LLMs to support arguments are wrong. The answers of an LLM may also depend on the person who is asking which will generate different outcomes for a specific scientific question. If one asks an LLM to explain very known facts, it could be correct, but it may also oversimplify things. In some cases, the explanations of LLMs are plainly incorrect. This hallucination of LLMs can be an obstacle, especially in plasma research, where the community is interdisciplinary and somewhat smaller compared to other fields. Consequently, only a few papers usually deal with a particular process or application, so the knowledge base for a specific topic is small and the statements these LLMs produce may not be robust. In that sense, the duty of any scientist to use several sources such as journal articles, textbooks, or discussions with colleagues before assessing any information is still the most important.
At the core of research is understanding fundamental principles and generating new insights or hypotheses. It is unclear whether LLMs can help here. For example, when comparing two plasma sources for a specific task, the LLM may recommend different combinations or operation parameters. However, a deep insight into the mechanisms may conclude that an entirely different discharge concept might be better suited. Commonly, statements are generated that one plasma method (such as DBD plasmas) is better than others (for example, microwave) or that “plasma” does not “work” for a particular application. The complexity of the addressed systems in plasma research is so significant that these simple answers are useless if they are not put into proper context. Since plasma research is also performed by scientists with training in other fields (such as chemical engineering, solid-state physics, etc.), these too-simple statements might not be questioned.
Finally, LLMs pose challenges for scientific journals. If one asks an LLM to explain a result or recommend a study, it necessarily collects information already published elsewhere. If the authors repeat that, they automatically repeat the research of others. This poses a challenge since LLMs allow us to quickly produce “nice” papers that only reproduce known information. This will blow up the number of published papers and dilute the “real” information going forward.
At present, there is a tendency to make it obligatory for transparency reasons to inform the reader that AI is being used to generate a manuscript or in the interpretation of a result (the authors, however, still bear full responsibility for the paper [3]). This may not be conclusive since using standard data visualisation or analysis tools and spelling software is already common without the need to be referenced. LLMs could be just another tool on that list since verification by the scientist will always be required.
In the end, it will be interesting to see how the scientific community integrates LLMs into the daily workflow. This transition is happening, but the input and guidance of critical scientists will always be necessary.
[1] ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope, Partha Pratim Ray, Internet of Things and Cyber-Physical Systems, 3, 121-154, (2023)
[2] ChatGPT: five priorities for research Eva A. M. van Dis, Johan Bollen, Robert van Rooij, Willem Zuidema & Claudi L. Bockting, Nature 614, 224 (2023)
[3] ChatGPT is fun, but not an author, H. HOLDEN THORP Authors Info & Affiliations, SCIENCE 379, 313 (2023)
[4] Exploring the potential of using ChatGPT in physics education, Yicong Liang, Di Zou, Haoran Xie & Fu Lee Wang, Smart Learning Environments 10, 52 (2023)
[5] After enabling AI it is time for the plasma community to benefit from AI – Personal view in a short perspective article, E. Kessels, Atomic Limits Blog, PMP Group TU Eindhoven, 7.5.2023
Publications
Paper on the cover of "Plasma Processes und Polymers"
The paper by Eloise Mestre, Inna Orel, Daniel Henze, Laura Chauvet, Sebastian Burhenn, Sebastien Dozias, Fabienne Brule-Morabito, Judith Golda and Claire Douat made it onto the cover of the renowned journal Plasma Processes and Polymers. This covers the interdisciplinary field of low-temperature plasma science. Congratulations to the authors!
Outgoing research stay
Laboratory stay in the USA
As part of his PhD, PhD student David Steuer (project A6) is spending nine weeks at the Sandia Plasma Research Facility (PRF) in Albuquerque, New Mexico, USA. Researchers can apply at PRF to submit project ideas. After a successful review process, there is then the option of using one of the excellently equipped laboratories or handing over the experiment to the cooperation partner.
The PRF also offers simulation capacities. In David's project, atomic oxygen densities are to be measured within a microcavity plasma array. A state-of-the-art picosecond laser system from the PRF can be used for this purpose.
The stay was funded by the Research School of the Ruhr-Universität Bochum (PRINT programme) and the CRC 1316.
Scientific exchange
Visit of Prof. Renato Montagnolli
Prof. Renato Montagnolli, a researcher from São Paulo State University, enriched our Collaborative Research Center with his visit from March 8th to March 19th. Professor Montagnolli's visit was made possible by a Research School Travel Grant, and co-funded by the Collaborative Research Center 1316. The main focus of his trip was to plan a joint project aimed at developing "green" pathways of protein immobilization for our plasma-driven biocatalysis.
During his stay, we had the opportunity to present our biocatalysis setup to Professor Montagnolli and demonstrate the whole process from protein purification to protein application under plasma. This interaction allowed us to jointly plan and refine important steps for the effective implementation of our project.
Another aim of his visit was to promote collaboration with future scientists. For this reason, we also targeted Bachelor students to raise awareness of the opportunities within the CRC. The SFB funding offers the chance for one person to go to Brazil for several months to test the various immobilization techniques and bring a fruitful exchange between the Research Centers.
Pupil's project week
Eventful project week full of physics and research
This year's schoolgirl project week took place at the RUB from March 25 to 28.
In addition to exciting workshops and experiments, the schoolgirls attended a lecture by Dr. Niklas Fornefeld on the topic of "Thermal radiation 'Is light light?' - From sunburn to trash TV", experienced current research at the RUB in laboratory tours and traveled through the vastness of space in the Zeiss Planetarium Bochum.
The highlights also included having breakfast together, lunch in the canteen and experiencing university life. This also served as an opportunity for exchange between the participants and the students.
The final event was the fiercely contested physics duel and the award ceremony for the winners. Everyone was then rewarded with a well-earned pizza!
Publication
Top 2 Ranking of the most read papers!
The paper entitled "Comparison of the performance of a microwave plasma torch and a gliding arc plasma for hydrogen production via methane pyrolysis" was recently published in the renowned journal "Plasma Processes and Polymers" and immediately achieved remarkable recognition and was downloaded the second most times in 2023. Simon Kreuznacht, Marc Böke and Achim von Keudell, among others, contributed to the paper. It deals with hydrogen production using plasma-heated methane pyrolysis in a microwave plasma torch (MPT) and a gliding arc plasmatron (GAP). The methane conversion, the product spectrum, the energy efficiency and the solid carbon particles produced were investigated.
The second-place ranking of the most-read papers is clear proof of the relevance and influence of this research on the professional community.
Congratulations to the authors!
Award
Hall of Fame Prize for Uwe Czarnetzki
The 4th Plasma Materials Science Hall of Fame Prize was awarded to Prof. Uwe Czarnetzki, Ruhr University Bochum for the excellent achievements in many years of outstanding research on physical analysis of phenomena related to low-temperature plasma materials processing, and proposals for original plasma processing equipment, which are expected to lead to advanced future plasma processing techniques.
MGK Colloquium 2024
Renewed exchange between young researchers at the MGK Colloquium
The MGK Colloquium 2024 of the CRC1316 took place from February 21 to 23 in Heidelberg. The colloquium is intended as a casual meeting where the young researchers of the CRC1316 can come together and exchange their knowledge.
The meeting began with a guided tour through Heidelberg Castle. During the 90-minute tour, the participants learned a lot about the history of Heidelberg and the castle. On Thursday and Friday, the scientific part took place at the DJH Jugendherberge Heidelberg. Each student presented their progress in project presentations and two poster sessions.
An invited speaker from the "Laboratoire de Physique des Plasmas" in Palaiseau, France, gave a scientific lecture on CO2 conversion. In addition, speakers from large companies such as the Hartmann Group, ASML and Zeiss, as well as from a start-up company, Lidrotec, were invited to present their companies and explain how they got to their current positions after completing their PhD. Overall, the MGK Colloquium was a very successful conference and fostered exchange and communication between the young researchers of CRC1316.
Plasma physics at Bo.Ing 2024
Pupils learn about the world of plasmas through the Bo.Ing
On 20th February the BO.Ing, a study orientation day for engineering studies, took place. High school students attended a lecture, were guided through laboratories, and could participate in exciting workshops such as plasma physics. The high school students learned a lot about plasmas and their applications. They coated samples using the sputter coater and analysed the properties of the produced gold layers.