USING ARTIFICIAL INTELLIGENCE FOR SELECTION OF ANALYTICAL REAGENTS, EXEMPLIFIED BY DETERMINATION OF IRON CONTENT IN WATER SAMPLES
DOI:
https://doi.org/10.20535/2218-930032025348572Keywords:
artificial intelligence, ChatGPT-4o mini, chromogenic compounds, iron detection, reagents selectionAbstract
Currently, education and science in Ukraine are facing many new challenges, including war. These challenges determine new priority areas of science and technology development, which in turn affects scientists and students of higher education institutions. The significant pollution of natural resources (marine environment, surface waters and soils) caused by active military operations is the reason for the emergence of many new research projects Students of higher education institutions, especially chemical, environmental, and technical majors, often face the problem of choosing the analysis methods they will use in the experimental part of their coursework or thesis. Also students often engage in scientific research, sometimes even within the framework of various projects, including those related to monitoring the marine environment of Ukraine. Traditionally, the selection process is accompanied by a lengthy and laborious literature search. But in recent years, the rapid development of artificial intelligence has made it possible to significantly simplify this process. The article is devoted to studying the relevance of information that ChatGPT-4o mini provided in response to different formulations of prompts. The search concerned the selection of analytical reagents for determining the iron content in water samples. By improving the prompts step by step, recommendations for reagents for simultaneous determining of Fe(II) and Fe(III) in water was received from ChatGPT-4o mini. The prompts were gradually made more complicated by introducing limitations on application and reaction conditions. It was found that currently ChatGPT-4o mini did not always effectively cope with the selection of reagents, but it can somewhat simplify the literature search. However, it's possible that future versions of ChatGPT will feature a more efficient reagent selection process.
References
Alshami, A.; Elsayed, M.; Ali, E.; Eltoukhy, A. E. E.; Zayed, T. Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions. Systems 2023, 11 (7), 351. https://doi.org/10.3390/systems11070351.
Bayer, H.; Araci, F. G. I.; Gurkan, G. ChatGPT-4o, ChatGPT-4 and Google Gemini are compared with Students: A Study in Higher Education. International Journal of Technology in Education and Science 2024, 8 (4), 627–644. https://doi.org/10.46328/ijtes.585.
Bolaños, F.; Salatino, A.; Osborne, F.; Motta, E. Artificial intelligence for literature reviews: opportunities and challenges. Artificial Intelligence Review 2024, 57 (10). https://doi.org/10.1007/s10462-024-10902-3.
Komadel, P.; Stucki, J. W. Quantitative assay of minerals for FE2+ and FE3+ using 1,10-Phenanthroline: III. a rapid photochemical method. Clays and Clay Minerals 1988, 36 (4), 379–381. https://doi.org/10.1346/ccmn.1988.0360415.
Kyrii, S.; Litynska, M.; Misevych, A. The War Impact on Ukraine’s Marine Environment. Water&Water Purification Technologies. Scientific and Technical News 2024, 38 (1), 50–64. https://doi.org/10.20535/2218-930012024316112.
Laboratory Work No. 2. Determination of Total Iron Content in Natural Water Samples and Iron Extraction by Aeration. Methodological Recommendations for Performing Laboratory Work in the Discipline "Technology and Equipment for Obtaining Drinking and Technical Water"; Igor Sikorsky Kyiv Polytechnic Institute: Kyiv, Ukraine, 2015. https://ela.kpi.ua/handle/123456789/12609 (accessed 2024-12-28).
Litynska, M.; Pelekhata. O. The influence of the war on the content of some components in the rivers of Ukraine. IOP Conference Series: Earth and Environmental Science 2024, 1415, 012094. https://doi.org/10.1088/1755-1315/1415/1/012094
Ma, J.; Wu, X.; Huang, L. The use of artificial intelligence in literature search and selection of the PubMed database. Scientific Programming 2022, 2022, 1–9. https://doi.org/10.1155/2022/8855307.
Mostafapour, M.; Fortier, J. H.; Pacheco, K.; Murray, H.; Garber, G. Evaluating Literature reviews conducted by Humans versus ChATGPT: Comparative study. JMIR AI 2024, 3, e56537. https://doi.org/10.2196/56537.
O’Leary, D. E. Do ChatGPT 4o, 4, and 3.5 generate “Similar” ratings? Findings and implications. IEEE Intelligent Systems 2024, 39 (5), 78–81. https://doi.org/10.1109/mis.2024.3441136.
OpenAI. GPT-4o mini: Advancing Cost-Efficient Intelligence. https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/ (accessed 2025-01-28).
OpenAI. ChatGPT-4o mini; OpenAI: San Francisco, CA, 2024a. https://chatgpt.com/ (accessed 2025-01-28).
Parisi, V.; Sutton, A. The role of ChatGPT in developing systematic literature searches: an evidence summary. Journal of EAHIL 2024, 20 (2), 30–34. https://doi.org/10.32384/jeahil20623.
Salvadó, V.; Ribas, X.; Valiente, M. The Chemistry of Iron in Biosystems. IV. Complex Formation Between Iron(III) and 5-Sulphosalicylic Acid, in Aqueous Solution. Polyhedron 1990, 9 (22), 2675–2679.
Wagner, G.; Lukyanenko, R.; Paré, G. Artificial intelligence and the conduct of literature reviews. Journal of Information Technology 2021, 37 (2), 209–226. https://doi.org/10.1177/02683962211048201.
Wang, S.; Scells, H.; Zuccon, G.; Koopman, B. Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search? In SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval; Association for Computing Machinery: New York, 2023; pp 1426–1436.
Yang, W.; Chen, Z.; Li, H. Simple and selective colorimetric detection of oxytetracycline based on FE(III) Ion-3,3’,5,5’-Tetramethylbenzidine. Materials Sciences and Applications 2018, 09 (13), 1057–1065. https://doi.org/10.4236/msa.2018.913076.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Litynska M.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The ownership of copyright remains with the Authors.
Authors may use their own material in other publications provided that the Journal is acknowledged as the original place of publication and National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” as the Publisher.
Authors are reminded that it is their responsibility to comply with copyright laws. It is essential to ensure that no part of the text or illustrations have appeared or are due to appear in other publications, without prior permission from the copyright holder.
WPT articles are published under Creative Commons licence:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY-NC 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. The use of the material for commercial purposes is not permitted.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
