Implementation of Deep Learning to Improve Students' Physics Learning Outcomes: A Systematic Literature Review

Anasya Astiananda Isdayanti; Khusaini Khusaini; Ahmad Taufiq

doi:10.20527/bipf.v13i3.22757

Implementation of Deep Learning to Improve Students' Physics Learning Outcomes: A Systematic Literature Review

Anasya Astiananda Isdayanti, Khusaini Khusaini, Ahmad Taufiq

Abstract

Deep learning models have been increasingly adopted in education, including the humanities, arts, technology, and natural sciences. In physics education, deep learning offers promising opportunities to enhance students’ learning outcomes. This study aims to systematically review research on the application of deep learning models in physics learning. Using the Systematic Literature Review (SLR) method, the research followed several steps: formulating research questions, defining selection criteria, designing a search strategy, selecting studies, assessing quality, and synthesizing results. Of the 360 identified articles, 11 met the eligibility criteria and were most relevant to the research focus. The review reveals that various models, such as Physics Deep Learning, ChatGPT, Deep Lagrangian Networks (DeLaN), smart virtual assistants, Fusing Dual Sampling Convolutional Neural Networks (FDS-MPI), Artificial Intelligence (AI), object detection algorithms, and Deep Neural Networks (DNN)—have been applied to topics including general physics, electronic physics, density and energy, wave propagation, and fluid dynamics. The findings suggest that deep learning improves students’ physics learning outcomes and provides implications for practice and research. This study is limited to the scope of selected articles and does not include direct classroom experimentation, which future research should address.

Keywords

Deep learning; Physics learning; SLR

Full Text:

PDF

References

Afwa, L. I., & Latifah, E. (2016). Deep learning question untuk meningkatkan pemahaman konsep fisika. Jurnal Pendidikan , 2013, 434–447.

Ahmad, T. (2020). Scenario based approach to re-imagining future of higher education which prepares students for the future of work. Higher Education, Skills and Work-Based Learning, 10(1), 217-238.

Akmal, A. N., Maelasari, N., Ilmu, T., & Islam, P. (2025). Pemahaman deep learning dalam pendidikan: analisis literatur melalui metode systematic literature review (slr). JIIP-Jurnal Ilmiah Ilmu Pendidikan, 8(3), 3229-3236.

Ali, M. R. M., Putri, N. E., & Kuswanto, H. (2023). Tinjauan literatur sistematis: Perkembangan penggunaan teknologi augmented reality (ar) pada pembelajaran fisika. Jurnal Pendidikan Mipa, 13(4), 1045–1055. https://doi.org/10.37630/jpm.v13i4.1277

Aryanto, Pratama, M. H., & Putri, N. U. (2023). Increasing the effectiveness of electronic physics learning by utilizing extended reality and smart virtual technology assistant as interactive media. 2023 International Conference on Networking, Electrical Engineering, Computer Science, and Technology (IConNECT), 127–131. https://doi.org/10.1109/IConNECT56593.2023.10326769

Chang, C.-W., Gao, Y., Wang, T., Lei, Y., Wang, Q., Pan, S., Sudhyadhom, A., Bradley, J. D., Liu, T., Lin, L., Zhou, J., & Yang, X. (2022). Dual-energy CT based mass density and relative stopping power estimation for proton therapy using physics-informed deep learning. Physics in Medicine & Biology, 67(11), 115010. https://doi.org/10.1088/1361-6560/ac6ebc

Chusni, M. M. (2022). A systematic review of adaptive learning research in physics education in Indonesia. Jurnal Pendidikan Sains, 10(2), 53–62.

Davis, F. D. (2019). Deep learning and constructivism in education. Academic Press.

Ding, L., Li, T., Jiang, S., & Gapud, A. (2023). Students’ perceptions of using ChatGPT in a physics class as a virtual tutor. International Journal of Educational Technology in Higher Education, 20(1), 1–18. https://doi.org/10.1186/s41239-023-00434-1

Edalatifar, M., Tavakoli, M. B., Ghalambaz, M., & Setoudeh, F. (2021). Using deep learning to learn physics of conduction heat transfer. Journal of Thermal Analysis and Calorimetry, 146(3), 1435–1452. https://doi.org/10.1007/s10973-020-09875-6

Elbashbishy, M. E. (2024). Deep learning in education. Sustainability Education Globe, 2(1), 15–21. https://doi.org/10.21608/seg.2024.269380.1000

Fadillah, M. A. (2024). Exploring user perceptions : The impact of ChatGPT on high school students ’ physics understanding and learning. 4(2), 1197–1207. https://doi.org/10.25082/AMLER.2024.02.013

Harris, C. J., Krajcik, J. S., Pellegrino, J. W., & DeBarger, A. H. (2019). Designing knowledge-in-use assessments to promote deeper learning. Educational Measurement: Issues and Practice, 38(2), 53–67. https://doi.org/10.1111/emip.12253

Hudha, M. N., Aji, S., & Rismawati, A. (2017). Pengembangan modul pembelajaran fisika berbasis problem based learning untuk meningkatkan kemampuan pemecahan masalah fisika. SEJ (Science Education Journal), 1(1), 36–51. https://doi.org/10.21070/sej.v1i1.830

Jiang, R. (2022). Understanding, Investigating, and promoting deep learning in language education: A survey on chinese college students' deep learning in the online EFL teaching context. Frontiers in Psychology, 13, 955565.

Jin, X., Laima, S., & Li, H. (2021). Physics-enhanced deep learning methods for modelling and simulating flow fields. Lixue Xuebao/Chinese Journal of Theoretical and Applied Mechanics, 53(10), 2616–2629. https://doi.org/10.6052/0459-1879-21-373

Liu, W., Wang, H., Xi, Z., Zhang, R., & Huang, X. (2022). Physics-driven deep learning inversion with application to magnetotelluric. Remote Sensing, 14(13). https://doi.org/10.3390/rs14133218

Luo, J., Ye, J., Shan, L., & He, Q. (2021). Research on object detection algorithm based on deep learning for mobile Terminal. Journal of Physics: Conference Series, 2083(3). https://doi.org/10.1088/1742-6596/2083/3/032019

Lutter, M., & Peters, J. (2023). Combining physics and deep learning to learn continuous-time dynamics models. International Journal of Robotics Research, 42(3), 83–107. https://doi.org/https://doi.org/10.1177/02783649231169492

Nisa, L. C., Sulistyaningsih, D., & Purnomo, E. A. (2025). Sistematic literatur review: Kecemasan matematika siswa terhadap kemampuan berpikir kritis. JIIP-Jurnal Ilmiah Ilmu Pendidikan, 8(4), 4249-4257.

Otto, S., Franziska Korner, Marschke, B., J., M. M., Brands, S., Sotiriuo, S., & Bogner, F. X. (2020). Deeper learning as integrated knowledge and fascination for Science. International Journal of Science Education, 42(5), 807–834.

Shafiq, M., Sami, M. A., Bano, N., Bano, R., & Rashid, M. (2025). Artificial intelligence in physics education: Transforming learning from primary to university level. Indus Journal of Social Sciences, 3(1), 717-733.

Shang, Y., Liu, J., Zhang, L., Wu, X., Zhang, P., Yin, L., Hui, H., & Tian, J. (2022). Deep learning for improving the spatial resolution of magnetic particle imaging. Physics in Medicine and Biology, 67(12). https://doi.org/10.1088/1361-6560/ac6e24

Suciati, I. (2022). Implementasi higher order thinking skills terhadap kemampuan berpikir kritis peserta didik dalam pembelajaran. Koordinat Jurnal MIPA, 3(1), 7–16. https://doi.org/10.24239/koordinat.v3i1.32

Weng, C., Chen, C., & Ai, X. (2023). A pedagogical study on promoting students' deep learning through design-based learning. International journal of technology and design education, 33(4), 1653-1674.

Winter, J. de, & Airey, J. (2022). Pre-service physics teachers ’ developing views. Pre-Service Physics Teachers’ Developing Views on the Role of Mathematics in the Teaching and Learning of Physics, 57(6), 13.

Zawacki-Richter, O., Kerres, M., Bedenlier, S., Bond, M., & Buntins, K. (2019). Systematic reviews in educational research: Methodology, perspectives and application (p. 161). Springer Nature.

DOI: http://dx.doi.org/10.20527/bipf.v13i3.22757