Gravitational Lens Detection in Simulated LSST Data: A Comprehensive Feature Extraction Approach

Document Type : Research Paper

Authors

Department of Physics, University of Guilan, 41335-1914, Rasht, Iran

10.22128/ijaa.2026.3309.1246

Abstract

Identifying strong gravitational lensing systems is a major challenge in modern astronomical surveys. This research presents a machine learning-based method to distinguish lensed objects from non-lensed objects using multiband data.
To this end, a comprehensive set of physically interpretable features is extracted from simulated data across the g, r, i, and z bands. These features capture statistical, spatial, amplitude, and frequency information. Then, using the XGBoost algorithm, we identify the features that have the greatest impact on the classification process. The model used in this study primarily relies on indicators of structural complexity (such as spread, entropy, and kurtosis) and asymmetry (such as skewness), especially in the g band. Our analysis shows that the proposed model achieves strong performance, with an accuracy of 0.88 and a TSS score of 0.75. Additionally, the Area Under the Curve (AUC) of 0.94 demonstrates the model's high ability to distinguish between gravitational lenses and non-lensed systems. Overall, the proposed framework can provide a reliable approach for identifying gravitational lens candidates.

Keywords

References

[1] Meylan, G., & et al. 2006, Gravitational Lensing: Strong, Weak and Micro. astro-ph.
[2] Walsh, D., Carswell, R. F., & et al. 1979, Nature, 279, 381.
[3] Treu, T., Koopmans, L. V. E. 2002, ApJ, 575, 87.
[4] Treu, T., Koopmans, L. V. E. 2003, MNRAS, 343, L29.
[5] Treu, T., Koopmans, L. V. E. 2004, ApJ, 611, 739.
[6] Mao, S., Schneider, P. 1998, MNRAS, 295, 587.
[7] Metcalf, R. B., Madau, P. 2001, ApJ,563, 9.
[8] Vegetti, S., Lagattuta, D. J., & et al. 2012, Nature, 481, 341.
[9] Refsdal, S., 1964b, MNRAS, 128, 307.
[10] Vuissoz, C., & et al., 2007, A&A , 464, 845.
[11] Kochanek, C. S., Schechter, P. L., 2004, Measuring and Modeling the Universe. Cambridge Univ. Press, Cambridge, p. 117.
[12] Suyu, S. H. & et al., 2014, ApJ, 788, L35.
[13] Goobar, A. & et al., 2016, Science, 356, 291.
[14] Bonvin, V., & et al., 2017, MNRAS, 465, 4914.
[15] Wong, K. C., & et al., 2020, MNRAS, 498, 1420.
[16] Claeskens, J.F., Sluse, D., & et al., 2006, A&A, 451, 865.
[17] Jackson, N., 2011, ApJ, 739, L28.
[18] Jackson, N., & et al., 2015, MNRAS, 454, 287.
[19] Zwicky, F., 1937, Phys. Rev, 51, 679.
[20] Alard, C., 2006, arXiv e-prints, astro–ph/0606757.
[21] Faure, C., & et al., 2008, ApJS, 176, 19.
[22] James, E., Gunn., & et al., 2006, AJ, 131, 2332.
[23] Williams, R., E., & et al., 1996, AJ, 112, 1335.
[24] Williams, R., E., & et al., 2000, AJ, 120, 2735.
[25] Koekemoer, A., & et al., 2007, ApJS, 172, 196.
[26] Tyson, J., Anthony., 2002, arXiv, astro-ph/0302102.
[27] Mohammed, M., & et al.,2016, Machine learning: algorithms and applications, CRC Press.
[28] Seidel, G., Bartelmann, M., 2007, A&A, 472, 341.
[29] Gavazzi, R., Marshall, P. J., & et al., 2014, ApJ, 785, 144.
[30] Lenzen, F., Schindler, S., Scherzer, O., 2004, A&A, 416, 391.
[31] More, A., Cabanac, R., More, S., & et al., 2012, ApJ, 749, 38.
[32] Petrillo, C., Tortora, C., Chatterjee, S., & et al., 2017, MNRAS, 472, 1129.
[33] Pearson, J., Pennock, C., Robinson, T., 2018, Emerg Sci, 2:1.
[34] Petrillo, C., Tortora, C., Vernardos, G., & et al., 2019, MNRAS, 484, 3879.
[35] Petrillo, C., Tortora, C., Chatterjee, S., & et al., 2019, MNRAS, 482, 807.
[36] Can˜ameras, R., Schuldt, S., Suyu, S., & et al., 2020, A&A, 644, 163.
[37] Savary, E., Rojas, K., Maus, M., & et al., 2022, A&A, 666, 1.
[38] Morgan, R., Nord, B., Bechtol, K., & et al., 2022, ApJ, 927, 109.
[39] Morgan, R., Nord, B., Bechtol, K., & et al., 2022, arXiv:2204.05924.
[40] Kodi Ramanah, D., Arendse, N., Wojtak, R., 2022, MNRAS, 512, 5404.
[41] PinciroliVagoN, O., Fraternali, P., 2023, Neural Comput. Appl., 35, 19253.
[42] Marshall, P. J., Hogg, D. W., Moustakas, L. A., & et al., 2009, ApJ, 694, 924.
[43] Khramtsov, V., Sergeyev, A., Spiniello, C., & et al., 2019, A&A, 632, 56.
[44] Chen, T., He, T., & et al., 2015, R package version 0.4-2, 1, 1.
[45] Morgan, R., Nord, B., & et al., 2021, J. Open Source Softw., 6, 2854.
[46] Birrer, S., Amara, A., 2018, Phys. Dark Univ., 22, 189.
[47] Stalder, B., & et al., 2020, Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, 11447.
[48] Fawcett, T., 2006, P. R. L., 27, 861.
[49] Raboonik, A., & et al., 2017, ApJ., 834, 11.
[50] Alipour, N., & et al., 2019, ApJS., 243, 20.
[51] Ghader, H., & et al., 2025, ApJS., 277, 10.
[52] Hassani, Z., & et al., 2025, ApJS., 279, 27.
[53] Hassani, Z., & et al., 2026, The J. Supercomputing, 82, 326. 
Iranian Journal of Astronomy and Astrophysics
Volume 12, Issue 4
January 2026
Pages 347-357

Files

Share

How to cite

Statistics