Lunar Sentinel: Computational Analysis of Lunar Surface Instabilities from Orbital Remote Sensing Data
DOI:
https://doi.org/10.63503/acset.978-81-995593-9-4.51Keywords:
Lunar Lander, Hazard detection, Deep Learning, -2 TMC Chandrayaan -2, Image Processing, Landing Safety Index.Abstract
Safe lunar landing requires quantitative assessment of the terrain of hazards such as steep slopes, shadowed regions and high crater density. This study presents an integrated multicriteria hazard modelling framework for lunar landing site evaluation using Chandrayaan-2 Terrain Mapping Camera-2 (TMC-2) imagery and corresponding Digital Elevation Model (DEM) data, combined with deep learning-based crater detection from LROC Narrow Angle Camera imagery. The terrain slope was derived from DEM gradients and was normalised using a min– max approach, while hillshade modelling was employed to identify persistent low-illumination zones. Crater instances were detected using a custom-trained YOLOv8 model trained and validated on 8521 annotated image samples, achieving a mean average precision (mAP@0.75) of 0.89 and an optimal F1 score of 0.87 at a confidence threshold of 0.45. The extracted hazard layers (slope, illumination mask and crater density surface) were integrated through a weighted multi-parameter fusion scheme to generate a continuous Landing Safety Index (LSI). The resulting LSI index classifies terrain into safe, moderate and high-risk zones, highlighting the steep craters and shadowed depressions as hazardous to rover landing. The given system shows the results of combining DEM-based terrain with a deep learning technique. This is used to identify the lunar hazard surface and also provides a structured methodology for future autonomous missions. The existing solution analysed crater detection, slope analysis and Illumination conditions separately. Whereas our approach combines all three components within a unified index, fulfilling the gaps in lunar hazard analysis.
References
[1] Schmidt, F., Schäfer, M., and Jahn, H., "Landsafe: landing site risk analysis software framework," ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XXXIX-B4, pp. 505–510, 2012. DOI: 10.5194/isprsarchives-XXXIX-B4-505-2012 Author. Title in Conference Name. Year of Conference. Conference Location: Publisher. DOI
[2] Wu, B., Li, F., Hu, H., Zhao, Y., Wang, Y., Xiao, P., Li, Y., Liu, W. C., Chen, L., Ge, X., and Oberst, J., "Topographic and geomorphological mapping and analysis of the Chang'E-4 landing site on the far side of the Moon," Photogrammetric Engineering and Remote Sensing, vol. 86, no. 4, pp. 247–258, 2020. DOI: 10.14358/PERS.86.4.247 7. Author, Title, in Book Title, Editor, Year, Publisher: Place Published|. p. Pages. DOI
[3] Dagar, A. K., Rajasekhar, R. P., and Nagori, R., "Analysis of boulder population around a young crater using very high-resolution image of OHRC on board Chandrayaan-2 mission," Icarus, vol. 386, art. no. 115168, 2022. DOI: 10.1016/j.icarus.2022.115168
[4] Zhao, J., et al., "Selection of Landing Sites for the Chang'E-7 Mission Using Multi-Source Remote Sensing Data," Remote Sensing, vol. 17, no. 7, art. no. 1121, 2025. DOI: 10.3390/rs17071121
[5] Amitabh, S., et al., "Comparative study of Chandrayaan-3 prime landing sites with heritage landing sites," in 55th Lunar and Planetary Science Conference, LPI Contribution No. 3040, Houston, TX, USA, Mar. 2024.
[6] Finco, G., "Assessment of a deep learning approach for autonomous lunar landing," M.S. thesis, Dept. of Aerospace Engineering, Politecnico di Milano, Milan, Italy, 2024. (Please verify and update with the correct institution/thesis type if different.)
[7] Scaioni, M., Yordanov, V., Brunetti, M. T., Melis, M. T., Zinzi, A., Kang, Z., and Giommi, P., "Recognition of landslides in lunar impact craters," European Journal of Remote Sensing, vol. 51, no. 1, pp. 47–61, 2018. DOI: 10.1080/22797254.2017.1401284
[8] Raju, G., et al., "Deep learning techniques for crater detection on lunar surface images from Chandrayaan-2 satellite," Journal of the Indian Society of Remote Sensing, 2024. DOI: 10.1007/s12524-024-01909-y (Volume and page numbers to be updated upon full publication.)
[9] Di, K., et al., "Landing Site Mapping and Lander Localisation for Chang'e-5 and Chang'e-6 Lunar Sample Return Missions," The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLVIII-G, pp. 383–388, 2025. DOI: 10.5194/isprs-archivesxlviii-g-2025-383-2025
[10] Lin, Y., et al., "Lunar Crater Detection on Digital Elevation Model: A Complete Workflow Using Deep Learning and Its Application," Remote Sensing, vol. 14, no. 3, art. no. 621, 2022. DOI: 10.3390/rs14030621
[11] Suresh, K., et al., "Computer Vision-Based Technique for Chandrayaan3 Lander Hazard Detection and Avoidance (HDA)," Journal of Aerospace Sciences and Technologies, vol. 76, no. 3, 2024. DOI: 10.61653/joast.v76i3a.2024.1005
[12] D. M. Mark, "Geographical information processing and applications," in Manual of Remote Sensing, vol. 1, 2nd ed., F. F. Sabins, Ed. Falls Church, VA, USA: American Society of Photogrammetry, 1987, pp. 631–711
[13] B. K. P. Horn, "Hill shading and the reflectance map," Proc. IEEE, vol. 69, no. 1, pp. 14–47, Jan. 1981
[14] T. R. Smith, J. H. Roberts, and P. Lee, "Terrain hazard assessment and illuminated landing zone analysis for planetary landing missions," Planet. Space Sci., vol. 89, pp. 1–13, Aug. 2013
[15] Halaas, D., et al., "Lunar Landing Site Hazard Assessment Approach," in AIAA SCITECH 2023 Forum, National Harbour, MD, USA, Jan. 2023. DOI: 10.2514/6.2023-1447
[16] Scorsoglio, A., et al., "Safe Lunar landing via images: A Reinforcement Meta-Learning application to autonomous hazard avoidance and landing," in AIAA SCITECH 2024 Forum, Orlando, FL, USA, Jan. 2024. (Please verify and add DOI if available.)
[17] Wen, T., et al., "ResGAT-F: a novel graph neural network-based approach for evaluating landing suitability in the lunar southern polar region," International Journal of Digital Earth, vol. 18, no. 1, 2025. DOI: 10.1080/17538947.2025.2547291
[18] La, H., et al., "LROC-PANGU-GAN: Closing the Simulation Gap in Learning Crater Segmentation with Planetary Simulators," arXiv preprint arXiv:2310.02781, 2023. DOI: 10.48550/arXiv.2310.02781
[19] Chen, M., et al., "Lunar Crater Detection Based on Terrain Analysis and Mathematical Morphology Methods Using Digital Elevation Models," IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 7, pp. 3681– 3692, 2018. DOI: 10.1109/TGRS.2018.2806371
[20] Sinha, M., Paul, S., Ghosh, M., Mohanty, S. N., and Pattanayak, R. M., "Automated Lunar Crater Identification with Chandrayaan-2 TMC-2 Images using Deep Convolutional Neural Networks," Scientific Reports, vol. 14, art. no. 8231, pp. 1–13, 2024. DOI: 10.1038/s41598-024-58438-4
[21] Wen, T., et al., "A New Robust Lunar Landing Selection Method Using the Bayesian Optimisation of Extreme Gradient Boosting Model (BOXGBoost)," Remote Sensing, vol. 16, no. 19, art. no. 3632, 2024. DOI: 10.3390/rs16193632
[22] Taşgın, U., et al., "Artificial Intelligence Assisted Crater Detection for Lunar Surface Landing and Terrain Relative Navigation," in 2024 International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Turkey, Sep. 2024. DOI: 10.1109/idap64064.2024.10710723
[23] Andolfo, S., et al., "Neural Network-Aided Optical Navigation for Precise Lunar Descent Operations," Aerospace, vol. 12, no. 3, art. no. 195, 2025. DOI: 10.3390/aerospace12030195
[24] Xiong, X., et al., "Deep Learning Detects Entire Multiple-Size Lunar Craters Driven by Elevation Data and Topographic Knowledge," Journal of Geodesy and Geoinformation Science, 2025. DOI: 10.1080/10095020.2025.2452932
[25] Jing, X., et al., "YOLOv8-LCNET: An Improved YOLOv8 Automatic Crater Detection Algorithm and Application in the Chang'e-6 Landing Area," Sensors, vol. 25, no. 1, art. no. 243, 2025. DOI: 10.3390/s25010243
[26] Chen, Y., et al., "The Identification of Impact Craters from GRAILAcquired Gravity Data by U-Net Architecture," Remote Sensing, vol. 14, no. 12, art. no. 2783, 2022. DOI: 10.3390/rs14122783
[27] Yu, H., et al., "Crater-MASN: A Multi-Scale Adaptive Semantic Network for Efficient Crater Detection," Remote Sensing, vol. 17, no. 18, art. no. 3139, 2025. DOI: 10.3390/rs17183139
[28] Yang, C., Zhao, H., Bruzzone, L., Benediktsson, J. A., Liang, Y., Liu, B., Zeng, X., Guan, R., Li, C., and Ouyang, Z., "Lunar impact crater identification and age estimation with Chang'E data by deep and transfer learning," Nature Communications, vol. 11, art. no. 6358, 2020.
[29] Seifamiri, H., Maghoul, P., Boudreault, R., and Jablonski, A. M., "Seismic evaluation of Apollo 17 landing site against moonquakes and meteorite impacts," in Proc. ANGSA Apollo 17 – Crustal Processes, 2022, abstract no. 2049
[30] Amitabh, S., Suresh, K., and Srinivasan, T. P., "Potential landing sites for Chandrayaan-2 lander in Southern Hemisphere of Moon," in 49th Lunar and Planetary Science Conference, LPI Contribution No. 2083, Houston, TX, USA, Mar. 2018.
[31] Nagori, R. R., Dagar, A. K., and Rudravaram, P. R., "Boulders distribution at the proposed SLIM landing site near Shioli crater," in 55th Lunar and Planetary Science Conference, Houston, TX, USA, Mar. 2024.
[32] Gaikwad, D. A., Shirpurkar, V., Todkar, N., Sutar, Z., Salunkhe, V., and Madane, V., "Advanced Crater and Boulder Detection in Lunar Exploration with CNN and YOLO," International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 9, no. 6, pp. 1–3, Jun. 2025.
[33] Rangarajan, A., Mahanti, S., and Krishnan, K., "Integrated terrain hazard indexing for autonomous lunar landing using multi-parameter surface analysis," Acta Astronautica, vol. 180, pp. 10–25, Mar. 2021.
[34] A. E. Johnson, J. F. Montgomery, and L. H. Matthies, "Vision guided landing of an autonomous helicopter in hazardous terrain," in Proc. IEEE International Conference on Robotics and Automation (ICRA), Barcelona, Spain, Apr. 2005, pp. 3966–3971.
[35] M. Ono, B. Rothrock, and A. Ansar, "Vision-based hazard detection for autonomous safe landing," in Proc. IEEE Aerospace Conference, Big Sky, MT, USA, Mar. 2013.
[36] Golombek, M., Grant, J., Parker, T., Greeley, R., et al., "Selection of the Mars Science Laboratory landing site," Space Science Reviews, vol. 170, no. 1–4, pp. 641–737, 2012.
