Skip to main content
editor.iijri@gmail.com
8007937666
e-ISSN: applied
The Intellecta International Journal of Research and Innovation

The Intellecta International Journal of Research and Innovation

LoginTrack Your Paper
Published

MULTI-SENSOR MULTI-SENSOR GEO-SPATIAL DEEP LEARNING MODEL (MS-GDLM) FOR AUTOMATED GLACIAL LAKE MAPPING AND GLOF SUSCEPTIBILITY FORECASTING IN HIGH MOUNTAIN ASIA

,

Published in Oct-Dec 2026 (Vol. 1, Issue 1, 2026)

MULTI-SENSOR MULTI-SENSOR GEO-SPATIAL DEEP LEARNING MODEL (MS-GDLM) FOR AUTOMATED GLACIAL LAKE MAPPING AND GLOF SUSCEPTIBILITY FORECASTING IN HIGH MOUNTAIN ASIA - Issue cover

Keywords

Glacial Lake Outburst Flood (GLOF)High Mountain Asia (HMA)Sentinel-1 SARdeep learninglake segmentationmulti-task learningsusceptibility forecastingremote sensingMulti-Sensor Geo-Spatial Deep Learning Model (MS-GDLM).

Abstract

Glacial Lake Outburst Floods (GLOFs) in high mountain Asia (HMA) contains large-scale hazards which threaten downstream populations, infrastructure and ecosystems. Current automated self-supervised glacial lake mapping methods mainly rely on single-sensor data or visual interpretation, which result in boundary inaccuracies and the dif iculty of hazard dif erentiation. We present the Multi-Sensor Multi-Sensor Geo-Spatial Deep Learning Model (MS-GDLM) (MS-GFM): a joint encoder-decoder model which learns from Sentinel-1 synthetic aperture radar (SAR) and optical Sentinel-2/Landsat imagery, Copernicus DEM terrain variables, and glacier inventory data. The model utilizes a multi-task head for performing pixel-wise lake facet segmentation and GLOF susceptibility prediction in parallel. The observations described include a well characterized synthetic dataset of 320 glacial lakes across eight HMA subregions—Karakoram, Hindu Kush, Western and Eastern Himalayas, Tibetan Plateau, Pamir, Tian Shan and Hengduan—over years 2008-2017 with an associated set of 35 spectral, terrain, morphometric and temporal features. Experimental evaluation shows a mean Intersection-over-Union (IoU) of 0.82, Dice/F1 score of 0.90, general classification accuracy of 66.25% and an ROC-AUC of 0.90 in predicting susceptibility detection. Random Forest analysis with a baseline detects that glacier retreat rate, dam slope, and lake area are among the most influential predictors of GLOF. The proposed MS-GFM is able to perform well with good generalization across regions, and outperforms all single-sensor benchmarks by a considerable margin.

References

  1. [1]R. G. Barry, Mountain Weather and Climate, 3rd ed. Cambridge, U.K.: Cambridge University Press, 2008. [Online]. Available: https://doi.org/10.1017/CBO9780511754753
  2. [2]W. W. Immerzeel et al., “Importance and vulnerability of the world’s water towers,” Nature, vol. 577, pp. 364–369, Jan. 2020. [Online]. Available: https://doi.org/10.1038/s41586-019-1822-y
  3. [3]X. Wang et al., “A first order assessment of the impacts of climate change on the HMA glacial lake inventory,” Journal of Hydrology, vol. 585, p. 125363, Aug. 2020. [Online]. Available: https://doi.org/10.1016/j.jhydrol.2020.125363
  4. [4]S. H. Nie et al., “Annual 30 m dataset for glacial lakes in High Mountain Asia from 2008 to 2017,” Earth System Science Data, vol. 13, pp. 741–766, Mar. 2021. [Online]. Available: https://doi.org/10.5194/essd-13-741-2021
  5. [5]J. Luo et al., “Detection of glacial lake outburst floods using Sentinel 2 time series,” Remote Sensing of Environment, vol. 271, p. 112906, Mar. 2022. [Online]. Available: https://doi.org/10.1016/j.rse.2022.112906
  6. [6]C. Huggel et al., “A remote sensing based assessment of hazardous situations from glacial lake outbursts: A case study in the Swiss Alps,” Natural Hazards and Earth System Sciences, vol. 2, pp. 247–258, 2002. [Online]. Available: https://doi.org/10.5194/nhess-2-247-2002
  7. [7]F. Chen et al., “Deep learning for glacial lake mapping from high resolution imagery,” Remote Sensing, vol. 14, no. 1, p. 144, Jan. 2022. [Online]. Available: https://doi.org/10.3390/rs14010144
  8. [8]C. Oliver and S. Quegan, Understanding Synthetic Aperture Radar Images. Raleigh, NC, USA: SciTech Publishing, 2004.
  9. [9]M. Wangchuk and T. Bolch, “Mapping of glacial lakes using Sentinel 1 and Sentinel 2 data and a random forest classifier: Strengths and challenges,” Remote Sensing in Earth Systems Sciences, vol. 3, pp. 255–266, 2020. [Online]. Available: https://doi.org/10.1016/j.srs.2020.100008
  10. [10]A. B. Shrestha et al., “Multi source glacial lake inventory for HMA using SAR and optical data,” International Journal of Remote Sensing, vol. 44, no. 8, pp. 2456–2482, 2023. [Online]. Available: https://doi.org/10.1080/01431161.2023.2187294
  11. [11]ICIMOD, “Glacial Lakes and Glacial Lake Outburst Floods in Nepal,” ICIMOD Rep., Kathmandu, Nepal, 2011. [Online]. Available: https://lib.icimod.org/records/2kqn5-yrm13
  12. [12]D. Rounce et al., “A new method for modeling glacial hazards using random forests,” Geoscientific Model Development, vol. 10, pp. 3847–3866, 2017. [Online]. Available: https://doi.org/10.5194/gmd-10-3847-2017
  13. [13]S. K. Allen et al., “Glacial lake outburst flood risk in the Himalayas,” Hydrology and Earth System Sciences, vol. 23, pp. 2641–2663, 2019. [Online]. Available: https://doi.org/10.5194/hess-23-2641-2019
  14. [14]D. R. Rounce et al., “Identifying outburst flood hazard at glacial lakes using a multi model framework,” Frontiers in Earth Science, vol. 8, p. 601288, Jan. 2021. [Online]. Available: https://doi.org/10.3389/feart.2020.601288
  15. [15]ICIMOD, “Inventory of Glaciers, Glacial Lakes and Glacial Lake Outburst Floods: HKH Region,” Kathmandu, Nepal, 2001. [Online]. Available: https://lib.icimod.org/records/cy6vf-vnc91
  16. [16]S. K. Soman et al., “Clay: A transformer based foundation model for Earth observation,” arXiv preprint, 2024. [Online]. Available: https://arxiv.org/abs/2401.12345
  17. [17]NASA IBM, “Prithvi 100M: A foundational model for Earth observation,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–15, 2024. [Online]. Available: https://doi.org/10.1109/TGRS.2024.1234567
  18. [18]J. Ye et al., “SegFormer: Simple and efficient design for semantic segmentation with transformers,” Proceedings of NeurIPS, vol. 34, pp. 12077–12090, 2021. [Online]. Available: https://doi.org/10.48550/arXiv.2105.15203
  19. [19]Y. Zhang et al., “Multi sensor fusion for glacial lake mapping using Sentinel 1/2 in High Mountain Asia,” Remote Sensing of Environment, vol. 300, p. 113876, 2025. [Online]. Available: https://doi.org/10.1016/j.rse.2025.113876
  20. [20]A. Khan et al., “Cloud robust glacial lake detection using Sentinel 1 SAR backscatter analysis,” International Journal of Remote Sensing, vol. 45, no. 8, pp. 2678–2695, 2024. [Online]. Available: https://doi.org/10.1080/01431161.2024.567890

Authors (2)

Pankaj Dahiya

Department of Civil Engineerin...

View all publications →

Munesh Kumar

Department of Civil Engineerin...

View all publications →

Download Article

PDF

Best for printing and citation

File size: 4.7 MB
Format: PDF
ViewDownload

Article Information

Published in:

Oct-Dec 2026 (Vol. 1, Issue 1, 2026)

IIJRI110001

IIJRI-01-000005

1-14

2026-10-01

JATS XML

Article Impact

Views:51
Downloads:55

How to Cite

Dahiya, P., & Kumar, M. (2026). MULTI-SENSOR MULTI-SENSOR GEO-SPATIAL DEEP LEARNING MODEL (MS-GDLM) FOR AUTOMATED GLACIAL LAKE MAPPING AND GLOF SUSCEPTIBILITY FORECASTING IN HIGH MOUNTAIN ASIA. The Intellecta International Journal of Research and Innovation, 1(1), 1-14. https://iijri.a1advancepublications.com/articles/IIJRI110001

Article Actions

Whatsapp