Comparison of Deep Learning approaches in classification of glacial landforms

• Autorzy: Nadachowski Paweł , Łubniewski Zbigniew , Trzcińska Karolina , Tęgowski Jarosław

Identyfikatory

DOI

10.24425/ijet.2024.152066

• Języki publikacji: EN

Abstrakty

EN

Glacial landforms, created by the continuous movements of glaciers over millennia, are crucial topics in geomorphological research. Their systematic analysis affords invaluable insights into past climatic oscillations and augments understanding of long-term climate change dynamics. The classification of these types of terrain traditionally depends on labor-intensive manual or semi-automated methods. However, the emergence of automated techniques driven by deep learning and neural networks holds promise for enhancing efficiency of terrain classification workflows. This study evaluated the effectiveness of Convolutional Neural Network (CNN) architectures, particularly Residual Neural Network (ResNet) and VGG in comparison with Vision Transformer (ViT) architecture in the glacial landform classification task. By using preprocessed input data from Digital Elevation Model (DEM) which covers regions such as the Lubawa Upland and Gardno-Leba Plain in Poland, as well as the Elise Glacier in Svalbard, Norway, comprehensive assessments of those methods were conducted. The final results highlight the unique ability of deep learning methods to accurately classify glacial landforms. Classification process presented in this study can be the efficient, repeatable and fast solution for automatic terrain classification.

Słowa kluczowe

EN

Convolutional Neural Network; CNN; deep learning; Digital Elevation Model; DEM; Elise glacier; Gardno-Leba Plain; glacial landforms; ResNet; supervised classification; Svalbard; VGG; ViT; residual neural network; Lubawa Upland; vision transformer

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2024
• Tom: Vol. 70, No. 4
• Strony: 823--829
• Opis fizyczny: Bibliogr. 30 poz., rys., tab.

Twórcy

autor

Nadachowski Paweł

• Gdańsk University of Technology

autor

Łubniewski Zbigniew

• Gdańsk University of Technology

autor

Trzcińska Karolina

• University of Gdansk

autor

Tęgowski Jarosław

• University of Gdansk

Bibliografia

• [1] V. H. Brown, C. R. Stokes, and C. O’Cofaigh, “The glacial geomorphology of the north-west sector of the Laurentide ice sheet”, J. Maps, vol. 7, no. 1, pp. 409-428, 2011.
• [2] B. M. P. Chandler et al., “Glacial geomorphological mapping: A review of approaches and frameworks for best practice”, Earth-Sci. Rev., vol. 185, pp. 806-846, 2018.
• [3] P. Dunlop, R. Shannon, M. McCabe, R. Quinn, and E. Doyle, “Marine geophysical evidence for ice sheet extension and recession on the Malin shelf: New evidence for the western limits of the British Irish ice sheet”, Mar. Geol., vol. 276, nos. 1-4, pp. 86-99, Oct. 2010.
• [4] L. R. Bjarnadóttir, M. C. M. Winsborrow, and K. Andreassen, “Deglaciation of the central Barents Sea”, Quaternary Sci. Rev., vol. 92, pp. 208-226, 2014.
• [5] J. M. Bendle, V. R. Thorndycraft, and A. P. Palmer, “The glacial geomorphology of the Lago Buenos Aires and Lago Pueyrredón ice lobes of central Patagonia”, J. Maps, vol. 13, no. 2, pp. 654-673, 2017.
• [6] M. Eckerstorfer, H. Ø. Eriksen, L. Rouyet, H. H. Christiansen, T. R. Lauknes, and L. H. Blikra, “Comparison of geomorphological field mapping and 2D-InSAR mapping of periglacial landscape activity at Nordnesfjellet, northern Norway”, Earth Surf. Processes Landforms, vol. 43, no. 10, pp. 2147-2156, 2018.
• [7] N. Holschuh, K. Christianson, J. Paden, R. B. Alley, and S. Anandakrishnan, “Linking postglacial landscapes to glacier dynamics using swath radar at Thwaites glacier, Antarctica”, Geology, vol. 48, no. 3, pp. 268-272, Mar. 2020.
• [8] D. C. Mason, T. R. Scott, and H.-J. Wang, “Extraction of tidal channel networks from airborne scanning laser altimetry”, ISPRS J. Photogramm. Remote Sens., vol. 61, no. 2, pp. 67-83, 2006.
• [9] I. S. Evans, “Geomorphometry and landform mapping: What is a landform?” Geomorphology, vol. 137, no. 1, pp. 94-106, 2012.
• [10] L. Janowski, K. Tylmann, K. Trzcinska, S. Rudowski and J. Tegowski, "Exploration of Glacial Landforms by Object-Based Image Analysis and Spectral Parameters of Digital Elevation Model", in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-17, 2022, Art no. 4502817, http://doi.org/10.1109/TGRS.2021.3091771
• [11] T. K. Ho, ‘Random decision forests’, in Proceedings of 3rd international conference on document analysis and recognition, 1995, vol. 1, pp. 278-282.
• [12] C. Cortes and V. Vapnik, ‘Support-vector networks’, Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
• [13] K. Tylmann et al., “The local last glacial maximum of the southern Scandinavian ice sheet front: Cosmogenic nuclide dating of erratics in northern Poland”, Quaternary Sci. Rev., vol. 219, pp. 36-46, 2019.
• [14] C. Porter et al., ArcticDEM. Harvard Dataverse, 2018, http://doi.org/10.7910/DVN/OHHUKH
• [15] Head Office of Geodesy and Cartography, GUGIK, Warsaw, Poland, 2017.
• [16] Li Deng, Dong Yu, “Deep Learning: Methods and Applications”, Now Foundations and Trends, 2014.
• [17] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning”, Nature, vol. 521, no. 7553. Springer Science and Business Media LLC, pp. 436-444, May 27, 2015. http://doi.org/10.1038/nature14539
• [18] X. Ying, “An Overview of Overfitting and its Solutions”, Journal of Physics: Conference Series, vol. 1168, no. 2, p. 022022, Feb. 2019.
• [19] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks”, in Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Lake Tahoe, Nevada, 2012, pp. 1097-110
• [20] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition”, in International Conference on Learning Representations, 2015.
• [21] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition”, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778.
• [22] X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks”, in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 13-15 May 2010, vol. 9, pp. 249-256.
• [23] A. Dosovitskiy et al., ‘An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale’, ICLR, 2021.
• [24] A. Vaswani et al., ‘Attention is All you Need’, in Advances in Neural Information Processing Systems, 2017, vol. 30.
• [25] S. H. Lee, S. Lee, and B. C. Song, ‘Vision Transformer for Small-Size Datasets’, arXiv [cs.CV]. 2021.
• [26] A. Paszke et al., ‘PyTorch: An Imperative Style, High-Performance Deep Learning Library’, in Advances in Neural Information Processing Systems 32, Curran Associates, Inc., 2019, pp. 8024-8035.
• [27] https://github.com/lucidrains/vit-pytorch
• [28] L. Prechelt, “Early Stopping - But When?”, Lecture Notes in Computer Science. Springer Berlin Heidelberg, pp. 55-69, 1998. http://doi.org/10.1007/3-540-49430-8_3
• [29] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, ‘Optuna: A Next-generation Hyperparameter Optimization Framework’, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019.
• [30] M. A. Zaharia et al., “Accelerating the Machine Learning Lifecycle with MLflow”, IEEE Data Eng. Bull., vol. 41, pp. 39-45, 2018.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).