Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru’s High-Mountain Remote Sensing Images
Abstract
:1. Introduction
- Using Landsat-8 multispectral images, a comprehensive dataset of high-mountain lakes in the Peruvian Andes has been created, expanding knowledge of surface waters in this region. This dataset is divided into a training, validation and test.
- This study explores the behavior and performance of WaterSegDiff, a diffusion model with transformers, for remote sensing lake segmentation in complex high-mountain environments and compares WaterSegDiff with established methods such as NDWI, WatNet and DeepWaterMapV2.
- Temporal analysis of Lake Singrenacocha (Vilcanota Mountains, Peru) for 2014, 2016, 2018, and 2020 using segmentation techniques to understand the impact of environmental conditions and evaluate the practical usefulness of the models in real-world challenges.
2. Related Work
3. Materials and Methods
3.1. Study Area
3.2. Dataset
3.2.1. Data Acquisition
3.2.2. Data Preprocessing
3.2.3. Masks
3.3. NDWI
3.4. WatNet
3.5. DeepWaterMapV2
3.6. WaterSegDiff
3.6.1. Anchor Conditioning
3.6.2. Semantic Conditioning with SS-Former
3.6.3. Loss Function
3.7. Evaluation Metrics
4. Experiments and Results
4.1. Implementation Details
4.2. Performance Evaluation
4.2.1. Quantitative Analysis
4.2.2. Qualitative Analysis
4.3. Temporal Analysis of Lake Singrenacocha
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Adrian, R.; O’Reilly, C.M.; Zagarese, H.; Baines, S.B.; Hessen, D.O.; Keller, W.; Livingstone, D.M.; Sommaruga, R.; Straile, D.; Van Donk, E.; et al. Lakes as sentinels of climate change. Limnol. Oceanogr. 2009, 54, 2283–2297. [Google Scholar] [CrossRef] [PubMed]
- Somers, L.D.; McKenzie, J.M. A review of groundwater in high mountain environments. Wiley Interdiscip. Rev. Water 2020, 7, e1475. [Google Scholar] [CrossRef]
- Motschmann, A. Water Resource Risks in the Andes of Peru: An Integrative Perspective. Ph.D. Thesis, University of Zurich, Zurich, Switzerland, 2021. [Google Scholar]
- Wood, J.; Harrison, S.; Wilson, R.; Emmer, A.; Yarleque, C.; Glasser, N.; Torres, J.; Caballero, A.; Araujo, J.; Bennett, G.; et al. Contemporary glacial lakes in the Peruvian Andes. Glob. Planet. Chang. 2021, 204, 103574. [Google Scholar] [CrossRef]
- Vergara, W.; Deeb, A.; Valencia, A.; Bradley, R.; Francou, B.; Zarzar, A.; Grünwaldt, A.; Haeussling, S. Economic impacts of rapid glacier retreat in the Andes. Eos Trans. Am. Geophys. Union 2007, 88, 261–264. [Google Scholar] [CrossRef]
- Wang, S.; Zhou, L. Integrated impacts of climate change on glacier tourism. Adv. Clim. Chang. Res. 2019, 10, 71–79. [Google Scholar] [CrossRef]
- Murfitt, J.; Duguay, C.R. 50 years of lake ice research from active microwave remote sensing: Progress and prospects. Remote Sens. Environ. 2021, 264, 112616. [Google Scholar] [CrossRef]
- Li, Y.; Dang, B.; Zhang, Y.; Du, Z. Water body classification from high-resolution optical remote sensing imagery: Achievements and perspectives. ISPRS J. Photogramm. Remote Sens. 2022, 187, 306–327. [Google Scholar] [CrossRef]
- Wang, Y.; Yang, K.; Jia, T.; Luo, Y. Influence of natural factors and land use change on changes in the main lake area in China over the past 30 years. Ecol. Indic. 2023, 155, 111005. [Google Scholar] [CrossRef]
- Huang, C.; Chen, Y.; Zhang, S.; Wu, J. Detecting, extracting, and monitoring surface water from space using optical sensors: A review. Rev. Geophys. 2018, 56, 333–360. [Google Scholar] [CrossRef]
- Weng, Y.; Li, Z.; Tang, G.; Wang, Y. OCNet-Based Water Body Extraction from Remote Sensing Images. Water 2023, 15, 3557. [Google Scholar] [CrossRef]
- Chen, C.; Wang, Y.; Yang, S.; Ji, X.; Wang, G. A K-Net-based hybrid semantic segmentation method for extracting lake water bodies. Eng. Appl. Artif. Intell. 2023, 126, 106904. [Google Scholar] [CrossRef]
- McFeeters, S.K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int. J. Remote Sens. 1996, 17, 1425–1432. [Google Scholar] [CrossRef]
- Xu, H. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int. J. Remote Sens. 2006, 27, 3025–3033. [Google Scholar] [CrossRef]
- Du, Q.; Li, G.; Chen, D.; Qi, S.; Zhou, Y.; Wang, F.; Cao, Y. Extracting water body data based on SDWI and threshold segmentation: A case study in permafrost area surrounding Salt Lake in Hoh Xil, Qinghai-Tibet Plateau, China. Res. Cold Arid Reg. 2023, 15, 202–209. [Google Scholar] [CrossRef]
- Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 1979, 9, 62–66. [Google Scholar] [CrossRef]
- Yousefi, P.; Jalab, H.A.; Ibrahim, R.W.; Noor, N.F.M.; Ayub, M.N.; Gani, A. Water-body segmentation in satellite imagery applying modified kernel kmeans. Malays. J. Comput. Sci. 2018, 31, 143–154. [Google Scholar] [CrossRef]
- Wang, F.; Wu, Y.; Zhang, Q.; Zhao, W.; Li, M.; Liao, G. Unsupervised SAR image segmentation using higher order neighborhood-based triplet Markov fields model. IEEE Trans. Geosci. Remote Sens. 2013, 52, 5193–5205. [Google Scholar] [CrossRef]
- Razaque, A.; Ben Haj Frej, M.; Almi’ani, M.; Alotaibi, M.; Alotaibi, B. Improved support vector machine enabled radial basis function and linear variants for remote sensing image classification. Sensors 2021, 21, 4431. [Google Scholar] [CrossRef] [PubMed]
- Shetty, S.; Gupta, P.K.; Belgiu, M.; Srivastav, S. Assessing the effect of training sampling design on the performance of machine learning classifiers for land cover mapping using multi-temporal remote sensing data and google earth engine. Remote Sens. 2021, 13, 1433. [Google Scholar] [CrossRef]
- Zhang, X.; Li, J.; Hua, Z. MRSE-Net: Multiscale residuals and SE-attention network for water body segmentation from satellite images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 5049–5064. [Google Scholar] [CrossRef]
- Ortiz, A.; Tian, W.; Sherpa, T.C.; Shrestha, F.; Matin, M.; Dodhia, R.; Ferres, J.M.L.; Sankaran, K. Mapping Glacial Lakes Using Historically Guided Segmentation Models. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 9226–9240. [Google Scholar] [CrossRef]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 2012, 25, 1097–1105. [Google Scholar] [CrossRef]
- Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015; Proceedings, Part III 18. Springer: Berlin/Heidelberg, Germany, 2015; pp. 234–241. [Google Scholar]
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, HI, USA, 21–26 July 2017; pp. 2881–2890. [Google Scholar]
- Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 834–848. [Google Scholar] [CrossRef] [PubMed]
- Wang, S.; Peppa, M.V.; Xiao, W.; Maharjan, S.B.; Joshi, S.P.; Mills, J.P. A second-order attention network for glacial lake segmentation from remotely sensed imagery. ISPRS J. Photogramm. Remote Sens. 2022, 189, 289–301. [Google Scholar] [CrossRef]
- Thati, J.; Ari, S. A systematic extraction of glacial lakes for satellite imagery using deep learning based technique. Measurement 2022, 192, 110858. [Google Scholar] [CrossRef]
- Zhao, H.; Wang, S.; Liu, X.; Chen, F. Exploring contrastive representation for weakly-supervised glacial lake extraction. Remote Sens. 2023, 15, 1456. [Google Scholar] [CrossRef]
- Luo, X.; Tong, X.; Hu, Z. An applicable and automatic method for earth surface water mapping based on multispectral images. Int. J. Appl. Earth Obs. Geoinf. 2021, 103, 102472. [Google Scholar] [CrossRef]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4510–4520. [Google Scholar]
- Isikdogan, L.F.; Bovik, A.; Passalacqua, P. Seeing through the clouds with deepwatermap. IEEE Geosci. Remote Sens. Lett. 2019, 17, 1662–1666. [Google Scholar] [CrossRef]
- Wu, J.; Fu, R.; Fang, H.; Zhang, Y.; Yang, Y.; Xiong, H.; Liu, H.; Xu, Y. Medsegdiff: Medical image segmentation with diffusion probabilistic model. Med. Imaging Deep Learn. 2024, 227, 1623–1639. [Google Scholar]
- Li, L.; Yan, Z.; Shen, Q.; Cheng, G.; Gao, L.; Zhang, B. Water body extraction from very high spatial resolution remote sensing data based on fully convolutional networks. Remote Sens. 2019, 11, 1162. [Google Scholar] [CrossRef]
- Liu, Z.; Chen, X.; Zhou, S.; Yu, H.; Guo, J.; Liu, Y. DUPnet: Water Body Segmentation with Dense Block and Multi-Scale Spatial Pyramid Pooling for Remote Sensing Images. Remote Sens. 2022, 14, 5567. [Google Scholar] [CrossRef]
- Kadhim, I.J.; Premaratne, P. A novel deep learning framework for water body segmentation from satellite images. Arab. J. Sci. Eng. 2023, 48, 10429–10440. [Google Scholar] [CrossRef]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 6000–6010. [Google Scholar]
- Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; Gelly, S.; et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv 2020, arXiv:2010.11929. [Google Scholar]
- Ho, J.; Jain, A.; Abbeel, P. Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 2020, 33, 6840–6851. [Google Scholar]
- Singh, V.; Jandial, S.; Chopra, A.; Ramesh, S.; Krishnamurthy, B.; Balasubramanian, V.N. On conditioning the input noise for controlled image generation with diffusion models. arXiv 2022, arXiv:2205.03859. [Google Scholar]
- Saharia, C.; Ho, J.; Chan, W.; Salimans, T.; Fleet, D.J.; Norouzi, M. Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 45, 4713–4726. [Google Scholar] [CrossRef] [PubMed]
- Nichol, A.; Dhariwal, P.; Ramesh, A.; Shyam, P.; Mishkin, P.; McGrew, B.; Sutskever, I.; Chen, M. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv 2021, arXiv:2112.10741. [Google Scholar]
- Lugmayr, A.; Danelljan, M.; Romero, A.; Yu, F.; Timofte, R.; Van Gool, L. Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022, New Orleans, LA, USA, 18–24 June 2022; pp. 11461–11471. [Google Scholar]
- Baranchuk, D.; Rubachev, I.; Voynov, A.; Khrulkov, V.; Babenko, A. Label-efficient semantic segmentation with diffusion models. arXiv 2021, arXiv:2112.03126. [Google Scholar]
- Amit, T.; Shaharbany, T.; Nachmani, E.; Wolf, L. Segdiff: Image segmentation with diffusion probabilistic models. arXiv 2021, arXiv:2112.00390. [Google Scholar]
- Tan, H.; Wu, S.; Pi, J. Semantic diffusion network for semantic segmentation. Adv. Neural Inf. Process. Syst. 2022, 35, 8702–8716. [Google Scholar]
- Ayala, C.; Sesma, R.; Aranda, C.; Galar, M. Diffusion models for remote sensing imagery semantic segmentation. In Proceedings of the IGARSS 2023—2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 16–21 July 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 5654–5657. [Google Scholar]
- Wu, J.; Fu, R.; Fang, H.; Zhang, Y.; Xu, Y. Medsegdiff-v2: Diffusion based medical image segmentation with transformer. arXiv 2023, arXiv:2301.11798. [Google Scholar] [CrossRef]
- Bezerra, E.; Mafalda, S.; Alvarez, A.B.; Uman-Flores, D.A.; Perez-Torres, W.I.; Palomino-Quispe, F. A Cloud Coverage Image Reconstruction Approach for Remote Sensing of Temperature and Vegetation in Amazon Rainforest. Appl. Sci. 2023, 13, 12900. [Google Scholar] [CrossRef]
- Instituto Nacional de Investigación en Glaciares y Ecosistemas de Montaña, Huaraz, INAIGEM. Inventario Nacional de Glaciares y Lagunas de Origen Glaciar 2023; Instituto Nacional de Investigación en Glaciares y Ecosistemas de Montaña: Huaraz, Peru, 2023. [Google Scholar]
- U.S. Geological Survey. Landsat 8 (L8) Data Users Handbook, 2019. Available online: https://www.usgs.gov/landsat-missions/landsat-8#web-tools (accessed on 30 May 2024).
- Duda, R.O.; Hart, P.E. Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 1972, 15, 11–15. [Google Scholar] [CrossRef]
- Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 1986, 6, 679–698. [Google Scholar] [CrossRef]
- Ahmed, K.R.; Akter, S. Analysis of landcover change in southwest Bengal delta due to floods by NDVI, NDWI and K-means cluster with Landsat multi-spectral surface reflectance satellite data. Remote Sens. Appl. Soc. Environ. 2017, 8, 168–181. [Google Scholar] [CrossRef]
- Guardamino, L.; Drenkhan, F. Evolución y potencial amenaza de lagunas glaciares en La Cordillera de Vilcabamba (Cusco y Apurímac, Perú) entre 1991-2014. Rev. Glaciares Ecosistemas Montaña 2016, 1, 21–36. [Google Scholar] [CrossRef]
- Tumbalobos, E.M. Relación de la Humedad de Suelo con el índice de Agua y Vegetación de los Bofedales Altoandinos de la Microcuenca-Apacheta, Ayacucho 2017; Universidad Nacional de San Cristóbal de Huamanga: Ayacucho, Peru, 2023. [Google Scholar]
- Li, W.; Du, Z.; Ling, F.; Zhou, D.; Wang, H.; Gui, Y.; Sun, B.; Zhang, X. A comparison of land surface water mapping using the normalized difference water index from TM, ETM+ and ALI. Remote Sens. 2013, 5, 5530–5549. [Google Scholar] [CrossRef]
- Chen, L.C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV) 2018, Munich, Germany, 8–14 September 2018; pp. 801–818. [Google Scholar]
- Naseer, M.M.; Ranasinghe, K.; Khan, S.H.; Hayat, M.; Shahbaz Khan, F.; Yang, M.H. Intriguing properties of vision transformers. Adv. Neural Inf. Process. Syst. 2021, 34, 23296–23308. [Google Scholar]
- Woo, S.; Park, J.; Lee, J.Y.; Kweon, I.S. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) 2018, Munich, Germany, 8–14 September 2018; pp. 3–19. [Google Scholar]
- Duda, R.O.; Hart, P.E. Pattern Classification and Scene Analysis; Wiley: New York, NY, USA, 1973; Volume 3. [Google Scholar]
- Terven, J.; Cordova-Esparza, D.; Ramirez-Pedraza, A.; Chavez-Urbiola, E. Loss Functions and Metrics in Deep Learning. arXiv 2023, arXiv:2307.02694. [Google Scholar]
- Nichol, A.Q.; Dhariwal, P. Improved denoising diffusion probabilistic models. In Proceedings of the International Conference on Machine Learning. PMLR 2021, Virtual, 18–24 July 2021; pp. 8162–8171. [Google Scholar]
- Lavado-Casimiro, W.; Espinoza, J.C. Impactos de El Niño y La Niña en las lluvias del Perú (1965–2007). Rev. Bras. Meteorol. 2014, 29, 171–182. [Google Scholar] [CrossRef]
- Amyar, A.; Guo, R.; Cai, X.; Assana, S.; Chow, K.; Rodriguez, J.; Yankama, T.; Cirillo, J.; Pierce, P.; Goddu, B.; et al. Impact of deep learning architectures on accelerated cardiac T1 mapping using MyoMapNet. NMR Biomed. 2022, 35, e4794. [Google Scholar] [CrossRef] [PubMed]
- U.S. Geological Survey. How Long Does It Take to Create Landsat Collection 2 Level-2 Products after a Landsat Scene Is Acquired? 2024. Available online: https://www.usgs.gov/faqs/how-long-does-it-take-create-landsat-collection-2-level-2-products-after-a-landsat-scene (accessed on 30 May 2024).
Bands | Name | Wavelength |
---|---|---|
Band 2 (B2) | Blue | 0.450–0.51 µm |
Band 3 (B3) | Green | 0.53–0.59 µm |
Band 4 (B4) | Red | 0.64–0.67 µm |
Band 5 (B5) | Near-Infrared | 0.85–0.88 µm |
Band 6 (B6) | SWIR 1 | 1.57–1.65 µm |
Band 7 (B7) | SWIR 2 | 2.11–2.29 µm |
Category | Number | Resolution |
---|---|---|
Train | 3228 | 256 × 256 |
Val | 402 | 256 × 256 |
Test | 402 | 256 × 256 |
Method | MIoU | PA | F1 Score | Parameters (M) |
---|---|---|---|---|
NDWI | 0.6437 | 0.8034 | 0.5395 | - |
WatNet | 0.9016 | 0.9960 | 0.8725 | 3.4 |
DeepWaterMapV2 | 0.9088 | 0.9967 | 0.8801 | 37.2 |
WaterSegdiff | 0.8243 | 0.9895 | 0.7504 | 129.4 |
Year | Metrics | NDWI | Watnet | DeepWaterMapV2 | WaterSegDiff |
---|---|---|---|---|---|
2014 | MIoU | 0.2670 | 0.7346 | 0.7391 | 0.6667 |
PA | 0.4797 | 0.9606 | 0.9770 | 0.9375 | |
F1 Score | 0.1452 | 0.6758 | 0.6683 | 0.5700 | |
2016 | MIoU | 0.8229 | 0.9766 | 0.9667 | 0.9547 |
PA | 0.9757 | 0.9977 | 0.9967 | 0.9956 | |
F1 Score | 0.8034 | 0.9773 | 0.9674 | 0.9551 | |
2018 | MIoU | 0.8205 | 0.9674 | 0.9074 | 0.9674 |
PA | 0.9757 | 0.9968 | 0.9899 | 0.9969 | |
F1 Score | 0.7998 | 0.9681 | 0.9044 | 0.9681 | |
2020 | MIoU | 0.8731 | 0.9747 | 0.9664 | 0.9553 |
PA | 0.9845 | 0.9975 | 0.9967 | 0.9957 | |
F1 Score | 0.8652 | 0.9754 | 0.9671 | 0.9557 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Perez-Torres, W.I.; Uman-Flores, D.A.; Quispe-Quispe, A.B.; Palomino-Quispe, F.; Bezerra, E.; Leher, Q.; Paixão, T.; Alvarez, A.B. Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru’s High-Mountain Remote Sensing Images. Sensors 2024, 24, 5177. https://doi.org/10.3390/s24165177
Perez-Torres WI, Uman-Flores DA, Quispe-Quispe AB, Palomino-Quispe F, Bezerra E, Leher Q, Paixão T, Alvarez AB. Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru’s High-Mountain Remote Sensing Images. Sensors. 2024; 24(16):5177. https://doi.org/10.3390/s24165177
Chicago/Turabian StylePerez-Torres, William Isaac, Diego Armando Uman-Flores, Andres Benjamin Quispe-Quispe, Facundo Palomino-Quispe, Emili Bezerra, Quefren Leher, Thuanne Paixão, and Ana Beatriz Alvarez. 2024. "Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru’s High-Mountain Remote Sensing Images" Sensors 24, no. 16: 5177. https://doi.org/10.3390/s24165177
APA StylePerez-Torres, W. I., Uman-Flores, D. A., Quispe-Quispe, A. B., Palomino-Quispe, F., Bezerra, E., Leher, Q., Paixão, T., & Alvarez, A. B. (2024). Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru’s High-Mountain Remote Sensing Images. Sensors, 24(16), 5177. https://doi.org/10.3390/s24165177