Abstract
In this study, an intelligent algorithm for the extraction of sand dune maps from Landsat satellite images in terrestrial and coastal environments was presented by a case study of the sand dunes in northeastern Iran and one example on the coast of the Oman Sea in southeastern Iran. First, to find the best sand dune detection algorithm, the land cover map is created by aerial photography and field observation in ILWIS software. Next, a binary image is created in which the sand dunes are considered as white pixels and other parts as black pixels. In the next step, the pixels of each land cover map class are divided into 50 equal parts, one part of them is used to train different smart grids and the rest of them are used for evaluation. Then the classification is done using all 50 parts in turn, and the Correct Classification Rate (CCR) index is calculated. This action is performed for the K-Nearest Neighbor, Decision Tree, AdaBoost, RUSBoost, and SVM algorithms. Furthermore, to see the effect of the PCA and LDA statistical methods, the classifier algorithms are implemented by applying these techniques. Finally, the proposed method was tested in a coastal area as an example. The findings show that the CCR of the proposed method is around 84% using 2% of the ground truth of the area for training and the other 98% of them for testing. In the case study, the detection results show that around 9.98% of the area is covered by sand dunes. To have a practical detection of the sand dunes area, the proposed machine learning method is applied to some experimentally verified points. Based on the results, ensemble classification methods, especially RUSBoost, have the best detection accuracy. Also, the result of its test on the coastal sand dunes showed its ability to identify, map, and monitor the sand dunes in coastal areas.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abuzneid MA, Mahmood A (2018) Enhanced human face recognition using LBPH descriptor, multi-KNN, and back-propagation neural network. IEEE Access 6:20641–20651
Ali I, Cawkwell F, Green S, Dwyer N (2014) Application of statistical and machine learning models for grassland yield estimation based on a hypertemporal satellite remote sensing time series. In: Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International, pp 5060–5063
Aydda A, Algouti A (2014) Assessment of sand dunes movements rate in Atlantic Sahara desert using multi-temporal landsat imagery and GIS technique. Multidimensão e Territórios de Risco. Guimarães, ed. Imprensa da Universidade de Coimbra, pp 101–105
Aydda A, Althuwaynee OF, Pokharel B (2020) An easy method for barchan dunes automatic extraction from multispectral satellite data. IOP Conf. Series: Earth and Environmental Science 419:1–9
Bankert RL, Hadjimichael M, Kuciauskas AP, Richardson KA, Turk FJ, Hawkins JD (2003) Automating the estimation of various meteorological parameters using satellite data and machine learning techniques. In: Frontiers of remote sensing information processing. World Scientific Publishing Co, pp 227–252
Berberoglu S, Akin A (2009) Assessing different remote sensing techniques to detect land use/cover changes in the eastern Mediterranean. Int J Appl Earth Obs Geoinf 11(1):46–53
Bhatt A, Ghosh SK, Kumar A (2015) Automated change detection in satellite images using machine learning algorithms for Delhi, India. In: Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, pp 1678–1681
Bibal A, Frénay B (2016) Interpretability of machine learning models and representations: an introduction. ESANN 2016 proceedings, pp 77–82
Blackard JA, Dean DJ (1999) Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Comput Electron Agric 24(3):131–151
Brownett JM, Mills RS (2017) The development and application of remote sensing to monitor sand dune habitats. J Coast Conserv 21:643–656
Buschjäger S, Morik K (2018) Decision tree and random forest implementations for fast filtering of sensor data. IEEE Trans Circuits Syst Regul Pap 65(1):209–222
Campbell JB (2007) Introduction to remote sensing, 4th edn. Guilford Press, New York
Clark ML (2016) Mapping land cover with hyperspectral and multispectral satellites using machine learning and spectral mixture analysis. In: Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, pp 513–516
Doody P (2020) Sand Dunes in Europe. Available from http://www.coastalwiki.org/wiki/Sand_Dunes_in_Europe. Accessed on 11-11-2020
Elhadi EM, Zomrawi N, Hu G (2009) Landscape change and Sandy desertification monitoring and assessment. Am J Environ Sci 5:633–638
Elhag A, Zomrawi Z, Khidir S (2019) Analysis of sand dunes accumulation using remote sensing and GIS. International Journal of Trend in Scientific Research and Development 4(1):423–427
Fadhil AM (2013) Sand dunes monitoring using remote sensing and GIS techniques for some sites in Iraq. Third international conference on photonics and image in agriculture engineering (PIAGENG 2013), Sanya, China. https://doi.org/10.1117/12.2019735
Freund Y (1995) Boosting a weak learning algorithm by majority. Inf Comput 121(2):256–285
Ghadiry M, Shalaby A, Koch B (2012) A new GIS-based model for automated extraction of sand dune encroachment case study: Dakhla oases, western desert of Egypt. Egypt J Remote Sens Space Sci 15:53–65. https://doi.org/10.1016/j.ejrs.2012.04.001
Jimenez JA, Maia LP, Serra J, Morais J (1999) Aeolian dune migration along the Ceara coast, north-eastern Brazil. Sedimentology 46:689–701
Kerr GH, Fischer C, Reulke R (2015) Reliability assessment for remote sensing data: beyond Cohen's kappa. In: Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, pp 4995–4998
Khalaf FI, Al-Ajmi D (1993) Aeolian processes and sand encroachment problems in Kuwait. Geomorphology 6:111–134
Kim EY (2017) Vision-based wheelchair navigation using geometric AdaBoost learning. Electron Lett 53(8):534–536. https://doi.org/10.1049/el.2016.3865
Kwarteng A, Touzi R, Al-Jassar H (2000) Utilization of satellite SAR imagery for mapping sand dunes in Kuwait. In: Geoscience and Remote Sensing Symposium (IGARSS), 2000 IEEE International, pp 1960–1962
Lillesand TM, Kiefer RW, Chipman JW (2008) Remote sensing and image interpretation, 6th edn. Wiley, New York
Liu H, Zhou C, Cheng W, Long E, Li R (2008) Monitoring sandy desertification of Otindag Sandy Land-based on multi-date remote sensing images. Acta Ecol Sin 28(2):627–635
Lu J, Zhang E (2007) Gait recognition for human identification based on ICA and fuzzy SVM truth multiple views fusion. Pattern Recogn Lett 28:2401–2411. https://doi.org/10.1016/j.patrec.2007.08.004
Lv F, Han M, Qiu T (2017) Remote sensing image classification based on ensemble extreme learning machine with stacked autoencoder. 2007 IEEE Access, pp 9021–9931
McKee ED (1979) Introduction to a study of global sand seas. In: McKee ED (ed) A study of global sand seas USGS. United States Department of Interior, Washington, DC, pp 1–20
Mohamed E (2010) Sand movement patterns in the Western Desert of Egypt: an environmental concern. Environ Earth Sci 59:1119–1127
Negaresh H, Latifi L (2007) Geomorphologic analysis of the progress of sand dunes of the east of the Sistan plain in the recent drought. Geography and development 12:43–60 (In Persian)
Oliva D, Cuevas E (2017) Advances and applications of optimised algorithms in image processing, an introduction to machine learning. Springer
Sarnthein M (1978) Sand deserts during glacial maximum and climatic optimum. Nature 272:43–46
Sasikala BS, Biju VG, Prashanth CM (2017) Kappa and accuracy evaluations of machine learning classifiers. In: Recent Trends in Electronics, Information & Communication Technology (RTEICT), 2nd IEEE International Conference, pp 20–23
Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A (2008) RUSBoost: Improving classification performance when training data is skewed. In: Pattern Recognition, ICPR 2008, 19th International Conference, pp 1–4
Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A (2010) RUSBoost: A hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern Part A Syst Humans 40(1):185–197
Sivakumar S, Selvaraj R (2018) Predictive modelling of students performance truth the enhanced decision Tree. In: Advances in Electronics, Communication and Computing, Springer, Singapore, pp 21–36
U.S. Geological Survey (2018) Earth resources observation and science: U.S. Geological Survey database, earth explorer, Download Satellite images. Accessed 20 Jun 2018. http://earthexplorer.usgs.gov
Zhang S, Li X, Zong M, Zhu X, Wang R (2018) Efficient knn classification with different numbers of nearest neighbors. IEEE transactions on neural networks and learning systems 29(5):1774–1785
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Highlights
• A multidisciplinary quick remote sensing method proposed for sustainable management of sand dunes.
• An intelligent algorithm introduced for extraction of sand dunes from Landsat satellite imagery.
• The ensemble classification methods are capable to extract the sand dunes from Landsat satellite imagery.
• The RUSBoost of the ensemble classification methods has the best detection accuracy for extraction of sand dunes from Landsat satellite imagery.
Rights and permissions
About this article
Cite this article
Mohammadpoor, M., Eshghizadeh, M. Introducing an intelligent algorithm for extraction of sand dunes from Landsat satellite imagery in terrestrial and coastal environments. J Coast Conserv 25, 3 (2021). https://doi.org/10.1007/s11852-020-00789-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11852-020-00789-x