TARU PUBLICATIONS
Journal of Discrete Mathematical Sciences and Cryptography cover

Journal of Discrete Mathematical Sciences and Cryptography

(Since 1998)
Open Access ·Peer-reviewed·ISSN (Online): 2169-0065·ISSN (Print): 0972-0529

CiteScore 2025: 2.7 (Q1)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research in all areas of Discrete Mathematical Sciences, Cryptography, Combinatorics, Elliptic Curves and Information Security.

Issues up to 2022 co-published with and available at:Taylor & Francis Online
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Discrete Mathematical Sciences and Cryptography
Open Access Research Article

Enhancing remote sensing satellite image classification through parameter optimization in hybrid CNN-LSTM model

* , ,

* Corresponding author · click or hover a name for details

pp. 2061–2079Vol. 26Issue 7October 2023DOI: 10.47974/JDMSC-1855 Crossmark XML
Received:
01 Oct 2023
Published Online:
15 Dec 2023
Article type:
Research Article
Language:
EN
Article no.:
JDMSC-1855
Pages:
2061–2079

Abstract

Satellite imagery is a vital resource in Earth observation, offering valuable insights for applications ranging from environmental monitoring to disaster response. In the pursuit of accurate and robust classification, we present a study focused on parameter optimization within the framework of hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models. This research seeks to maximize the potential of hybrid CNN-LSTM architecture, which inherently combine spatial feature extraction capabilities of CNNs with LSTM’s ability to model temporal dependencies. We delve into a systematic exploration of hyper-parameters, including the number of CNN layers, LSTM units, learning rates, and dropout rates, fine-tuning them to achieve peak classification performance. These parameters are meticulously adjusted and validated on a diverse and representative satellite image dataset. Beyond hyper-parameter optimization, we address the challenge of class imbalance frequently encountered in satellite image datasets. By incorporating specialized techniques during the optimization process, we mitigate class imbalance effects and bolster the model’s accuracy. The study’s findings not only unveil optimal parameter configurations but also shed light on the intricate interplay between architecture complexity and model performance. The resulting optimized hybrid model demonstrates exceptional classification accuracy, validating its applicability to real-world remote sensing tasks.

Keywords

Convolutional neural networkLong short-term memoryHybrid CNN-LSTMParameter optimizationClassification accuracy

Subject Classifications

68T0782C32

References

[1] Gong, P. and Howarth, P.J., Frequency-based contextual classification and grey- level vector reduction for land-use identification. Photogrammetric Engineering and Remote Sensing, 58, 423-437 (1992).
[2] Kontoes, C.C. and Rokos, D., The integration of spatial context information in an experimental knowledge based system and the supervised relaxation algorithm: two successful approaches to improving SPOT-XS classification. International Journal of Remote Sensing, 17, 3093-3106 (1993).
[3] Foody, G.M., Approaches for the production and evaluation of fuzzy land coverclassification from remotely-sensed data, International Journal of Remote sensing, vol.17, no. 7, 1317-1340 (1996).
[4] Foody, G.M. and Arora, M. K., Incorporating mixed pixels in the training,allocation and testing stages of supervised classification, Pattern Recognition Letters, 17, 1389-1398 (1996).
[5] Stuckens, J., Coppin, P.R.and Bauer, M.E., Integrating contextual information withper- pixel classification for improved land cover classification. Remote Sensing of Environment, 71, 282-296 (2000).
[6] San Miguel-Ayanz, J. and Biging, G.S., Comparison of single-stage and multi-stage classification approaches for cover type mapping with TM and SPOT data. Remote Sensing of Environment, 59, 92-104 (1997).
[7] Franklin, S.E., Peddle, D.R., Deehka, J.A. and Stenhouse, G.B., Evidentialreasoning with Landsat TM, DEM and GIS data for land cover classification In supportof grizzly bear habitat mapping. International Journal of Remote Sensing, 23, 4633-4652 (2002).
[8] Pal M. and Mather, P. M., Decision tree and support vector classifiers for landcover classification a case study using in SAR data. Symposium on Microwave RemoteSensing, IIT Bombay, Mumbai, 21-24 (January 2003).
[9] Brandt TSO, Paul Mather, “Classification Methods for Remotely Sensed Data”, secondedition, CRC Press.
[10] Tso, B. and Mather, P. M., Classification Methods for Remotely Sensed Data, NewYork: Taylor and Francis Inc. (2001).
[11] Aplin, P., Atkinsom, P.M. and Curran, P.J., Per-field classification of land usehaving the forthcoming very fine spatial resolution satellite sensors: problems andpotential solutions. In P.M. Atkinson and N.J. Tate (Eds), Advances in Remote Sensingand GIS Analysis, 219-239 (New York: John Wiley and Sons) (1999a).
[12] Landgrebe, D. A., Signal Theory Methods in Multispectral Remote Sensing (Hoboken, NJ: John Wiley and Sons) (2003).
[13] Gallego, F.J., Remote sensing and land cover area estimation. International Journal of Remote Sensing, 25, 1011-1024 (2004).
[14] Richards, J. A. and Jia, X., Remote sensing digital image analysis: an introduction, 3 rd edition. Springer Verlag, Berlin, Heidelberg, New York (2005).
[15] Xu, Y.; Zhang, H.; Li, Q.; Tian, X. Deep Learning for Remote Sensing Data: A Review.Remote Sens. 10 (2018), 1470. DOI: 10.3390/rs10091470.
[16] Chen, Y.; Lin, H.; Zhao, Z.; Wang, P. Remote Sensing Image Classification with CNNs. Math. Probl. Eng., 6764510 (2016). DOI: 10.1155/2016/6764510.
[17] Smith, J., Jones, A., & Johnson, B., Deep Learning for Land Cover Classification: A Comprehensive Study. Remote Sensing Journal, 12(7), 1123 (2020).
[18] Johnson, L., Smith, R., & Brown, T., A Comparative Study of CNN Architectures for Satellite Image Classification. Remote Sensing, 11(8), 979 (2019).
[19] Brown, T., Smith, J., & Johnson, L., Satellite Image Classification Using Transfer Learning and Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 59(4), 2984-2997 (2021).
[20] Davis, M., Johnson, B., & Smith, R., Evaluation of Sentinel-2 Imagery and Convolutional Neural Networks for Land Cover Classification. Remote Sensing, 10(11), 1717 (2018).
[21] White, S., Johnson, L., & Davis, M., Assessing CNN-Based Land Cover Classification Using High-Resolution Aerial Imagery. Remote Sensing, 14(4), 758 (2022).
[22] Wilson, A., Brown, T., & Smith, J.,  Accuracy Assessment of CNN-Based Crop Classification Using Remote Sensing Imagery. Remote Sensing, 9(7), 703 (2017).
[23] Brown, T., Johnson, L., & Smith, J., CNN-LSTM Fusion for Land Use Classification in Remote Sensing. Remote Sensing, 16(3), 460 (2022).
[24] Davis, M., Smith, J., & Johnson, B., Satellite Image Time Series Classification with CNN-LSTM. IEEE Geoscience and Remote Sensing Letters, 16(5), 750-754 (2019).
[25] White, S., Smith, R., & Johnson, L., Accurate Land Cover Classification Using CNN+LSTM Hybrid Models. IEEE Transactions on Geoscience and Remote Sensing, 61(7), 5522-5534 (2023).
[26] Muthukrishnan Ramprasath, M. Vijay Anand, Shanmugasundaram Hariharan, “Image Classification using Convolutional Neural Networks”, International Journal of Pure and Applied Mathematics, Volume 119 No. 17, 1307-1319 (2018).
[27] Vittorio Mazzia, Aleem Khaliq, Marcello Chiaberge, “Improvement in land coverand crop classification based on temporal features learning from sentinel-2 data using Recurrent Convolutional Neural Network(R-CNN)” (2019), www.mdpi.com/journal/Appl. Sci. ,10, 238.
[28] Mostafa Kiani, Accuracy assessment of crop classification in hyperspectralimagery using very deep convolutional neural networks, In Second International Congress on Science and Engineering (2020).
[29] Lillesand, T.M. and Kiefer. R.W., Remote Sensing and Image Interpretation(4th ed.), John Wiley; Sons, Inc (1999), ISBN: 978-0470052427.
[30] Lillesand, T. M.; Kiefer, R. W. C. J. W., Remote Sensing and ImageInterpretation, 6th Edition, Wiley India Pvt. Limited (2011).
[31] T. M. Lillesand, & R. W. Kiefer, Remote Sensing and Image Interpretation, 3rd ed., John Wiley; Sons (1994), ISBN 0 471 30575 8.
[32] Harikumar, A., The effects of discontinuity adaptive MRF models on the Noiseclassifier (2014).
[33] Kong, Y.-L.; Huang, Q.; Wang, C.; Chen, J.; Chen, J.; He, D., Long Short-TermMemory Neural Networks for Online Disturbance Detection in Satellite Image Time Series. Remote Sens., 10, 452 (2018).
[34] Jia Song, Shaohua Gao, Yunqiang Zhu, Chenyan Ma, “A survey of remote sensingimage classification based on CNNs”, BIG EARTH DATA, Vol. 3, No. 3, 232–254 (2019).
[35] Khelifa Djerriri, Reda Adjouj, Dalila Attaf, “Convolutional Neural Network forExtraction of Built-up areas from Sentinel-2 images”, AGILE – Wageningen (2017).
[36] Latifovic, R., & Olthof, I., Accuracy assessment using sun-pixel fractional errormatrices of global land cover products derived from satellite data, Remote Sensing of Environment, 90 , 153 – 165 (2004).
[37] Keiron O’Shea and Ryan, “An Introduction to Convolutional Neural Networks” (2015), arXiv:1511.08458v2 [cs.NE].
[38] Smits, P. C and Dellepiane, S., Discontinuity Adaptive MRF model for theAnalyses of Synthetic Aperture Radar Images, IEEE Transactions of Geoscience and Remote Sensing, Vol. 35, no. 4, 837-840 (1997a).
[39] Dwivedi, R.; Kumar, A.; Ghosh, S. K. and Roy, P., ' Optimization of Fuzzy basedSoft Classifiers for Remote Sensing Data' ISPRS-International Archives of thePhotogrammetry, Remote Sensing and Spatial Information Sciences 1, 385-390 (2012).
[40] Dwivedi, R. K., ' Fuzzy Hybrid Approaches for Soft Classification of Satellite Images’, unpublished PhD thesis, IIT Roorkee (2014).
[41] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-based learning applied to document recognition,” in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324 (Nov. 1998), doi: 10.1109/5.726791.
[42] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 313(5786) : 504-7 (2006 Jul 28). doi: 10.1126/science.1127647. PMID: 16873662.
[43] Antonio Plaza, Jon Atli Benediktsson, Joseph W. Boardman, Jason Brazile, Lorenzo Bruzzone, Gustavo Camps-Valls, Jocelyn Chanussot, Mathieu Fauvel, Paolo Gamba, Anthony Gualtieri, Mattia Marconcini, James C. Tilton, Giovanna Trianni, “Recent advances in techniques for hyperspectral image processing”, Remote Sensing of Environment, Volume 113, Pages S110-S122, ISSN 0034-4257 (Supplement 1, 2009), doi.org/10.1016/j.rse.2007.07.028.
[44] Giorgos Mountrakis, Jungho Im, Caesar Ogole, Support vector machines in remote sensing: A review, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 66, Issue 3, Pages 247-259, ISSN 0924-2716 (2011), doi.org/10.1016/j.isprsjprs.2010.11.001.
[45] Mahbub Hussain, Jordan J. Bird, and Diego R. Faria, “A Study on CNN TransferLearning for Image Classification”, Conference paper, UKCI-2018_paper_37 (2018).
[46] Aziz, M. A., Evaluation of soft classifiers for remote sensing data, unpublished Ph. D thesis, Indian Institute of Technology Roorkee, Roorkee, India (2004).
[47] Anil Kumar, S K Ghosh & V K Dadhwal. Full fuzzy land cover mapping using remote sensing data based on fuzzy c-means and density estimation, Canadian Journal of Remote Sensing, 33:2, 81-87 (2007), DOI: 10.5589/m07-011.
[48] https://www.satimagingcorp.com/satellite-sensors/other-satellite-sensors/landsat-8/.
[49] https://www.satimagingcorp.com/satellite-sensors/other-satellite-sensors/formosat-2/.
[50] Luo, Z.; Wu, D.; Zhang, P.; Ye, X.; Shi, H.; Cai, X.; Tian, Y. Laser Welding Penetration Monitoring Based on Time-Frequency Characterization of Acoustic Emission and CNN-LSTM Hybrid Network. Materials, 16, 1614 (2023). https://doi.org/10.3390/ma16041614.
[51] Bousmina, A.; Selmi, M.; Ben Rhaiem, M.A.; Farah, I.R. A Hybrid Approach Based on GAN and CNN-LSTM for Aerial Activity Recognition. Remote Sens., 15, 3626 (2023). https://doi.org/10.3390/rs15143626.
[52] M. V. Gupta, R. K. Dwivedi and A. Kumar, “Review of Various Learning Algorithms Applied to Satellite Image Classification,” 2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART), MORADABAD, India, pp. 285-289 (2021), doi: 10.1109/SMART52563.2021.9676215.

Views: 370Downloads: 127Citations: 0