Published March 30, 2024 | Version CC-BY-NC-ND 4.0
Journal article Open

An Innovative Approach: Sea Ice Types Classification Using Convolutional Neural Networks with DDDTDWT Filter

Creators

  • 1. Department of Computer science and Engineering, N.B.K.R Institute of Science and Technology, Tirupati, India.

Contributors

  • 1. Department of Computer science and Engineering, N.B.K.R Institute of Science and Technology, Tirupati, India.
  • 2. Department of Electronics and Communication Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India.

Description

Abstract: Studying sea ice and its interaction with climate change is crucial due to its significant impact on the environment, society, and global stability. The pressing need to address the underlying reasons for the rapid melting of Arctic and Antarctic sea ice is underscored by its adverse effects on the environment and society. In this proposed study, a Convolutional Neural Network (CNN) is utilized to predict ice types using data from the NSIDC DAAC Advanced Microwave Scanning Radiometer - Earth Observing System Sensor (AMSR-E) collection. This dataset contains parameters such as sea ice types and spans data products from June 2002, obtained from the NASA Data Centre. By employing hand-crafted features as input and a single layer of hidden nodes, the CNN used in this approach generates improved estimates of ice types, outperforming traditional image analysis methods. At each stage, ConvNets use diverse filter banks, feature extraction pooling layers, and fully connected layers with basic activation functions like Relu. This allows the network to build multifaceted hierarchies of features. The sea ice type estimates produced by the CNN are then compared with those obtained from passive microwave brightness temperature data using existing algorithms as well as a proposed CNN algorithm, resulting in an increased classification accuracy of 98.58%. This improvement is particularly notable in the reduction of the error rate, which has been effectively minimized from 3.01% without feature selection to 1.42% with infinite feature selection. When compared to existing algorithms, the CNN demonstrates superior performance. These findings underscore the impact of input patch size, CNN layer count, and input size on the model's performance.

Files

B809913020724.pdf

Files (621.4 kB)

Name Size Download all
md5:ffa5be3d255280d910a92094096831ec
621.4 kB Preview Download

Additional details

Identifiers

DOI
10.35940/ijsce.B8099.14010324
EISSN
2231-2307

Dates

Accepted
2024-03-15
Manuscript received on 07 February 2024 | Revised Manuscript received on 06 March 2024 | Manuscript Accepted on 15 March 2024 | Manuscript published on 30 March 2024.

References

  • Carrieres, T.; Greenan, B.; Prinsenberg, S.; Peterson, I.," Comparison of Canadian daily ice charts with surface observations off New found land", winter 1992. Atmos. Ocean 1996, 34, 207–226, Oct 1996. https://doi.org/10.1080/07055900.1996.9649563
  • Masahiro kazumori., "Impact Study of AMSR-E Radiances in the NCEP Global Data Assimilation System", Page (s): 541–559, 2008. https://doi.org/10.1175/2007MWR2147.1
  • J. Rohrs and L. Kaleschke An algorithm to detect sea ice leads by using AMSR-E passive microwave imagery ".Articles European Geoscience union Volume 6, issue 2 TC, 6, 343–352, 2012. https://doi.org/10.5194/tc-6-343-2012
  • Ayushman Ramola, Study of statistical methods for texture analysis and their modern evolutions", 2022.
  • Clausi, D.A., et al.,"Comparison and fusion of co-occurrence, Gabor, and MRF texture features for classification of SAR sea ice imagery. Atmos. Ocean 39, 183–194, 2001. https://doi.org/10.1080/07055900.2001.9649675
  • Pogson, L et al.,"A collection of empirically derived characteristic values from SAR across a year of sea ice environments for use in data assimilation", Mon. Weather Revinpress, 2016. https://doi.org/10.1175/MWR-D-16-0110.1
  • Buehner, M.; Caya, A.; Pogson, L.; Carrieres, T.; Pestieau, "PA new Environment Canada regional ice analysis system" .Atmos.Ocean, 51,18–34, 2013. https://doi.org/10.1080/07055900.2012.747171
  • Drusch, M. et al., "Sea ice concentration analyses for the Baltic Sea andtheir impacton numerical weather prediction", J.Appl.Meteorol.Climatol.45,982–994, 2006. https://doi.org/10.1175/JAM2376.1
  • Le Cun,Y.;Bengio,J.;Hinton,G DeepLearning. Nature, 521,436–444, 2015. https://doi.org/10.1038/nature14539
  • Wang, L.; Scott, K.A.; Xu, L.; Clausi, D.A.,"Sea Ice Concentration Estimation During Melt From Dual-Pol SAR Scenes Using Deep Convolutional Neural Networks: A Case Study", IEEE Trans. Geosci. Remote Sens. 2016, 54, 4524–4533. https://doi.org/10.1109/TGRS.2016.2543660
  • Ivanova,N.;Tonboe,R.;Pedersenc.,"L.T.SICCI Product Validation and Algorithm Selection Report (PVASR)-Sea Ice Concentration", Technical Report; European Space Agency:Paris,France, 2013.
  • Najafabadi, M.M.; Villanustre, F.; Khoshgoftaar, T.M.; Seliya, N.; Wald, R.; E., "Deep learning applications and challenges in big data analytics" Big Data, 2, 2015. https://doi.org/10.1186/s40537-014-0007-7
  • Mnih, V.; Hinton, G.ELearning to detect roads in high-resolution aerial images. In Computer Vision-ECCV" , Springer: Berlin/Heidelberg, Germany, pp.210-223., 2010. https://doi.org/10.1007/978-3-642-15567-3_16
  • Chen, X.; Xiang, S.; Liu, C.L.; Pan, C.H.,"Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks". IEEE Geosci. Remote Sens. Lett. 11, 1797-1801, 2014. https://doi.org/10.1109/LGRS.2014.2309695
  • Maggiori, E.; Tarabalka, Y.; Charpiat, G.; Alliez, PFully convolutional neural networks for remote sensing image classification. In Proceedings of the 2016 IEEE Geoscience and Remote Sensing Symposium, Beijing, China, 10-15,2016. https://doi.org/10.1109/IGARSS.2016.7730322
  • Karvonen, J.; Vainio, J.; Marnela, M.; Eriksson, P.; Niskanen, T.)A comparison between high-resolution EO-based and ice analyst-assigned sea ice concentrations. J. Sel. Top. Appl. Earth Obs. Remote Sens 8, 1799–1807, 2015. https://doi.org/10.1109/JSTARS.2015.2426414
  • Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning; Springer: Berlin/Heidelberg, Germany Volume 2, 2009. https://doi.org/10.1007/978-0-387-84858-7
  • Bishop, C.MPattern Recognition and Machine Learning; Springer: Berlin/Heidelberg,Germany, 2006.
  • Le Cun, Y.; Kavukcuoglu, K.; Farabet, C.," Convolutional networks and applications in vision. In Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS), Paris, France, 30 May–2 June 2010; pp. 253–256, 2010. https://doi.org/10.1109/ISCAS.2010.5537907
  • https://github.com/tensorflow/tensorflow
  • https://en.wikipedia.org/wiki/PyTorch
  • https://en.wikipedia.org/wiki/Measurement_of_sea_ice
  • Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 3-6; pp. 1097-1105, December 2012.
  • Karpathy, A.; Toderici, G.; Shetty, S.; Leung, T.; Sukthankar, R.; Fei-Fei, L Large-scale video classification with convolutional neural networks. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 1725-1732,2014. https://doi.org/10.1109/CVPR.2014.223
  • Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L.
  • Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv, arXiv:1412.7062, 2016. LeCun, Y.; Bottou, L.; Orr, G.; Müller, K. Efficient backprop. In Neural Networks: Tricks of the Trade; Springer:Berlin/Heidelberg, Germany, 2012
  • Prechelt, L Early stopping-but when? In Neural Networks: Tricks of the Trade;springer: Berlin/Heidelberg, Germany, pp. 53-67, 2012. https://doi.org/10.1007/978-3-642-35289-8_5
  • Hinton, G.E.; Srivastava, N.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R.R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv arXiv:1207.0580, 2012.
  • Watkins,J.C. Probability Theory. In Course Note for Probability Theory; University of Arizona: Tucson, AZ, USA, 2006.
  • Jia, Y.; Shelhamer, E.; Donahue, J.; Karayev, S.; Long, J.; Girshick, R.; Guadarrama, S.; Darrell T.Caffe Convolutional architecture for fast feature embedding. In Proceedings of the ACM International Conference on Multimedia, Orlando, FL, USA, pp.675–678, 2014. https://doi.org/10.1145/2647868.2654889
  • Lei Wang, K. Andrea Scott et al., Sea Ice Concentration Estimation during Freeze-Up from SAR Imagery Using a Convolutional Neural Network, 2017. https://doi.org/10.3390/rs9050408
  • Jessica L. Matthews et al. Sensitivity of Arctic Sea Ice Extent to Sea Ice Concentration Threshold Choice and Its Implication to Ice Coverage Decadal Trends and Statistical Projection", 2014.
  • R. Lindsay and D. Rothrock et al., The calculation of surface temperature and albedo of Arctic sea ice from AVHRR, December 2012.
  • Qing Ji, et al., Statistical Analysis of SSMIS Sea Ice Concentration Threshold at the Arctic Sea Ice Edge during Summer Based on MODIS and Ship-Based Observational Data. Sensors.
  • Venkata KondaReddy Gajjala et al.,"AN EFFICIENT MULTI-CLASS SUPPORT VECTOR MACHINE CLASSIFICATION OF AMSR-E DATASET IMAGES ISSN: 2096-3246,Volume 54, Issue 02, October, 2022.
  • Venkata KondaReddy Gajjala et al.,"AN EFFICIENT K-NEAREST NEIGHBOR CLASSIFICATION OF AMSR-E DATASET IMAGES", ISSN: 2096-3246, Volume 54, Issue 02, and October, 2022.
  • Das, S., S, S., M, A., & Jayaram, S. (2021). Deep Learning Convolutional Neural Network for Defect Identification and Classification in Woven Fabric. In Indian Journal of Artificial Intelligence and Neural Networking (Vol. 1, Issue 2, pp. 9–13). https://doi.org/10.54105/ijainn.b1011.041221
  • Kumar, P., & Rawat, S. (2019). Implementing Convolutional Neural Networks for Simple Image Classification. In International Journal of Engineering and Advanced Technology (Vol. 9, Issue 2, pp. 3616–3619). https://doi.org/10.35940/ijeat.b3279.129219
  • Pagare, S., & Kumar, Dr. R. (2024). Human Action Recognition using Long Short-Term Memory and Convolutional Neural Network Model. In International Journal of Soft Computing and Engineering (Vol. 14, Issue 2, pp. 20–26). https://doi.org/10.35940/ijsce.i9697.14020524