Journal of Forest and Environmental Science

Institute of Forest Science, kangwon National University (강원대학교 산림과학연구소)
권호 표지
DOI QR코드

DOI QR Code

Accuracy Assessment of Forest Degradation Detection in Semantic Segmentation based Deep Learning Models with Time-series Satellite Imagery

  • Woo-Dam Sim (Division of Forest Sciences, Department of Forest Management, College of Forest and Environmental Sciences, Kangwon National University) ;
  • Jung-Soo Lee (Division of Forest Sciences, Department of Forest Management, College of Forest and Environmental Sciences, Kangwon National University)
  • Received : 2024.02.19
  • Accepted : 2024.03.02
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

Keywords

Acknowledgement

This research was funded by the Korea National Institute of Forest Science under project FM 0103-2021- 04-2023.

References

  1. Cha SE, Won MS, Jang KC, Kim KM, Kim WK, Baek SI, Lim JB. 2022. Deep Learning-based Forest Fire Classification Evaluation for Application of CAS500-4. Korean J Remote Sens 38: 1273-1283.
  2. Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y. 2021. TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv doi: 10.48550/arXiv.2102.04306.
  3. Cho KH, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv doi: 10.48550/arXiv.1406.1078.
  4. Clausi DA. 2002. An analysis of co-occurrence texture statistics as a function of grey level quantization. Can J Remote Sens 28: 45-62.
  5. Geron A. 2022. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. 3rd ed. O'Reilly Media, Zurich.
  6. Haralick RM, Shanmugam K, Dinstein I. 1973. Textural Features for Image Classification. IEEE Trans Syst Man Cybern 6: 610-621.
  7. Huang MH, Rust RT. 2018. Artificial Intelligence in Service. J Serv Res 21: 155-172.
  8. Kim ES, Won MS, Kim KM, Park JW, Lee JS. 2019. Forest Management Research using Optical Sensors and Remote Sensing Technologies. Korean J Remote Sens 35: 1031-1035.
  9. Kingma DP, Ba J. 2014. Adam: A Method for Stochastic Optimization. arXiv doi: 10.48550/arXiv.1412.6980.
  10. Korea Forest Service. 2024. K-Forest. https://www.forest.go.kr/kfsweb/cmm/fms/FileDown.do;jsessionid=ilhoHh5xodlaj9EjQFVng72ZmSquwRmeOHcfgEKOp6bvbLJ3J9FsuCkqyoYpAx6h.frswas01_servlet_engine5?atchFileId=FILE_000000020048405&fileSn=1&dwldHistYn=N&bbsId=BBSMSTR_1018. Accessed 15 Feb 2023.
  11. Kross A, McNairn H, Lapen D, Sunohara M, Champagne C. 2015. Assessment of RapidEye vegetation indices for estimation of leaf area index and biomass in corn and soybean crops. Int J Appl Earth Observ Geoinf 34: 235-248.
  12. Lee WK, Kim MI, Song CH, Lee SG, Cha SE, Kim GS. 2016. Application of Remote Sensing and Geographic Information System in Forest Sector. J Cadastre Land InformatiX 46: 27-42.
  13. Li W, Li Y, Gong J, Feng Q, Zhou J, Sun J, Shi C, Hu W. 2021. Urban Water Extraction with UAV High-Resolution Remote Sensing Data Based on an Improved U-Net Model. Remote Sens 13: 3165.
  14. Loshchilov I, Hutter F. 2018. Fixing Weight Decay Regularization in Adam. https://openreview.net/forum?id=rk6qdGgCZ. Accessed 15 Feb 2024.
  15. Ministry of Land, Infrastructure and Transport. 2023. Cadastral Statistics. https://stat.molit.go.kr/portal/cate/statMetaView.do?hRsId=24. Accessed 15 Feb 2023.
  16. Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B, Rueckert D. 2018. Attention U-Net: Learning Where to Look for the Pancreas. arXiv doi: 10.48550/arXiv.1804.03999.
  17. Park EB, Song CH, Ham BY, Kim JW, Lee JY, Choi SE, Lee WK. 2018. Comparison of Sampling and Wall-to-Wall Methodologies for Reporting the GHG Inventory of the LULUCF Sector in Korea. J Clim Chang Res 9: 385-398. 
  18. Ronneberger O, Fischer P, Brox T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 (Navab N, Hornegger J, Wells W, Frangi A, eds). Springer, Cham, pp 234-241.
  19. Rouhi R, Jafari M, Kasaei S, Keshavarzian P. 2015. Benign and malignant breast tumors classification based on region growing and CNN segmentation. Expert Syst Appl 42: 990-1002.
  20. Rumelhart DE, Hinton GE, Williams RJ. 1986. Learning representations by back-propagating errors. Nature 323: 533-536. 
  21. Smith LN, Topin N. 2019. Super-convergence: very fast training of neural networks using large learning rates. SPIE 11006: 369-386.
  22. Solorzano JV, Mas JF, Gao Y, Gallardo-Cruz JA. 2021. Land Use Land Cover Classification with U-Net: Advantages of Combining Sentinel-1 and Sentinel-2 Imagery. Remote Sens 13: 3600.
  23. Son SH, Lee SH, Bae JG, Ryu MJ, Lee DI, Park SR, Seo DJ, Kim JS. 2022. Land-Cover-Change Detection with Aerial Orthoimagery Using SegNet-Based Semantic Segmentation in Namyangju City, South Korea. Sustainability 14: 12321.
  24. Woo HS, Cho SW, Jung GH, Park JW. 2019. Precision Forestry Using Remote Sensing Techniques: Opportunities and Limitations of Remote Sensing Application in Forestry. Korean J Remote Sens 35: 1067-1082.
  25. Zhang P, Ke Y, Zhang Z, Wang M, Li P, Zhang S. 2018. Urban Land Use and Land Cover Classification Using Novel Deep Learning Models Based on High Spatial Resolution Satellite Imagery. Sensors 18: 3717. 
  26. Zheng X, Han L, He G, Wang N, Wang G, Feng L. 2023. Semantic Segmentation Model for Wide-Area Coseismic Landslide Extraction Based on Embedded Multichannel Spectral-Topographic Feature Fusion: A Case Study of the Jiuzhaigou Ms7.0 Earthquake in Sichuan, China. Remote Sens 15: 1084.
  27. Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. 2018. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support (Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L, Tavares JMRS, Bradley A, Papa JP, Belagiannis V, Nascimento JC, Lu Z, Conjeti S, Moradi M, Greenspan H, Madabhushi A, eds). Springer, Cham, pp 3-11.