Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.2.2.6

Deep Learning Based Floating Macroalgae Classification Using Gaofen-1 WFV Images  

Kim, Euihyun (Korea Ocean Satellite Center, Korea Institute of Ocean Science & Technology)
Kim, Keunyong (Korea Ocean Satellite Center, Korea Institute of Ocean Science & Technology)
Kim, Soo Mee (Maritime ICT R&D Center, Korea Institute of Ocean Science & Technology)
Cui, Tingwei (Ministry of Natural Resources, China First Institute of Oceanography)
Ryu, Joo-Hyung (Korea Ocean Satellite Center, Korea Institute of Ocean Science & Technology)
Publication Information
Korean Journal of Remote Sensing / v.36, no.2_2, 2020 , pp. 293-307 More about this Journal
Abstract
Every year, the floating macroalgae, green and golden tide, are massively detected at the Yellow Sea and East China Sea. After influx of them to the aquaculture facility or beach, it occurs enormous economic losses to remove them. Currently, remote sensing is used effectively to detect the floating macroalgae flowed into the coast. But it has difficulties to detect the floating macroalgae exactly because of the wavelength overlapped with other targets in the ocean. Also, it is difficult to distinguish between green and golden tide because they have similar spectral characteristics. Therefore, we tried to distinguish between green and golden tide applying the Deep learning method to the satellite images. To determine the network, the optimal training conditions were searched to train the AlexNet. Also, Gaofen-1 WFV images were used as a dataset to train and validate the network. Under these conditions, the network was determined after training, and used to confirm the test data. As a result, the accuracy of test data is 88.89%, and it can be possible to distinguish between green and golden tide with precision of 66.67% and 100%, respectively. It is interpreted that the AlexNet can be pick up on the subtle differences between green and golden tide. Through this study, it is expected that the green and golden tide can be effectively classified from various objects in the ocean and distinguished each other.
Keywords
Deep learning; Transfer learning; AlexNet; Green and Golden tide; Gaofen-1 WFV;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Ye, N.H., X.W. Zhang, Y.Z. Mao, C.W. Liang, D. Xu, J. Zou, Z.M. Zhuang, and Q.Y. Wang, 2011. 'Green tides' are overwhelming the coastline of our blue planet: taking the world's largest example, Ecological Research, 26(3): 477.   DOI
2 Zhang, J., J. Shi, S. Gao, Y. Huo, J. Cui, H. Shen, G. Liu, and P. He, 2019. Annual patterns of macroalgal blooms in the Yellow Sea during 2007-2017, PloS One, 14(1).
3 Zhang, J., Y. Huo, H. Wu, K. Yu, J.K. Kim, C. Yarish, Y. Qin, C. Liu, R. Xu, and P. He, 2014. The origin of the Ulva macroalgal blooms in the Yellow Sea in 2013, Marine Pollution Bulletin, 89: 276-283.   DOI
4 Garcia, R.A., P. Fearns, J.K. Keesing, and D. Liu, 2013. Quantification of floating macroalgae blooms using the scaled algae index, Journal of Geophysical Research: Oceans, 118(1): 26-42.   DOI
5 Cui, T., F. Li, Y. Wei, X. Yang, Y. Xiao, X. Chen, R. Liu, Y. Ma, and J. Zhang, 2020. Super-resolution optical mapping of floating macroalgae from geostationary orbit, Applied Optics, 59(10): C70-C77.   DOI
6 Cui, T., J. Zhang, L.E. Sun, Y.J. Jia, W. Zhao, Z.L. Wang, and J.M. Meng, 2012. Satellite monitoring of massive green macroalgae bloom (GMB): imaging ability comparison of multi-source data and drifting velocity estimation, International Journal of Remote Sensing, 33(17): 5513-5527.   DOI
7 Dhillon, A. and G.K. Verma, 2019. Convolutional neural network: a review of models, methodologies and applications to object detection, Progress in Artificial Intelligence, 1-28.
8 Hu, L., C. Hu, and H.E. Ming-Xia, 2017. Remote estimation of biomass of Ulva prolifera macroalgae in the Yellow Sea, Remote Sensing of Environment, 192: 217-227.   DOI
9 Hu, C., 2009. A novel ocean color index to detect floating algae in the global oceans, Remote Sensing of Environment, 113(10): 2118-2129.   DOI
10 Hu, C., L. Feng, R.F. Hardy, and E.J. Hochberg, 2015. Spectral and spatial requirements of remote measurements of pelagic Sargassum macroalgae, Remote Sensing of Environment, 167: 229-246.   DOI
11 Hwang, E.K., S.J. Lee, D.S. Ha, and C.S. Park, 2016. Sargassum golden tides in the Shinan-gun and Jeju Island, Korea, Korean Journal of Fisheries and Aquatic Sciences, 49(5): 689-693 (in Korea with English abstract).   DOI
12 Kim, K., J. Shin, and J.H. Ryu, 2018. Application of multi-satellite sensors to estimate the green-tide area, Korean Journal of Remote Sensing, 34(2-2): 339-349 (in Korean with English abstract).   DOI
13 Liu, D., J.K. Keesing, P. He, Z. Wang, Y. Shi, and Y. Wang, 2013. The world's largest macroalgal bloom in the Yellow Sea, China: formation and implications, Estuarine, Coastal and Shelf Science, 129: 2-10.   DOI
14 Krizhevsky, A., I. Sutskever, and G.E. Hinton, 2012. Imagenet classification with deep convolutional neural networks, Proc. of 26th Annual Conference on Neural Information Processing Systems, Siem Reap, Cambodia, Dec. 3-8, vol. 1, pp. 1097-1105.
15 Kwon, H.K., H. Kang, Y.H. Oh, S.R. Park, and G. Kim, 2017. Green tide development associated with submarine groundwater discharge in a coastal harbor, Jeju, Korea, Scientific Reports, 7(1): 1-9.
16 Kwon, K., B.J. Choi, K.Y. Kim, and K. Kim, 2019. Tracing the trajectory of pelagic Sargassum using satellite monitoring and Lagrangian transport simulations in the East China Sea and Yellow Sea, Algae, 34(4): 315-326.   DOI
17 Lee, J.H., I.C. Pang, I.J. Moon, and J.H. Ryu, 2011. On physical factors that controlled the massive green tide occurrence along the southern coast of the Shandong Peninsula in 2008: A numerical study using a particle-tracking experiment, Journal of Geophysical Research: Oceans, 116(C12).
18 Liang, X.J., P. Qin, Y.F. Xiao, K.Y. Kim, R.J. Liu, X.Y. Chen, and Q.B. Wang, 2019. Automatic remote sensing detection of floating macroalgae in the Yellow and East China Seas using extreme learning machine, Journal of Coastal Research, 272-281.
19 Min, S.H., J.D. Hwang, H.J. Oh, and Y.B. Son, 2019. Reflectivity characteristics of the green and golden tides from the Yellow Sea and East China Sea, Journal of Coastal Research, 310-316.
20 Mordvintsev, A., C. Olah, and M. Tyka, 2015. Deepdream-a code example for visualizing neural networks, Google Research, 2(5).
21 Kim, K., J. Shin, K.Y. Kim, and J.H. Ryu, 2019. Long-term trend of green and golden tides in the eastern Yellow Sea, Journal of Coastal Research, 317-323.
22 Xiao, Y., J. Zhang, T. Cui, J. Gong, R. Liu, X. Chen, and X. Liang, 2019. Remote sensing estimation of the biomass of floating Ulva prolifera and analysis of the main factors driving the interannual variability of the biomass in the Yellow Sea, Marine Pollution Bulletin, 140: 330-340.   DOI
23 Chen, Y.L., J.H. Wan, J. Zhang, Y.J. Ma, L. Wang, J.H. Zhao, and Z.Z. Wang, 2019. Spatial-temporal distribution of golden tide based on high-resolution satellite remote sensing in the South Yellow Sea, Journal of Coastal Research, 90(sp1): 221-227.   DOI
24 Qi, L., C. Hu, M. Wang, S. Shang, and C. Wilson, 2017. Floating algae blooms in the East China Sea, Geophysical Research Letters, 44(22): 11-501.
25 Smetacek, V. and A. Zingone, 2013. Green and golden seaweed tides on the rise, Nature, 504(7478): 84-88.   DOI
26 Son, Y.B., B.J. Choi, Y.H. Kim, and Y.G. Park, 2015. Tracing floating green algae blooms in the Yellow Sea and the East China Sea using GOCI satellite data and Lagrangian transport simulations, Remote Sensing of Environment, 156: 21-33.   DOI
27 Son, Y.B., J.E. Min, and J.H. Ryu, 2012. Detecting massive green algae (Ulva prolifera) blooms in the Yellow Sea and East China Sea using geostationary ocean color imager (GOCI) data, Ocean Science Journal, 47(3): 359-375.   DOI
28 Wang, S., L. Liu, L. Qu, C. Yu, Y. Sun, F. Gao, and J. Dong, 2019. Accurate Ulva prolifera regions extraction of UAV images with superpixel and CNNs for ocean environment monitoring, Neurocomputing, 348: 158-168.   DOI
29 Xiao, J., Z. Wang, H. Song, S. Fan, C. Yuan, M. Fu, X. Miao, X. Zhang, R. Su, and C. Hu, 2020. An anomalous bi-macroalgal bloom caused by Ulva and Sargassum seaweeds during spring to summer of 2017 in the western Yellow Sea, China, Harmful Algae, 93: 101760.   DOI
30 Xing, Q., R. Guo, L. Wu, D. An, M. Cong, S. Qin, and X. Li, 2017. High-resolution satellite observations of a new hazard of golden tides caused by floating Sargassum in winter in the Yellow Sea, IEEE Geoscience and Remote Sensing Letters, 14(10): 1815-1819.   DOI