Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea

Choi, Youngjin; Park, Youngmin; Lim, Weol-Ae; Min, Seung-Hwan; Lee, Joon-Soo

doi:10.3390/jmse10010031

Open AccessArticle

Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea

by

Youngjin Choi

¹,

Youngmin Park

¹

,

Weol-Ae Lim

²,

Seung-Hwan Min

¹ and

Joon-Soo Lee

^3,*

¹

Geosystem Research Inc., Gunpo 15807, Korea

²

Research and Development Planning Division, National Institute of Fisheries Science, Busan 46083, Korea

³

Ocean Climate and Ecology Research Division, National Institute of Fisheries Science, Busan 46083, Korea

^*

Author to whom correspondence should be addressed.

J. Mar. Sci. Eng. 2022, 10(1), 31; https://doi.org/10.3390/jmse10010031

Submission received: 27 October 2021 / Revised: 19 December 2021 / Accepted: 21 December 2021 / Published: 29 December 2021

(This article belongs to the Special Issue “Coastal Dynamics, Hazards, and Numerical Modelling” in Memory of Prof. Byung Ho Choi)

Download

Browse Figures

Versions Notes

Abstract

In this study, the occurrence of Cochlodinium polykrikoides bloom was predicted based on spatial information. The South Sea of Korea (SSK), where C. polykrikoides bloom occurs every year, was divided into three concentrated areas. For each domain, the optimal model configuration was determined by designing a verification experiment with 1–3 convolutional neural network (CNN) layers and 50–300 training times. Finally, we predicted the occurrence of C. polykrikoides bloom based on 3 CNN layers and 300 training times that showed the best results. The experimental results for the three areas showed that the average pixel accuracy was 96.22%, mean accuracy was 91.55%, mean IU was 81.5%, and frequency weighted IU was 84.57%, all of which showed above 80% prediction accuracy, indicating the achievement of appropriate performance. Our results show that the occurrence of C. polykrikoides bloom can be derived from atmosphere and ocean forecast information.

Keywords: Cochlodinium polykrikoides; convolution neural network (CNN); prediction; South Sea of Korea (SSK)

Share and Cite

MDPI and ACS Style

Choi, Y.; Park, Y.; Lim, W.-A.; Min, S.-H.; Lee, J.-S. Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea. J. Mar. Sci. Eng. 2022, 10, 31. https://doi.org/10.3390/jmse10010031

AMA Style

Choi Y, Park Y, Lim W-A, Min S-H, Lee J-S. Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea. Journal of Marine Science and Engineering. 2022; 10(1):31. https://doi.org/10.3390/jmse10010031

Chicago/Turabian Style

Choi, Youngjin, Youngmin Park, Weol-Ae Lim, Seung-Hwan Min, and Joon-Soo Lee. 2022. "Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea" Journal of Marine Science and Engineering 10, no. 1: 31. https://doi.org/10.3390/jmse10010031

APA Style

Choi, Y., Park, Y., Lim, W.-A., Min, S.-H., & Lee, J.-S. (2022). Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea. Journal of Marine Science and Engineering, 10(1), 31. https://doi.org/10.3390/jmse10010031

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI