Cite this paper:
Shi Suixiang, Wang lei, Yu Xuan, Xu Lingyu. Application of long term and short term memory neural network in prediction of chlorophyll a concentration[J]. Haiyang Xuebao, 2020, 42(2): 134-142

Application of long term and short term memory neural network in prediction of chlorophyll a concentration

Shi Suixiang1, Wang lei1,2, Yu Xuan3, Xu Lingyu3
1. Key Laboratory of Digital Ocean, National Marine Data and Information Service, Tianjin 300171, China;
2. East Sea Information Center of State Oceanic Administration, Shanghai 200136, China;
3. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Prediction of chlorophyll a concentration in traditional artificial network methods has some disadvantages, such as slower training speed, lower convergence precision, and easy to fall into local optimum situation. In particular, it is not possible to flexibly use historical information of any length to predict chlorophyll a concentration. To solve these problems, this paper defines the relationship between chlorophyll a concentration and various elements, depending on the long-term and short-term dependence between elements and the concentration of chlorophyll a. In this way, the long-term dependence between each element and the chlorophyll a concentration is separated from the short-term dependence. Then, based on the Long Short-Term Memory (LSTM), a merged LSTM prediction model was proposed. In this model, short and long term dependencies were presented respectively by different neurons and finally merged at the top of the model. The experimental data involves the continuous monitoring data of the station of Sandu Ao. The main result includes that the model has the advantage of fast reduction of training error, but also has significantly higher prediction accuracy compared with other three classical neural network models.
Key words:    chlorophyll a    Merged-LSTM    multi-factors    neural network   
Received: 2019-03-12   Revised: 2019-06-28
PDF (4782 KB) Free
Print this page
Add to favorites
Articles by Shi Suixiang
Articles by Wang lei
Articles by Yu Xuan
Articles by Xu Lingyu
[1] br>Shi Rui, Zhang Hong, Yue Rong, et al. A wavelet theory based remote sensing inversion of chlorophyll a concentrations for inland lakes in arid areas using TM image data[J]. Acta Ecologica Sinica, 2017, 37(3):1043-1053
[2] br>Luo Jianmei, Huo Yongwei, Han Xiaoqing. Inversion of chlorophyll a concentration in offshore Ⅱ. waters using HJ satellite data——Example in the north of the Luanhe Delta[J]. Haiyang Xuebao, 2017, 39(4):117-129
[3] br>Sheng Lin, Chen Jing, Liu Rui, et al. A method of water quality analysis:chlorophyll a concentration estimation of Dongping Lake based on GOCI image[J]. Environmental Protection, 2017, 45(10):60-63
[4] Vollenweider R A. Scientific fundamentals of the eutrophication of lakes and flowing waters, with particular reference to nitrogen and phosphorus as factors in eutrophication[R]. Paris, France:OECD, 1968.
[5] Jørgensen S E, Mejer H, Friis M. Examination of a lake model[J]. Ecological Modelling, 1978, 4(2/3):253-278.
[6] br>Mao Jiangmei, Chen Xinjun, Yu Jing. Forecasting fishing ground of Thunnus alalunga based on BP neural network in the South Pacific Ocean[J]. Haiyang Xuebao, 2016, 38(10):34-43
[7] br>Zhao Yuqin, Wang Xili, Jiang Sai. Study on neural network model for Weihe River water quality retrieving using remote-sensing image[J]. Remote Sensing Technology and Application, 2009, 24(1):63-67
[8] br>Lu Zhijuan, Zhu Ling, Pei Hongping, et al. The model of chlorophyll a concentration forecast in the West Lake based on wavelet analysis and BP neural networks[J]. Acta Ecologica Sinica, 2008, 28(10):4965-4973
[9] br>Zhou Luhong, Gu Xiaohong, Zeng Qingfei, et al. Applications of back propagation neural network for short-term prediction of chlorophyll a concentration in different regions of Lake Taihu[J]. Journal of Hydroecology, 2012, 33(4):1-6
[10] br>Yang Liu, Han Yu, Wang Zumao, et al. Study on retrieval model of water quality parameter in Wenyu River based on BP neural network[J]. Journal of Water Resources and Water Engineering, 2013, 24(6):25-28
[11] br>Tong Yuhua, Zhou Hongliang, Huang Zhefeng, et al. Time series prediction of the concentration of chlorophyll a based on RBF neural network with parameters self-optimizing[J]. Acta Ecologica Sinica, 2011, 31(22):6788-6795
[12] Dekker A G, Brando V E, Anstee J M, et al. Imaging Spectrometry of Water[M]//van der Meer F D, de Jong S M. Imaging Spectrometry:Basic Principles and Prospective Applications. Dordrecht:Springer, 2002:307-359.
[13] br>Chai Yongqiang, Shao Fengjing, Sun Rencheng, et al. The intelligent detection technology of redtide from modis imagery based on decision tree[J]. Journal of Qingdao University:Natural Science Edition, 2012, 25(2):47-52
[14] br>Li Xiuzhu, Su Rongguo, Zhang Chuansong, et al. A Chl a prediction model based on support vector machine in Yangtze River estuaries and its Adjacent sea areas[J]. Periodical of Ocean University of China, 2019, 49(1):69-76
[15] br>Zhong Lingshu. Overhead line status data mining based on ARIMA-LSTM[D]. Guangzhou:South China University of Technology, 2016.
[16] Gers F A, Schmidhuber J, Cummins F. Learning to forget:continual prediction with LSTM[C]//Proceedings of the 9th International Conference on Artificial Neural Networks. Edinburgh, UK:IET, 1999.
[17] Graves A. Supervised Sequence Labelling with Recurrent Neural Networks[M]. Heidelberg:Springer, 2012.
[18] Shi Xingjian, Chen Zhourong, Wang Hao, et al. Convolutional LSTM network:a machine learning approach for precipitation nowcasting[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada:MIT Press, 2015.
[19] Yang Yuting, Dong Junyu, Sun Xin, et al. A CFCC-LSTM model for sea surface temperature prediction[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(2):207-211.
[20] Greff K, Srivastava R K, Koutnik J, et al. LSTM:a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10):2222-2232.
[21] Ma Xuezhe, Hovy E. End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF[M]. Stroudsburg:Association for Computational Linguistics, 2016.
[22] Ordóñez J F, Roggen D. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition[J]. Sensors, 2016, 16(1):115.
[23] Gers F A, Eck D, Schmidhuber J. Applying LSTM to time series predictable through time-window approaches[C]//Proceedings of the International Conference on Artificial Neural Networks. Vienna, Austria:Springer, 2001:669−676.
Haiyang Xuebao