Factors Influencing and Predicting Marine Chlorophyll Content
DOI:
https://doi.org/10.6919/ICJE.202505_11(5).0019Keywords:
Marine Carbon Sinks; Chlorophyll Content; Machine Learning; Environmental Factors; Random Forests.Abstract
Marine chlorophyll content plays an important role in the global carbon cycle and climate change regulation. Based on machine learning and data mining techniques, this paper explores its key influencing factors and constructs a prediction model. Gray correlation analysis and Spearman's rank correlation coefficient method are used to screen out the main environmental variables, such as carbon dioxide concentration, pH, salinity, temperature and dissolved oxygen, and the Random Forest Model is used to analyze the importance of the characteristics and predict the future trend. The results showed that the chlorophyll content was significantly correlated with the environmental factors, especially affected by CO2 concentration. The results of the study can provide data support and scientific basis for the management of ocean carbon sinks and climate change response strategies.
Downloads
References
[1] Orr J C, Fabry V J, Aumont O, et al. Anthropogenic ocean acidification over the twenty-first century and its impact on calcifying organisms [J]. Nature, 2005, 437(7059): 681-686.
[2] Ryther J H ,Yentsch C S. The estimation of phytoplankton production in the ocean from chlorophyll and light data. Limnology and Oceanography,1957,2( 3) : 281-286.
[3] Jiang Y, Zhang T, Gou Y, et al. High-resolution temperature and salinity model analysis using support vector regression[J]. Journal of Ambient Intelligence and Humanized Computing, 2018:1-9.
[4] Gou Y, Liu J, Zhang T. KNN regression model-based refinement of thermohaline data[C]//Proceedings of the Thirteenth ACM International Conference on Underwater Networks & Systems. 2018:1-8.
[5] Li Z, Wang J, Cao D, et al. Investigating Neural Activation Effects on Deep Belief Echo-State Networks for Prediction Toward Smart Ocean Environment Monitoring[J]. Arabian Journal for Science and Engineering, 2021, 46(4):3913-3923.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
