Analysis and Prediction of Factors Affecting Marine Chlorophyll Based on Gray Correlation and Random Forest Modeling

Xiaoyi Liu

doi:10.54097/hj70qg35

Authors

Xiaoyi Liu

DOI:

https://doi.org/10.54097/hj70qg35

Keywords:

Marine Chlorophyll, Grey Correlation Analysis, Spearman Correlation Coefficient, Random Forest Model.

Abstract

In this paper, the relationship between marine chlorophyll content and environmental factors is deeply investigated by utilizing ocean observation big data. Through data preprocessing, gray correlation analysis, Spearman correlation analysis and random forest modeling, this study identified the key factors affecting the chlorophyll content. The results showed that carbon dioxide levels, seawater temperature, salinity, pH and dissolved oxygen were the key environmental drivers, with carbon dioxide and temperature being significantly negatively correlated with chlorophyll content. These findings emphasize the potential role of marine chlorophyll and associated aquaculture in carbon sequestration. This work provides valuable insights into marine resource management and ecological conservation, providing a scientific basis for further research and policy development.

References

[1] Zhang Z, Qiu B, Klein P, et al. The influence of geostrophic strain on oceanic ageostrophic motion and surface chlorophyll[J].Nature Communications, 2019, 10(1):1-11.

[2] AlHossainy H R, Saber A, Ghany E A R, et al. Inferring Bathymetry from Sentinel-2 Satellite Images Using Machine Learning Algorithms Based on Chlorophyll Concentration Data in the Absence of Ground Measurement[J]. Arabian Journal for Science and Engineering, 2025, (prepublish): 1-18.

[3] Wen J, Yang J, Jiang B, et al. Big data driven marine environment information forecasting: a time series prediction network[J]. IEEE Transactions on Fuzzy Systems, 2020, 29(1): 4-18.

[4] 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.

[5] Ke P, Gui X, Cao W, et al. Near-real-time monitoring of global ocean carbon sink based on CNN[R]. Copernicus Meetings, 2024.

[6] Jin Y, Zhang F, Wang X, et al. Multi-Step Forecasting of Chlorophyll Concentration with Multi-Attention Collaborative Network[J].Journal of Marine Science and Engineering, 2025, 13(1): 151-151.

[7] Yuan T, Zhang J, YangS, et al. Vertical Structures of Marine Heatwaves in the South China Sea: Characteristics, Drivers and Impacts on Chlorophyll Concentration[J]. Journal of Geophysical Research: Oceans, 2024, 129(12): e2024JC021091-e2024JC021091.

[8] Francisco G, Isabel F, Lidia Y, et al. Two decades of satellite surface chlorophyll a concentration (1998–2019) in the Spanish Mediterranean marine waters (Western Mediterranean Sea): Trends, phenology and eutrophication assessment[J]. Remote Sensing Applications: Society and Environment, 2022, 28.