Significant Improvement in Short-Term Green-Tide Transport Predictions Using the XGBoost Model
Open Access
- 5 May 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (9) , 1636
Abstract
Accurately predicting the drift trajectory of green tides is crucial for assessing potential risks and implementing effective countermeasures. This paper proposes a short-term green-tide drift prediction method that combines green-tide patch characteristics, 1 h interval drift distances from GOCI-II images, and driving-factor data using the XGBoost machine learning model to enhance prediction accuracy. The results demonstrate that the proposed method outperforms the traditional OpenDrift model in short-term predictions. Specifically, at time intervals of 3, 5, and 7 h, the root mean square errors (RMSEs) of the OpenDrift model in the zonal direction are 1.81 km, 2.89 km, and 3.55 km, respectively, whereas the RMSEs of the proposed method are 0.80 km, 0.98 km, and 1.20 km, respectively; in the meridional direction, the RMSEs of the OpenDrift model are 1.77 km, 2.67 km, and 3.10 km, while the RMSEs for the proposed method are 0.82 km, 1.10 km, and 1.25 km, respectively. Furthermore, the proposed XGBoost method more-accurately tracks the actual positions of green-tide patches compared to the OpenDrift model. Specifically, at the 25 h interval, the proposed method continues to accurately predict patch positions, while the OpenDrift model exhibits significant deviations. This study demonstrates that the proposed method, by learning drift patterns from historical data, effectively predicts the short-term drift process of green tides. It provides valuable support for early warning systems, thereby helping to mitigate the ecological and economic impacts of green-tide disasters.Keywords
Funding Information
- National Natural Science Foundation (42130405, JSSCTD202346)
- Innovative and Entrepreneurial Talent Program of Jiangsu Province (42130405, JSSCTD202346)
This publication has 40 references indexed in Scilit:
- Review of the development of the green tide and the process of control in the southern Yellow Sea in 2022Estuarine, Coastal and Shelf Science, 2024
- A multi-module with a two-way feedback method for Ulva drift-diffusionActa Oceanologica Sinica, 2023
- Parameterization Method of Wind Drift Factor Based on Deep Learning in the Oil Spill ModelJournal of Ocean University of China, 2023
- Where does floating Sargassum in the East China Sea come from?Harmful Algae, 2023
- Estimating Ulva prolifera green tides of the Yellow Sea through ConvLSTM data fusionEnvironmental Pollution, 2023
- Analysis of environmental factors affecting the large-scale long-term sequence of green tide outbreaks in the Yellow SeaEstuarine, Coastal and Shelf Science, 2021
- Dynamic Diurnal Changes in Green Algae Biomass in the Southern Yellow Sea Based on GOCI ImagesJournal of Ocean University of China, 2020
- Tempo-spatial dynamics of water quality and its response to river flow in estuary of Taihu Lake based on GOCI imageryEnvironmental Science and Pollution Research, 2017
- Who made the world's largest green tide in China?—an integrated study on the initiation and early development of the green tide in Yellow SeaLimnology and Oceanography, 2015
- The world's largest macroalgal bloom in the Yellow Sea, China: Formation and implicationsEstuarine, Coastal and Shelf Science, 2013