Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.05260 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915433555165184 |
|---|---|
| author | Qian, Zhouyao Chen, Yang Li, Baodian Zhang, Shuyi Tian, Zhen Wang, Gongsen Gu, Tianyue Zhou, Xinyu Chen, Huilin Li, Xinyi Zhu, Hao Zhang, Shuyao Li, Zongheng Wang, Siyuan |
| author_facet | Qian, Zhouyao Chen, Yang Li, Baodian Zhang, Shuyi Tian, Zhen Wang, Gongsen Gu, Tianyue Zhou, Xinyu Chen, Huilin Li, Xinyi Zhu, Hao Zhang, Shuyao Li, Zongheng Wang, Siyuan |
| contents | Marine chlorophyll concentration is an important indicator of ecosystem health and carbon cycle strength, and its accurate prediction is crucial for red tide warning and ecological response. In this paper, we propose a LSTM-RF hybrid model that combines the advantages of LSTM and RF, which solves the deficiencies of a single model in time-series modelling and nonlinear feature portrayal. Trained with multi-source ocean data(temperature, salinity, dissolved oxygen, etc.), the experimental results show that the LSTM-RF model has an R^2 of 0.5386, an MSE of 0.005806, and an MAE of 0.057147 on the test set, which is significantly better than using LSTM (R^2 = 0.0208) and RF (R^2 =0.4934) alone , respectively. The standardised treatment and sliding window approach improved the prediction accuracy of the model and provided an innovative solution for high-frequency prediction of marine ecological variables. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Marine Chlorophyll Prediction and Driver Analysis based on LSTM-RF Hybrid Models Qian, Zhouyao Chen, Yang Li, Baodian Zhang, Shuyi Tian, Zhen Wang, Gongsen Gu, Tianyue Zhou, Xinyu Chen, Huilin Li, Xinyi Zhu, Hao Zhang, Shuyao Li, Zongheng Wang, Siyuan Machine Learning Artificial Intelligence Marine chlorophyll concentration is an important indicator of ecosystem health and carbon cycle strength, and its accurate prediction is crucial for red tide warning and ecological response. In this paper, we propose a LSTM-RF hybrid model that combines the advantages of LSTM and RF, which solves the deficiencies of a single model in time-series modelling and nonlinear feature portrayal. Trained with multi-source ocean data(temperature, salinity, dissolved oxygen, etc.), the experimental results show that the LSTM-RF model has an R^2 of 0.5386, an MSE of 0.005806, and an MAE of 0.057147 on the test set, which is significantly better than using LSTM (R^2 = 0.0208) and RF (R^2 =0.4934) alone , respectively. The standardised treatment and sliding window approach improved the prediction accuracy of the model and provided an innovative solution for high-frequency prediction of marine ecological variables. |
| title | Marine Chlorophyll Prediction and Driver Analysis based on LSTM-RF Hybrid Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.05260 |