Decoding Flow-Ecology Relationships: A Machine Learning Framework for flow Regime Characterization and Riparian Vegetation Prediction
Fuente:
Zenodo
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Recurso digital |
| Sprache: | Englisch |
| Veröffentlicht: |
Zenodo
2025
|
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866902026695213056 |
|---|---|
| author | Yifan, Huang |
| author_facet | Yifan, Huang |
| contents | <p> </p> <p>Flow regimes, characterized by magnitude and seasonality dynamics, exert critical controls on ecological communities across spatial scales, with growing alterations from climate change and anthropogenic interventions. Effective ecological restoration requires advancing mechanistic understanding of flow-ecology relationships across time.</p> <p>This study presents a hybrid attribution framework integrating seasonality analysis and machine learning to explore drivers of flow-ecology coupling in China's Han River Basin.By integrating structural equation modeling and machine learning principles, we propose induced machine learning models to establish flow-ecology relationships, achieving R² of 0.8 in simulating riverine NDVI. Employing optimized LSTM-Transformer models (NSE>0.95), we project flow patterns, and predict vegetation responses under SSP245 and SSP585 scenarios (2025-2035) based on induced machine learning.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_14799026 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Decoding Flow-Ecology Relationships: A Machine Learning Framework for flow Regime Characterization and Riparian Vegetation Prediction Yifan, Huang <p> </p> <p>Flow regimes, characterized by magnitude and seasonality dynamics, exert critical controls on ecological communities across spatial scales, with growing alterations from climate change and anthropogenic interventions. Effective ecological restoration requires advancing mechanistic understanding of flow-ecology relationships across time.</p> <p>This study presents a hybrid attribution framework integrating seasonality analysis and machine learning to explore drivers of flow-ecology coupling in China's Han River Basin.By integrating structural equation modeling and machine learning principles, we propose induced machine learning models to establish flow-ecology relationships, achieving R² of 0.8 in simulating riverine NDVI. Employing optimized LSTM-Transformer models (NSE>0.95), we project flow patterns, and predict vegetation responses under SSP245 and SSP585 scenarios (2025-2035) based on induced machine learning.</p> |
| title | Decoding Flow-Ecology Relationships: A Machine Learning Framework for flow Regime Characterization and Riparian Vegetation Prediction |
| url | https://doi.org/10.5281/zenodo.14799026 |