Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918159257174016 |
|---|---|
| author | Nie, Wanshu Kumar, Sujay V. Chen, Junyu Zhao, Long Skulovich, Olya Yoo, Jinwoong Pflug, Justin Ahmad, Shahryar Khalique Konapala, Goutam |
| author_facet | Nie, Wanshu Kumar, Sujay V. Chen, Junyu Zhao, Long Skulovich, Olya Yoo, Jinwoong Pflug, Justin Ahmad, Shahryar Khalique Konapala, Goutam |
| contents | Recent advances in machine learning such as Long Short-Term Memory (LSTM) models and Transformers have been widely adopted in hydrological applications, demonstrating impressive performance amongst deep learning models and outperforming physical models in various tasks. However, their superiority in predicting land surface states such as terrestrial water storage (TWS) that are dominated by many factors such as natural variability and human driven modifications remains unclear. Here, using the open-access, globally representative HydroGlobe dataset - comprising a baseline version derived solely from a land surface model simulation and an advanced version incorporating multi-source remote sensing data assimilation - we show that linear regression is a robust benchmark, outperforming the more complex LSTM and Temporal Fusion Transformer for TWS prediction. Our findings highlight the importance of including traditional statistical models as benchmarks when developing and evaluating deep learning models. Additionally, we emphasize the critical need to establish globally representative benchmark datasets that capture the combined impact of natural variability and human interventions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10799 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage Nie, Wanshu Kumar, Sujay V. Chen, Junyu Zhao, Long Skulovich, Olya Yoo, Jinwoong Pflug, Justin Ahmad, Shahryar Khalique Konapala, Goutam Machine Learning Atmospheric and Oceanic Physics Geophysics Recent advances in machine learning such as Long Short-Term Memory (LSTM) models and Transformers have been widely adopted in hydrological applications, demonstrating impressive performance amongst deep learning models and outperforming physical models in various tasks. However, their superiority in predicting land surface states such as terrestrial water storage (TWS) that are dominated by many factors such as natural variability and human driven modifications remains unclear. Here, using the open-access, globally representative HydroGlobe dataset - comprising a baseline version derived solely from a land surface model simulation and an advanced version incorporating multi-source remote sensing data assimilation - we show that linear regression is a robust benchmark, outperforming the more complex LSTM and Temporal Fusion Transformer for TWS prediction. Our findings highlight the importance of including traditional statistical models as benchmarks when developing and evaluating deep learning models. Additionally, we emphasize the critical need to establish globally representative benchmark datasets that capture the combined impact of natural variability and human interventions. |
| title | Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage |
| topic | Machine Learning Atmospheric and Oceanic Physics Geophysics |
| url | https://arxiv.org/abs/2510.10799 |