Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins
Quick Take
This study compares an encoder-only Transformer and LSTM for upstream streamflow prediction in ungauged basins, revealing that LSTM outperforms Transformer in both configurations. Incorporating downstream data enhances performance, increasing median NNSE by over 60%, indicating that recurrent memory is more effective for hydrologic sequence inference.
Key Points
- LSTM outperformed Transformer in upstream streamflow inference across two configurations.
- Incorporating downstream information increased median NNSE by over 60%.
- The study emphasizes architectural inductive bias for hydrologic sequence inference.
- Recurrent memory aligns better with upstream reconstruction tasks than Transformer.
- Downstream context significantly improves prediction skill across models.
Article Content
From source RSS / original summaryarXiv:2606. 02791v1 Announce Type: new Abstract: Watershed networks exhibit convergent topologies in which multiple tributaries merge into downstream channels,integrating diverse upstream hydrological processes. In ungauged basins, the absence of direct observations increases uncertainty and limits the ability to anticipate extreme events.
This study evaluates whether an encoder-only Transformer provides an advantage over an LSTM for upstream streamflow inference under limited hydrologic information, using retrospective simulations from the NOAA National Water Model (NWM). Across both upstream-only and combined configurations, the LSTM showed stronger overall performance than the Transformer model across the two configurations. Incorporating downstream information further boosted performance for all models, increasing median NNSE by more than 60%.
Rather than treating this as a leaderboard-style comparison, we interpret the experiments as a test of architectural inductive bias for hydrologic sequence inference. The results indicate that recurrent memory remains better aligned with this upstream reconstruction task than an encoder-only Transformer, while downstream hydrologic context provides a strong auxiliary constraint that substantially improves prediction skill across architectures
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
AuditFlow introduces a multi-agent framework for structured financial reporting verification, achieving 82.09% accuracy with GPT-5.5, outperforming the baseline by 14.93 points. It utilizes a symbolic environment for effective audit processes, demonstrating the necessity of deterministic checks for reliable verification.