# AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS

arXiv: https://arxiv.org/abs/2602.16579 · HTML: https://mlsanity.com/paper/2602.16579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 49 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 7 of 7)

- [Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets](https://mlsanity.com/paper/1907.08456/) (2019)
- [HydroNets: Leveraging River Structure for Hydrologic Modeling](https://mlsanity.com/paper/2007.00595/) (2020)
- [Hydra-LSTM: A semi-shared Machine Learning architecture for prediction across Watersheds](https://mlsanity.com/paper/2410.16343/) (2024)
- [RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting](https://mlsanity.com/paper/2505.22535/) (2025)
- [HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space Backbone](https://mlsanity.com/paper/2512.12183/) (2025)
- [Caravan MultiMet: Extending Caravan with Multiple Weather Nowcasts and Forecasts](https://mlsanity.com/paper/2411.09459/) (2024)
- [Fine Flood Forecasts: Incorporating local data into global models through fine-tuning](https://mlsanity.com/paper/2504.12559/) (2025)

## Abstract (arXiv)

Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operational forecast products. This paper introduces AIFL (Artificial Intelligence for Floods), a deterministic LSTM-based model designed for global daily streamflow forecasting. Trained on 18,588 basins curated from the Caravan dataset, AIFL utilises a two-stage transfer-learning strategy to bridge the reanalysis-to-forecast domain shift. The model is first pre-trained on 40 years of ERA5-Land reanalysis (1980-2019) to capture robust hydrological processes, then fine-tuned on operational Integrated Forecasting System (IFS) forecasts (2016-2019) to adapt to the specific error structures and biases of operational numerical weather prediction. Ablation experiments confirm that this two-stage approach outperforms both a naive IFS-only baseline and a mixed-forcing single-stage alternative. To our knowledge, this is the first global model trained end-to-end within the Caravan ecosystem. On an independent temporal test set (2021-2024), AIFL achieves high predictive skill with a median modified Kling-Gupta Efficiency (KGE') of 0.66 and a median Nash-Sutcliffe Efficiency (NSE) of 0.53. Benchmarking results show that AIFL achieves comparable accuracy to current state-of-the-art global systems. The model provides a streamlined and operationally robust baseline for the global hydrological community.