Saved in:
Bibliographic Details
Main Authors: Taccari, Maria Luisa, Tazi, Kenza, Morrison, Oisín M., Grafberger, Andreas, Colonese, Juan, de Wiart, Corentin Carton, Prudhomme, Christel, Mazzetti, Cinzia, Chantry, Matthew, Pappenberger, Florian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16579
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918344021508096
author Taccari, Maria Luisa
Tazi, Kenza
Morrison, Oisín M.
Grafberger, Andreas
Colonese, Juan
de Wiart, Corentin Carton
Prudhomme, Christel
Mazzetti, Cinzia
Chantry, Matthew
Pappenberger, Florian
author_facet Taccari, Maria Luisa
Tazi, Kenza
Morrison, Oisín M.
Grafberger, Andreas
Colonese, Juan
de Wiart, Corentin Carton
Prudhomme, Christel
Mazzetti, Cinzia
Chantry, Matthew
Pappenberger, Florian
contents 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 novel two-stage training 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) control forecasts (2016-2019) to adapt to the specific error structures and biases of operational numerical weather prediction. 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 is highly competitive with current state-of-the-art global systems, achieving comparable accuracy while maintaining a transparent and reproducible forcing pipeline. The model demonstrates exceptional reliability in extreme-event detection, providing a streamlined and operationally robust baseline for the global hydrological community.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16579
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AIFL: A Global Daily Streamflow Forecasting Model Using Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS
Taccari, Maria Luisa
Tazi, Kenza
Morrison, Oisín M.
Grafberger, Andreas
Colonese, Juan
de Wiart, Corentin Carton
Prudhomme, Christel
Mazzetti, Cinzia
Chantry, Matthew
Pappenberger, Florian
Machine Learning
Artificial Intelligence
Applied Physics
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 novel two-stage training 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) control forecasts (2016-2019) to adapt to the specific error structures and biases of operational numerical weather prediction. 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 is highly competitive with current state-of-the-art global systems, achieving comparable accuracy while maintaining a transparent and reproducible forcing pipeline. The model demonstrates exceptional reliability in extreme-event detection, providing a streamlined and operationally robust baseline for the global hydrological community.
title AIFL: A Global Daily Streamflow Forecasting Model Using Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS
topic Machine Learning
Artificial Intelligence
Applied Physics
url https://arxiv.org/abs/2602.16579